Related
I'm trying to implement a simple addition calculator, but I'm not able to store the input in my array. I'm trying to read char by char because I want to use it later to implement a backend for my B compiler (which has the getchar function that reads char by char from stdin). My code is the fallowing:
segment .data
numb db 0, 0, 0, 0
indx db 0
char db '0'
newl db 0ah
msg1 db 'enter a number: '
len1 equ $ - msg1
segment .text
global _start ; defines the entry point
print: ; push msg; push len
pop eax ; removes caller address from stack
pop edx ; gets length
pop ecx ; gets msg
push eax ; pushes CA to stack again
mov ebx , 01h ; tells that it's an output call
mov eax , 04h ; system call (write)
int 80h ; calls it
ret
getc: ; push add; push len
pop eax ; removes caller address from stack
pop ecx ; gets ouput addrress
push eax ; pushes CA to stack again
mov edx , 01h
mov ebx , 00h ; tells that it's an input call
mov eax , 03h ; system call (read)
int 80h ; calls it
ret
exit:
mov ebx , 0 ; sets exit code
mov eax , 01h ; system call (exit)
int 80h ; calls it
_start:
push msg1
push len1
call print
read:
push char
call getc
mov eax , numb
add eax , indx
mov [eax], dword char
inc byte [indx]
mov eax , char
cmp eax , newl
jne read
jmp exit ; exits program
for now I'm just trying to store the input, because I got segfaults from the complete code, so I started stripping off code until I found the error cause.
You probably don't want to insert the newline in the array, so start with checking for the newline:
read:
push char
call getc
mov al, [char]
cmp al, 10
je done
Then load the byte-sized index in an address register, remembering that AL already contains the datum, so pick another register than EAX. Also, instead of adding the array address numb and the index indx yourself, let the CPU do that for your with an addressing mode that has a displacement component ([numb + ebx]):
movzx ebx, byte [indx]
mov [numb + ebx], al
inc byte [indx]
jmp read
done:
jmp exit
There's also the possibility to define the index indx as a dword with indx dd 0. Then the code becomes:
read:
push char
call getc
mov al, [char]
cmp al, 10
je done
mov ebx, [indx]
mov [numb + ebx], al
inc dword [indx]
jmp read
done:
jmp exit
The lesson here is that NASM is different from MASM in how you address memory:
MASM
mov eax, offset MyVar ; Load address of MyVar
mov eax, MyVar ; Load value stored in MyVar
NASM
mov eax, MyVar ; Load address of MyVar
mov eax, [MyVar] ; Load value stored in MyVar
I asked for help earlier and thought I was home free but I'm not. My logic was wrong and I've greatly altered it. This program is supposed to return the Max int in the array (which also happens to be the last element). After tracing it with GDB a few times, I see that I get to the 5th (2nd to last) element in the array, "20", when I hit a segmentation fault and the program halts. I set ECX to the array length and subtracted 1 from ECX to avoid this, but my logic is obviously wrong. Am I wrong in depending on the ECX counter to terminate the loop. Any ideas please?
***EDIT MAJOR EDITS TO CODE
SECTION .data ;data section
msg1: db "Here are the array elements:", 10, 0
msg1Len: equ $-msg1
msg2: db "Here is the sorted array:", 10, 0
msg2Len: equ $-msg2
arr: dd 12, 16, 6, 18, 10, 40, 30
arrLen: equ ($-arr)/4 ;number of elements = array length / 4
SECTION .bss
max resd 1 ;declare and reserve space for max
SECTION .text
global bsort
bsort:
push ebp ; save old ebp register
mov ebp, esp ; build a new stack
restart:
mov ebx, arr ; the base address argument is saved in ebx register
mov ecx, arrLen ; the size argument is saved in exc register
sub ecx, 1 ; Last member has no following element to compare with.
