Why this asm code not doubling the value the pointer points - c

I am trying to interface c code with asm.
But it is not working correctly and I am not able to find the problem.
program.c
#include<stdio.h>
int *asm_multi(int *ptr);
int main()
{
int i=10;
int *p=&i;
asm_multi(p);
printf("%d\n",*p);
return 0;
}
code.asm
.section .text
.global asm_multi
.type asm_multi,#function
asm_multi:
pushl %ebp
movl %esp,%ebp
movl 8(%ebp),%eax
movl %eax,%edx
leal (%edx,%edx,1),%edx
movl %edx,%eax
movl %ebp,%esp
popl %ebp
ret
I am creating the final executable by
as code.asm -o code.o
gcc program.c code.o -o output
./output
The output it prints is :10 whereas I am expecting: 20
What is the problem in the code? Don't consider the efficiency of the program. I have just started asm programming.
I created above code after reading from a more complex example kept at this link. This works perfectly.

You should learn to use a debugger as soon as possible. It not only helps you find bugs, but also allows you to exactly see what the cpu is doing at each instruction and you can compare that to your intentions.
Also, comment your code, especially when asking for help, so we can tell you where the instructions don't match your intentions, if you were unable to do so yourself.
Let's comment your code then:
asm_multi:
pushl %ebp
movl %esp,%ebp
movl 8(%ebp),%eax # fetch first argument, that is p into eax
movl %eax,%edx # edx = p too
leal (%edx,%edx,1),%edx # edx = eax + edx = 2 * p
movl %edx,%eax # eax = edx = 2 * p
movl %ebp,%esp
popl %ebp
ret
As you can see, there are two problems:
You are doubling the pointer not the value it points to
You are not writing it back into memory, just returning it in eax which is then ignored by the C code
A possible fix:
asm_multi:
pushl %ebp
movl %esp,%ebp
movl 8(%ebp),%eax # fetch p
shll $1, (%eax) # double *p by shifting 1 bit to the left
# alternatively
# movl (%eax), %edx # fetch *p
# addl %edx, (%eax) # add *p to *p, doubling it
movl %ebp,%esp
popl %ebp
ret

Related

counting the '0's in a string in assembly

I have a little program written with c and assembly. the principle is simple: "count the '0's in a a string given by main.c
so for test0 str0ing 0 it should return 3 because there's 3 '0's in the string
the function itself is made in x86 asm with AT&T syntax, i am given a pointer to the string via C. both main.c and the asm is linked via header file.
this is my code so far and the problem is that it always returns 0. it never reaches conditional jump to increment %eax(to be returned)
// C
#include "asm.h"
char string[] = "2a0 a0 ";
char *ptr1 = string;
int main(){
printf("\nthere are : %d %s in :%s", zero_count(), "0s", string);
printf("\nstring address is: %p\n", ptr1);
return 0;
}
// x86asm
.global ptr1
.section .text
.global zero_count #func()
zero_count:
# prologue
pushl %ebp # save these previous stack frame pointer
movl %esp, %ebp # the stack frame pointer for function
# save registers
#pushl $ebx # needs to be pushed out of stack when used
#pushl %esi # needs to be pushed out of stack when used
#pushl %edi # needs to be pushed out of stack when used
# function body
movl ptr1, %ecx # moves the value of ptr1 to ecx
movl $0, %eax # cleans eax with 0
# loop start
loop_beginning:
cmp $0, (%ecx)
je end
# compare to 'o'
cmp $48, %ecx # 48 is "0" in the asci table
je if_0
increment_pointer:
addl $1, %ecx
jmp loop_beginning
if_0:
addl $1, %eax
jmp increment_pointer
end:
#popl %edi # needs to be popped when used
#popl %esi # needs to be popped when useds
#popl %ebx # needs to be popped when used
# epilogue
movl %ebp, %esp # restore the previous stack pointer("cleaner" the stack)
popl %ebp # restore the previous stack frame pointer
ret #w returns
i apolagize for using global variables in advance, i know it's not good but I'm still learning to use the stack
by switching the cmp to cmpb worked in this string. but i still don't know why. would this operation also worked if this was an int[]?
.global ptr1
.section .text
.global zero_count #func()
zero_count:
# prologue
pushl %ebp # save these previous stack frame pointer
movl %esp, %ebp # the stack frame pointer for function
# save registers
#pushl $ebx # needs to be pushed out of stack when used
#pushl %esi # needs to be pushed out of stack when used
#pushl %edi # needs to be pushed out of stack when used
# function body
mov ptr1, %ecx # moves the value of ptr1 to ecx
movl $0, %eax # cleans eax with 0
# loop start
loop_beginning:
cmpb $0, (%ecx)
je end
# compare to 'o'
cmpb $48, (%ecx) # 48 is "0" in the asci table
je if_0
increment_pointer:
addl $1, %ecx
jmp loop_beginning
if_0:
addl $1, %eax
jmp increment_pointer
# movl (%ecx), %eax
end:
#popl %edi # needs to be popped when used
#popl %esi # needs to be popped when useds
#popl %ebx # needs to be popped when used
# epilogue
movl %ebp, %esp # restore the previous stack pointer("cleaner" the stack)
popl %ebp # restore the previous stack frame pointer
ret #w returns