; So we need to reduce the counter by 1
top:
mov eax, [ebx] ;; access first array element. Move its value to eax
cmp eax, [ebx+4] ; compare the value of eax ([ebx]) with [ebx+4]
jle noswap ; if value at eax is less or equal to value of [ebx+4]
; no need to exchang values. Jump to noswap
xchg eax, [ebx+4] ; if value at eax > value [ebx+4], exchange
mov [ebx], eax ; store the new exchanged value at [ebx]
jmp restart ; reset the base address and counter. Start over
noswap:
add ebx, 4 ; move to the next array element
loop top ; loop back to the top if the register ecx > 0
leave
ret
global main
main:
push ebp
mov ebp, esp
mov ecx, msg1 ;print msg1
mov edx, msg1Len
call PString
;save array base address in ebx and save sizein in ecx
mov ebx, arr
mov ecx, arrLen; store num elements in ecx
;loop to print array
PrintArray:
mov eax, [ebx] ;move value [ebx] to eax
call PrintDec
call Println
add ebx, 4
loop PrintArray
;call bubblesort
call bsort
mov ecx, msg2
mov edx, msg2Len
call PString
;save arr base add in sbx and size in ecx
mov ebx, arr
mov ecx, arrLen
PrintSortedArray:
mov eax, [ebx]
call PrintDec
call Println
add ebx, 4
loop PrintSortedArray
;exit program and clean stack
mov esp, ebp
pop ebp
ret
PString:; save register values of the called function
pusha
mov eax,4 ; use 'write' system call = 4
mov ebx,1 ; file descriptor 1 = STDOUT
int 80h ; call the kernel
; restore the old register values of the called function
popa
ret
Println:
;will call PString func
;will change content of ecx and edx
;need to save registers used by the main program
section .data
nl db 10
section .text
pusha
mov ecx, nl
mov edx, 1
call PString
;return original register values
popa
ret
PrintDec:
;saves all registers so they return unmodified
;build the function to handle dword size
section .bss
decstr resb 10 ; 10 32-bit digits
ct1 resd 1 ;keep track of dec-string size
section .text
pusha; save registers
mov dword[ct1],0 ;initially assume 0
mov edi, decstr ; edi points to dec-string
add edi, 9 ; moved to the last element of string
xor edx, edx ; clear edx for 64-bit div
whileNotZero:
mov ebx, 10 ; get ready to divide by 10
div ebx ; divide by 10
add edx, '0' ; convert to ascii
mov byte[edi], dl ; put it in string
dec edi ; move to next char in str
inc dword[ct1] ; inc char counter
xor edx, edx ; clear edx
cmp eax, 0 ;is remainder 0?
jne whileNotZero ;if no, keep on looping
inc edi ; conversion finished, bring edi
mov ecx, edi ; back to start of string. make ecx
mov edx, [ct1] ; point to counterm edx gets # chars
mov eax, 4 ; print to stdout
mov ebx, 1
int 0x80 ; call kernel
popa ; restore registers
ret
My program works, but there is something wrong with my printMax function. The program terminates with a
Segmentation fault (core dumped).
I have tried building a stack for the function and just doing a pusha popa and both ways, I get the seg fault core dumped.
I've tried calling the function, but it just runs twice.
Any idea what I am doing wrong?