Calling C function from the x86 assembler

I am trying to write a function that converts decimal numbers into binary in assembler. Since printing is so troublesome in there, I have decided to make a separate function in C that just prints the numbers. But when I run the code, it always prints '0110101110110100'
Heres the C function (both print and conversion):
void printBin(int x) {
printf("%d", x);
}
void DecToBin(int n)
{
// Size of an integer is assumed to be 16 bits
for (int i = 15; i >= 0; i--) {
int k = n >> i;
printBin(k & 1);
}
heres the code in asm:
.globl _DecToBin
.extern _printBin
_DecToBin:
pushl %ebp
movl %esp, %ebp
movl 8(%ebp),%eax
movl $15, %ebx
cmpl $0, %ebx
jl end
start:
movl %ebx, %ecx
movl %eax, %edx
shrl %cl, %eax
andl $1, %eax
pushl %eax
call _printBin
movl %edx, %eax
dec %ebx
cmpl $0, %ebx
jge start
end:
movl %ebp, %esp
popl %ebp
ret
Cant figure out where the mistake is. Any help would be appreciated
disassembled code using online program
Your principle problem is that it is very unlikely that %edx is preserved across the function call to printBin.
Also:
%ebx is not a volatile register in most (any?) C calling convention rules. You need to check your compilers documentation and conform to it.
If you are going to use ebx, you need to save and restore it.
The stack pointer needs to be kept aligned to 16 bytes. On my machine (macos), it SEGVs under printBin if you don’t.

How does ESP and EBP registers act when a new program is executed?

I recently went through an Assembly language book by Richard Blum wherein there was a subject on the C program to assembly conversion.
Consider the following C program:
#include <stdio.h>
int main(){
int a=100;
int b=25;
if (a>b)
printf("The higher value is %d\n", a);
else
printf("The higher value is %d\n", b);
return 0;
}
when I compiled the above program using -S parameter as:
gcc -S abc.c
I got the following result:
.file "abc.c"
.section .rodata
.LC0:
.string "The higher value is %d\n"
.text
.globl main
.type main, #function
main:
.LFB0:
.cfi_startproc
leal 4(%esp), %ecx
.cfi_def_cfa 1, 0
andl $-16, %esp
pushl -4(%ecx)
pushl %ebp
.cfi_escape 0x10,0x5,0x2,0x75,0
movl %esp, %ebp
pushl %ecx
.cfi_escape 0xf,0x3,0x75,0x7c,0x6
subl $20, %esp
movl $100, -16(%ebp)
movl $25, -12(%ebp)
movl -16(%ebp), %eax
cmpl -12(%ebp), %eax
jle .L2
subl $8, %esp
pushl -16(%ebp)
pushl $.LC0
call printf
addl $16, %esp
jmp .L3
.L2:
subl $8, %esp
pushl -12(%ebp)
pushl $.LC0
call printf
addl $16, %esp
.L3:
movl $0, %eax
movl -4(%ebp), %ecx
.cfi_def_cfa 1, 0
leave
.cfi_restore 5
leal -4(%ecx), %esp
.cfi_def_cfa 4, 4
ret
.cfi_endproc
.LFE0:
.size main, .-main
.ident "GCC: (Ubuntu 6.2.0-5ubuntu12) 6.2.0 20161005"
.section .note.GNU-stack,"",#progbits
What I cant understand is this:
Snippet
.LFB0:
.cfi_startproc
leal 4(%esp), %ecx
.cfi_def_cfa 1, 0
andl $-16, %esp
pushl -4(%ecx)
pushl %ebp
.cfi_escape 0x10,0x5,0x2,0x75,0
movl %esp, %ebp
pushl %ecx
.cfi_escape 0xf,0x3,0x75,0x7c,0x6
subl $20, %esp
I am unable to predict what is happening with the ESP and EBP register. About EBP, I can understand to an extent that it is used as a local stack and so it's value is saved by pushing onto stack.
Can you please elaborate the above snippet?
This is a special form of function entry-sequence suitable for the main()
function. The compiler knows that main() really is called as main(int argc, char **argv, char **envp), and compiles this function according to that very special behavior. So what's sitting on the stack when this code is reached is four long-size values, in this order: envp, argv, argc, return_address.
So that means that the entry-sequence code is doing something like this
(rewritten to use Intel syntax, which frankly makes a lot more sense
than AT&T syntax):
; Copy esp+4 into ecx. The value at [esp] has the return address,
; so esp+4 is 'argc', or the start of the function's arguments.
lea ecx, [esp+4]
; Round esp down (align esp down) to the nearest 16-byte boundary.
; This ensures that regardless of what esp was before, esp is now
; starting at an address that can store any register this processor
; has, from the one-byte registers all the way up to the 16-byte xmm
; registers
and esp, 0xFFFFFFF0
; Since we copied esp+4 into ecx above, that means that [ecx] is 'argc',
; [ecx+4] is 'argv', and [ecx+8] is 'envp'. For whatever reason, the
; compiler decided to push a duplicate copy of 'argv' onto the function's
; new local frame.
push dword ptr [ecx+4]
; Preserve 'ebp'. The C ABI requires us not to damage 'ebp' across
; function calls, so we save its old value on the stack before we
; change it.
push ebp
; Set 'ebp' to the current stack pointer to set up the function's
; stack frame for real. The "stack frame" is the place on the stack
; where this function will store all its local variables.
mov ebp, esp
; Preserve 'ecx'. Ecx tells us what 'esp' was before we munged 'esp'
; in the 'and'-instruction above, so we'll need it later to restore
; 'esp' before we return.
push ecx
; Finally, allocate space on the stack frame for the local variables,
; 20 bytes worth. 'ebp' points to 'esp' plus 24 by this point, and
; the compiler will use 'ebp-16' and 'ebp-12' to store the values of
; 'a' and 'b', respectively. (So under 'ebp', going down the stack,
; the values will look like this: [ecx, unused, unused, a, b, unused].
; Those unused slots are probably used by the .cfi pseudo-ops for
; something related to exception handling.)
sub esp, 20
At the other end of the function, the inverse operations are used to put
the stack back the way it was before the function was called; it may be
helpful to examine what they're doing as well to understand what's happening
at the beginning:
; Return values are always passed in 'eax' in the x86 C ABI, so set
; 'eax' to the return value of 0.
mov eax, 0
; We pushed 'ecx' onto the stack a while back to save it. This
; instruction pulls 'ecx' back off the stack, but does so without
; popping (which would alter 'esp', which doesn't currently point
; to the right location).
mov ecx, [ebp+4]
; Magic instruction! The 'leave' instruction is designed to shorten
; instruction sequences by "undoing" the stack in a single op.
; So here, 'leave' means specifically to do the following two
; operations, in order: esp = ebp / pop ebp
leave
; 'esp' is now set to what it was before we pushed 'ecx', and 'ebp'
; is back to the value that was used when this function was called.
; But that's still not quite right, so we set 'esp' specifically to
; 'ecx+4', which is the exact opposite of the very first instruction
; in the function.
lea esp, [ecx+4]
; Finally, the stack is back to the way it was when we were called,
; so we can just return.
ret