SECTION .data ;data section
msg1 : db "Here are the array elements:", 10, 0
msg1Len: equ $-msg1
msg2 : db "Here is the max value in the array:", 10, 0
msg2Len: equ $-msg2
arr : dd 2,4,6,8,10,20,40
arrLen : equ ($-arr)/4 ;number of elements = array length / 4
SECTION .bss
max resd 1 ;declare and reserve space for max
SECTION .text
global main
main:
push ebp
mov ebp, esp
mov ecx, msg1 ;print msg1
mov edx, msg1Len
call PString
;save array base address in ebx and save sizein in ecx
mov ebx, arr
mov ecx, arrLen; store num elements in ecx
;loop to print array
PrintArray:
mov eax, [ebx] ;move value [ebx] to eax
call PrintDec
call Println
add ebx, 4
loop PrintArray
printMax:
section .text
pusha
;reset array to find max
mov ebx, arr
mov ecx, arrLen
loopForMax:
mov eax, [ebx]
cmp eax, [ebx +4]
jle sameMax
mov [max], eax
sameMax:
add ebx, 4 ;move to next element
loop loopForMax
mov ecx, msg2
mov edx, msg2Len
call PString
mov eax, [max]
call PrintDec
call Println
popa
ret
;exit program and clean stack
mov esp, ebp
pop ebp
ret
PString:; save register values of the called function
pusha
mov eax,4 ; use 'write' system call = 4
mov ebx,1 ; file descriptor 1 = STDOUT
int 80h ; call the kernel
; restore the old register values of the called function
popa
ret
Println:
;will call PString func
;will change content of ecx and edx
;need to save registers used by the main program
section .data
nl db 10
section .text
pusha
mov ecx, nl
mov edx, 1
call PString
;return original register values
popa
ret
PrintDec:
;saves all registers so they return unmodified
;build the function to handle dword size
section .bss
decstr resb 10 ; 10 32-bit digits
ct1 resd 1 ;keep track of dec-string size
section .text
pusha; save registers
mov dword[ct1],0 ;initially assume 0
mov edi, decstr ; edi points to dec-string
add edi, 9 ; moved to the last element of string
xor edx, edx ; clear edx for 64-bit div
whileNotZero:
mov ebx, 10 ; get ready to divide by 10
div ebx ; divide by 10
add edx, '0' ; convert to ascii
mov byte[edi], dl ; put it in string
dec edi ; move to next char in str
inc dword[ct1] ; inc char counter
xor edx, edx ; clear edx
cmp eax, 0 ;is remainder 0?
jne whileNotZero ;if no, keep on looping
inc edi ; conversion finished, bring edi
mov ecx, edi ; back to start of string. make ecx
mov edx, [ct1] ; point to counterm edx gets # chars
mov eax, 4 ; print to stdout
mov ebx, 1
int 0x80 ; call kernel
popa ; restore registers
ret
Hello all.
So I'm learning assembly.And as per my usual learning steps with any new language I pick up I've arrived at networking with assembly.
Which, sadly isn't going that well as I've pretty much failed at step 0, which would be getting a socket through which communication can begin.
The assembly code should be roughly equal to the following C code:
#include <stdio.h>
#include <sys/socket.h>
int main(){
int sock;
sock = socket(AF_INET, SOCK_STREAM, 0);
}
(Let's ignore the fact that it's not closing the socket for now.)
So here's what I did thus far:
Checked the manual. Which would imply that I need to make a socketcall() this is all good and well. The problem starts with that it would need an int that describes what sort of socketcall it should make. The calls manpage isn't helping much with this either as it only describes that:
On a some architectures—for example, x86-64 and ARM—there is no
socketcall() system call; instead socket(2), accept(2), bind(2), and
so on really are implemented as separate system calls.
Yet there are no such calls in the original list of syscalls - and as far as I know the socket(), accept(), bind(), listen(), etc. are calls from libnet and not from the kernel. This got me utterly confused so I've decided to compile the above C code and check up on it with strace. This yielded the following:
socket(PF_INET, SOCK_STREAM, IPPROTO_IP) = 3
While that didn't got me any closer to knowing what socket() is it did explain it's arguments. For witch I don't seem to find the proper documentation (again). I thought that PF_INET, SOCK_STREAM, IPPROTO_IP would be defined in <sys/socket.h> but my grep-ing for them didn't seem to find anything of use. So I decided to just wing it by using gdb in tandem with disass main to find the values. This gave the following output:
Dump of assembler code for function main:
0x00000000004004fd <+0>: push rbp
0x00000000004004fe <+1>: mov rbp,rsp
0x0000000000400501 <+4>: sub rsp,0x10
0x0000000000400505 <+8>: mov edx,0x0
0x000000000040050a <+13>: mov esi,0x1
0x000000000040050f <+18>: mov edi,0x2
0x0000000000400514 <+23>: call 0x400400
0x0000000000400519 <+28>: mov DWORD PTR [rbp-0x4],eax
0x000000000040051c <+31>: leave
0x000000000040051d <+32>: ret
End of assembler dump.