Segmentation fault when calling assembly function from C code

I'm trying to link assembly functions to a C code for exercise.
Here's my assembly function, written in x86 assembly:
.code32
.section .text
.globl max_function
.type max_function, #function
# i parametri saranno in ordine inverso a partire da 8(%ebp)
max_function:
pushl %ebp # save ebp
movl %esp, %ebp # new frame function
movl $0, %edi # first index is 0
movl 8(%ebp), %ecx # ecx is loaded with the number of elements
cmpl $0, %ecx # check that the number of elements is not 0
je end_function_err #if it is, exit
movl 12(%ebp),%edx # edx is loaded with the array base
movl (%edx), %eax # first element of the array
start_loop:
incl %edi #increment the index
cmpl %edi,%ecx #if it's at the end quit
je loop_exit
movl (%edx,%edi,4),%ebx #pick the value
cmpl %ebx,%eax #compare with actual maximum value
jle start_loop #less equal -> repeat loop
movl %ebx,%eax #greater -> update value
jmp start_loop #repeat loop
loop_exit:
jmp end_function #finish
end_function: #exit operations
movl %ebp, %esp
popl %ebp
ret
end_function_err:
movl $0xffffffff, %eax #return -1 and quit
jmp end_function
It basically defines a function that finds the maximum number of an array (or it should be)
And my C code:
#include <stdio.h>
#include <stdlib.h>
extern int max_function(int size, int* values);
int main(){
int values[] = { 4 , 5 , 7 , 3 , 2 , 8 , 5 , 6 } ;
printf("\nMax value is: %d\n",max_function(8,values));
}
I compile them with gcc -o max max.s max.c.
I get a SegmentationFault when executing the code.
My suspect is that I don't access the value in a right manner, but I can't see why, even because I based my code on an example code that prints argc and argv values when called from the command line.
I'm running Debian 8 64-bit
The problems were:
not preserving %ebx and %edi
not compiling for 32 bit (had to use -m32 flag for gcc)
cmpl operands were inverted
Thanks everybody, problem is solved.
I'll focus more on debugging tools to (disassembling and running step by step was very useful)!