In my experience this would imply that socket() gets it's parameters from EDX (PF_INET), ESI (SOCK_STREAM), and EDI (IPPROTO_IP). Which would be odd for a syscall (as the convention with linux syscalls would be to use EAX/RAX for the call number and other registers for the parameters in increasing order, eg. RBX, RCX, RDX ...). The fact that this is beaing CALL-ed and not INT 0x80'd would also imply that this is not in fact a system call but rather something thats being called from a shared object. Or something.
But then again. Passing arguments in registers is very odd for something that's CALL-ed. Normally as far as I know argument's for called things should be PUSH-ed onto the stack, as the compiler can't know what registers they would try to use.
This behavior becomes even more curious when checking the produced binary with ldd:
linux-vdso.so.1 (0x00007fff4a7fc000)
libc.so.6 => /lib/x86_64-linux-gnu/libc.so.6 (0x00007f56b0c61000)
/lib64/ld-linux-x86-64.so.2 (0x00007f56b1037000)
There appears to be no networking library's linked.
And that's the point where I've ran out of ideas.
So I'm asking for the following:
A documentation that describes the x86-64 linux kernel's actual syscalls and their associated numbers. (Preferably as a header file for C.)
The header files that define PF_INET, SOCK_STREAM, IPPROTO_IP as it really bugs me that I wasn't able to find them on my own system.
Maybe a tutorial for networking in assembly on x86-64 linux. (For x86-32 it's easy to find material but for some reason I came up empty with the 64 bits stuff.)
Thanks!
The 64 bit calling convention does use registers to pass arguments, both in user space and to system calls. As you have seen, the user space convention is rdi,rsi, rdx, rcx, r8, r9. For system calls, r10 is used instead of rcx which is clobbered by the syscall instruction. See wikipedia or the ABI documentation for more details.
The definitions of the various constants are hidden in header files, which are nevertheless easily found via a file system search assuming you have the necessary development packages installed. You should look in /usr/include/x86_64-linux-gnu/bits/socket.h and /usr/include/linux/in.h.
As for a system call list, it's trivial to google one, such as this. You can also always look in the kernel source of course.
socket.asm
; Socket
; Compile with: nasm -f elf socket.asm
; Link with (64 bit systems require elf_i386 option): ld -m elf_i386 socket.o -o socket
; Run with: ./socket
%include 'functions.asm'
SECTION .text
global _start
_start:
xor eax, eax ; init eax 0
xor ebx, ebx ; init ebx 0
xor edi, edi ; init edi 0
xor esi, esi ; init esi 0
_socket:
push byte 6 ; push 6 onto the stack (IPPROTO_TCP)
push byte 1 ; push 1 onto the stack (SOCK_STREAM)
push byte 2 ; push 2 onto the stack (PF_INET)
mov ecx, esp ; move address of arguments into ecx
mov ebx, 1 ; invoke subroutine SOCKET (1)
mov eax, 102 ; invoke SYS_SOCKETCALL (kernel opcode 102)
int 80h ; call the kernel
call iprintLF ; call our integer printing function (print the file descriptor in EAX or -1 on error)
_exit:
call quit ; call our quit function
more docs...
this is for x86 system. if you want use for x86_64 system change x86 register to x86_64. for example change 'eax' to 'rax' or 'esp' to 'rsp'. and change syscall value in eax(rax), see https://chromium.googlesource.com/chromiumos/docs/+/master/constants/syscalls.md
[bits 32]
global _start
section .data
msg: db "Socket Failed To Create!",0xa,0
len: equ $-msg
msg1: db "Socket Created",0xa,0
len1: equ $-msg1
msg2: db "Recv Or Send Failed",0xa,0
len2: equ $-msg2
msg3: db "Shutdown Socket Failed",0xa,0
len3: equ $-msg3
DATASIZE: equ 5
SOCK_STREAM: equ 1
AF_INET: equ 2
AF_INET: equ 2
INADDR_ANY: equ 0
MSG_WAITALL: equ 0x100
MSG_DONTWAIT: equ 0x40
SHUT_RDWR: equ 2
SYS_SOCKET: equ 1 ; sys_socket(2)
SYS_BIND: equ 2 ; sys_bind(2)
SYS_CONNECT: equ 3 ; sys_connect(2)
SYS_LISTEN: equ 4 ; sys_listen(2)
SYS_ACCEPT: equ 5 ; sys_accept(2)
SYS_GETSOCKNAME:equ 6 ; sys_getsockname(2)
SYS_GETPEERNAME:equ 7 ; sys_getpeername(2)
SYS_SOCKETPAIR: equ 8 ; sys_socketpair(2)
SYS_SEND: equ 9 ; sys_send(2)
SYS_RECV: equ 10 ; sys_recv(2)
SYS_SENDTO: equ 11 ; sys_sendto(2)
SYS_RECVFROM: equ 12 ; sys_recvfrom(2)
SYS_SHUTDOWN: equ 13 ; sys_shutdown(2)
SYS_SETSOCKOPT: equ 14 ; sys_setsockopt(2)
SYS_GETSOCKOPT: equ 15 ; sys_getsockopt(2)
SYS_SENDMSG: equ 16 ; sys_sendmsg(2)
SYS_RECVMSG: equ 17 ; sys_recvmsg(2)
SYS_ACCEPT4: equ 18 ; sys_accept4(2)
SYS_RECVMMSG: equ 19 ; sys_recvmmsg(2)
SYS_SENDMMSG: equ 20 ; sys_sendmmsg(2)
struc sockaddr_in, -0x30
.sin_family: resb 2 ;2bytes
.sin_port: resb 2 ;2bytes
.sin_addr: resb 4 ;4bytes
.sin_zero: resb 8 ;8bytes
endstruc
struc socket, -0x40
.socketfd resb 4
.connectionfd resb 4
.count resb 4
.data resb DATASIZE
endstruc
section .text
_start:
push ebp
mov ebp, esp
sub esp, 0x400 ;1024byte
xor edx, edx ;or use cdq
;
; int socket(int domain, int type, int protocol);
; domain: The domain argument specifies a communication domain
;
push edx ; Push protocol
push dword SOCK_STREAM ; Push type
push dword AF_INET ; Push domain
mov ecx, esp ; ECX points to args
mov ebx, SYS_SOCKET ;
mov eax, 0x66 ; socketcall()
int 0x80
cmp eax, 0
jl .socket_failed
mov [ebp + socket.socketfd], eax
;
; fill struct sockaddr_in serv_addr;
;
mov word [ebp + sockaddr_in.sin_family], AF_INET
mov word [ebp + sockaddr_in.sin_port], 0x3905
mov dword [ebp + sockaddr_in.sin_addr], INADDR_ANY
push dword [ebp + sockaddr_in.sin_addr]
push word [ebp + sockaddr_in.sin_port]
push word [ebp + sockaddr_in.sin_family]
mov ecx, esp
;
; int bind(int sockfd, const struct sockaddr *addr, socklen_t addrlen);
;
push byte 0x10 ; sizeof(struct sockaddr)
push ecx ; pointer struct sockaddr
push dword [ebp + socket.socketfd]
mov ecx, esp ; ECX points to args
mov ebx, SYS_BIND ;
mov eax, 0x66
int 0x80
cmp eax, 0
jne .socket_failed
;
; int listen(int sockfd, int backlog);
;
push dword 0x10
push dword [ebp + socket.socketfd]
mov ecx, esp
mov ebx, SYS_LISTEN
mov eax, 0x66
int 0x80
cmp eax, 0
jne .socket_failed
;
; int accept(int sockfd, struct sockaddr *addr, socklen_t *addrlen);
;
xor ebx, ebx
push ebx
push ebx
push dword [ebp + socket.socketfd]
mov ecx, esp
mov ebx, SYS_ACCEPT
mov eax, 0x66
int 0x80
cmp eax, -1
je .socket_failed
mov [ebp + socket.connectionfd], eax
mov dword [ebp + socket.count], 0