Understand the assembly code generated by a simple C program

I am trying to understand the assembly level code for a simple C program by inspecting it with gdb's disassembler.
Following is the C code:
#include <stdio.h>
void function(int a, int b, int c) {
char buffer1[5];
char buffer2[10];
}
void main() {
function(1,2,3);
}
Following is the disassembly code for both main and function
gdb) disass main
Dump of assembler code for function main:
0x08048428 <main+0>: push %ebp
0x08048429 <main+1>: mov %esp,%ebp
0x0804842b <main+3>: and $0xfffffff0,%esp
0x0804842e <main+6>: sub $0x10,%esp
0x08048431 <main+9>: movl $0x3,0x8(%esp)
0x08048439 <main+17>: movl $0x2,0x4(%esp)
0x08048441 <main+25>: movl $0x1,(%esp)
0x08048448 <main+32>: call 0x8048404 <function>
0x0804844d <main+37>: leave
0x0804844e <main+38>: ret
End of assembler dump.
(gdb) disass function
Dump of assembler code for function function:
0x08048404 <function+0>: push %ebp
0x08048405 <function+1>: mov %esp,%ebp
0x08048407 <function+3>: sub $0x28,%esp
0x0804840a <function+6>: mov %gs:0x14,%eax
0x08048410 <function+12>: mov %eax,-0xc(%ebp)
0x08048413 <function+15>: xor %eax,%eax
0x08048415 <function+17>: mov -0xc(%ebp),%eax
0x08048418 <function+20>: xor %gs:0x14,%eax
0x0804841f <function+27>: je 0x8048426 <function+34>
0x08048421 <function+29>: call 0x8048340 <__stack_chk_fail#plt>
0x08048426 <function+34>: leave
0x08048427 <function+35>: ret
End of assembler dump.
I am seeking answers for following things :
how the addressing is working , I mean (main+0) , (main+1), (main+3)
In the main, why is $0xfffffff0,%esp being used
In the function, why is %gs:0x14,%eax , %eax,-0xc(%ebp) being used.
If someone can explain , step by step happening, that will be greatly appreciated.
The reason for the "strange" addresses such as main+0, main+1, main+3, main+6 and so on, is because each instruction takes up a variable number of bytes. For example:
main+0: push %ebp
is a one-byte instruction so the next instruction is at main+1. On the other hand,
main+3: and $0xfffffff0,%esp
is a three-byte instruction so the next instruction after that is at main+6.
And, since you ask in the comments why movl seems to take a variable number of bytes, the explanation for that is as follows.
Instruction length depends not only on the opcode (such as movl) but also the addressing modes for the operands as well (the things the opcode are operating on). I haven't checked specifically for your code but I suspect the
movl $0x1,(%esp)
instruction is probably shorter because there's no offset involved - it just uses esp as the address. Whereas something like:
movl $0x2,0x4(%esp)
requires everything that movl $0x1,(%esp) does, plus an extra byte for the offset 0x4.
In fact, here's a debug session showing what I mean:
Microsoft Windows XP [Version 5.1.2600]
(C) Copyright 1985-2001 Microsoft Corp.
c:\pax> debug
-a
0B52:0100 mov word ptr [di],7
0B52:0104 mov word ptr [di+2],8
0B52:0109 mov word ptr [di+0],7
0B52:010E
-u100,10d
0B52:0100 C7050700 MOV WORD PTR [DI],0007
0B52:0104 C745020800 MOV WORD PTR [DI+02],0008
0B52:0109 C745000700 MOV WORD PTR [DI+00],0007
-q
c:\pax> _
You can see that the second instruction with an offset is actually different to the first one without it. It's one byte longer (5 bytes instead of 4, to hold the offset) and actually has a different encoding c745 instead of c705.
You can also see that you can encode the first and third instruction in two different ways but they basically do the same thing.
The and $0xfffffff0,%esp instruction is a way to force esp to be on a specific boundary. This is used to ensure proper alignment of variables. Many memory accesses on modern processors will be more efficient if they follow the alignment rules (such as a 4-byte value having to be aligned to a 4-byte boundary). Some modern processors will even raise a fault if you don't follow these rules.
After this instruction, you're guaranteed that esp is both less than or equal to its previous value and aligned to a 16 byte boundary.
The gs: prefix simply means to use the gs segment register to access memory rather than the default.
The instruction mov %eax,-0xc(%ebp) means to take the contents of the ebp register, subtract 12 (0xc) and then put the value of eax into that memory location.
Re the explanation of the code. Your function function is basically one big no-op. The assembly generated is limited to stack frame setup and teardown, along with some stack frame corruption checking which uses the afore-mentioned %gs:14 memory location.