.again:
lea edi, [ebp + socket.data]
mov ecx, DATASIZE
mov eax, 0
rep stosd
lea eax, [ebp + socket.data]
;
; ssize_t recv(int sockfd, const void *buf, size_t len, int flags);
;
push dword MSG_WAITALL
push dword DATASIZE
push eax
push dword [ebp + socket.connectionfd]
mov ecx, esp
mov ebx, SYS_RECV
mov eax, 0x66
int 0x80
cmp eax, 0
jle .recv_or_send_failed
mov edx, eax
lea ecx, [ebp + socket.data]
call printk
inc dword [ebp + socket.count]
cmp dword [ebp + socket.count], 5
jle .again
.break:
;
; int shutdown(int sockfd, int how);
;
push dword SHUT_RDWR
push dword [ebp + socket.socketfd]
mov ecx, esp
mov ebx, SYS_SHUTDOWN
mov eax, 0x66
int 0x80
cmp eax, 0
jne .shutdown_failed
;
; int close(int fd)
;
mov ebx, [ebp + socket.connectionfd]
mov eax, 0x06
int 0x80
cmp eax, 0
jne .shutdown_failed
jmp .success
.shutdown_failed:
mov edx, len3
mov ecx, msg3
call printk
jmp .end
.recv_or_send_failed:
mov edx, len2
mov ecx, msg2
call printk
jmp .end
.socket_failed:
mov edx, len
mov ecx, msg
call printk
jmp .end
.success:
mov edx, len1
mov ecx, msg1
call printk
jmp .end
.end:
leave
mov ebx,0 ;first syscall argument: exit code
mov eax,1 ;system call number (sys_exit)
int 0x80 ;call kernel
ret
; EDX: message length
; ECX: pointer to message to write
printk:
pusha
mov ebx,1 ;first argument: file handle (stdout)
mov eax,4 ;system call number (sys_write)
int 0x80 ;call kernel
popa
ret
I'm new in assembly programming and I have an assignment in which I have to read a text file line by line and use what is written in the file and pass it to another function. My problem is that I'm not sure of how to read the text this way because from what I have discovered for reading a text file first I have to create a buffer reserving certain quantity of bytes for storing what is in the file. Howerver in this case I want to read line by line (like a loop) until the end of file so I dont know how much bytes I have to reserve. Thanks.
Btw here is the code I'm trying to use:
SECTION .data
file_name db 'instruct.txt',0
SECTION .bss
fd_out resb 1
fd_in resb 1
info resb 20
SECTION .text
global main
main: ;tell linker entry point
push ebp
mov ebp, esp
push ebx
;open the file for reading
mov eax, 5
mov ebx, file_name
mov ecx, 2
mov edx, 0777 ;read, write and execute by all
int 0x80
mov [fd_in], eax
loop:
;read from file
mov eax, 3
mov ebx, [fd_in]
mov ecx, info
mov edx, 5
int 0x80
cmp eax, 0
;check EOF
je exit
; print the info
mov eax, 4
mov ebx, 1
mov ecx, info
mov edx, 5
int 0x80
;
jmp loop
mov eax,1 ;system call number (sys_exit)
int 0x80 ;call kernel
exit:
; close the file
mov eax, 6
mov ebx, [fd_in]
pop ebx
mov esp, ebp
pop ebp
ret
use mmap syscall, read entire file to memory and search for 0x0A sequence. This is the ASCII code for end of line. Perhaps usefull too to check for 0x0D (in case you are dealing with windows text files. There the sequence 0x0A,0x0D indicates an new line and thus an end of line.
mmap will try to allocate memory for you without the overhead of administration for you. Otherwise determine the file length and reserve memory with syscall sbrk. Works also but you have to program a bit more. My suggestion is that mmap is the best way.