It loads the value from that location (probably something like 0xdeadbeef) into the stack frame, does its job, then checks the stack to ensure it hasn't been corrupted.
Its job, in this case, is nothing. So all you see is the function administration stuff.
Stack set-up occurs between function+0 and function+12. Everything after that is setting up the return code in eax and tearing down the stack frame, including the corruption check.
Similarly, main consist of stack frame set-up, pushing the parameters for function, calling function, tearing down the stack frame and exiting.
Comments have been inserted into the code below:
0x08048428 <main+0>: push %ebp ; save previous value.
0x08048429 <main+1>: mov %esp,%ebp ; create new stack frame.
0x0804842b <main+3>: and $0xfffffff0,%esp ; align to boundary.
0x0804842e <main+6>: sub $0x10,%esp ; make space on stack.
0x08048431 <main+9>: movl $0x3,0x8(%esp) ; push values for function.
0x08048439 <main+17>: movl $0x2,0x4(%esp)
0x08048441 <main+25>: movl $0x1,(%esp)
0x08048448 <main+32>: call 0x8048404 <function> ; and call it.
0x0804844d <main+37>: leave ; tear down frame.
0x0804844e <main+38>: ret ; and exit.
0x08048404 <func+0>: push %ebp ; save previous value.
0x08048405 <func+1>: mov %esp,%ebp ; create new stack frame.
0x08048407 <func+3>: sub $0x28,%esp ; make space on stack.
0x0804840a <func+6>: mov %gs:0x14,%eax ; get sentinel value.
0x08048410 <func+12>: mov %eax,-0xc(%ebp) ; put on stack.
0x08048413 <func+15>: xor %eax,%eax ; set return code 0.
0x08048415 <func+17>: mov -0xc(%ebp),%eax ; get sentinel from stack.
0x08048418 <func+20>: xor %gs:0x14,%eax ; compare with actual.
0x0804841f <func+27>: je <func+34> ; jump if okay.
0x08048421 <func+29>: call <_stk_chk_fl> ; otherwise corrupted stack.
0x08048426 <func+34>: leave ; tear down frame.
0x08048427 <func+35>: ret ; and exit.
I think the reason for the %gs:0x14 may be evident from above but, just in case, I'll elaborate here.
It uses this value (a sentinel) to put in the current stack frame so that, should something in the function do something silly like write 1024 bytes to a 20-byte array created on the stack or, in your case:
char buffer1[5];
strcpy (buffer1, "Hello there, my name is Pax.");
then the sentinel will be overwritten and the check at the end of the function will detect that, calling the failure function to let you know, and then probably aborting so as to avoid any other problems.
If it placed 0xdeadbeef onto the stack and this was changed to something else, then an xor with 0xdeadbeef would produce a non-zero value which is detected in the code with the je instruction.
The relevant bit is paraphrased here:
mov %gs:0x14,%eax ; get sentinel value.
mov %eax,-0xc(%ebp) ; put on stack.
;; Weave your function
;; magic here.
mov -0xc(%ebp),%eax ; get sentinel back from stack.
xor %gs:0x14,%eax ; compare with original value.
je stack_ok ; zero/equal means no corruption.
call stack_bad ; otherwise corrupted stack.
stack_ok: leave ; tear down frame.
Pax has produced a definitive answer. However, for completeness, I thought I'd add a note on getting GCC itself to show you the assembly it generates.
The -S option to GCC tells it to stop compilation and write the assembly to a file. Normally, it either passes that file to the assembler or for some targets writes the object file directly itself.
For the sample code in the question:
#include <stdio.h>
void function(int a, int b, int c) {
char buffer1[5];
char buffer2[10];
}
void main() {
function(1,2,3);
}
the command gcc -S q3654898.c creates a file named q3654898.s:
.file "q3654898.c"
.text
.globl _function
.def _function; .scl 2; .type 32; .endef
_function:
pushl %ebp
movl %esp, %ebp
subl $40, %esp
leave
ret
.def ___main; .scl 2; .type 32; .endef
.globl _main
.def _main; .scl 2; .type 32; .endef
_main:
pushl %ebp
movl %esp, %ebp
subl $24, %esp
andl $-16, %esp
movl $0, %eax
addl $15, %eax
addl $15, %eax
shrl $4, %eax
sall $4, %eax
movl %eax, -4(%ebp)
movl -4(%ebp), %eax
call __alloca
call ___main
movl $3, 8(%esp)
movl $2, 4(%esp)
movl $1, (%esp)
call _function
leave
ret
One thing that is evident is that my GCC (gcc (GCC) 3.4.5 (mingw-vista special r3)) doesn't include the stack check code by default. I imagine that there is a command line option, or that if I ever got around to nudging my MinGW install up to a more current GCC that it could.
Edit: Nudged to do so by Pax, here's another way to get GCC to do more of the work.
C:\Documents and Settings\Ross\My Documents\testing>gcc -Wa,-al q3654898.c
q3654898.c: In function `main':
q3654898.c:8: warning: return type of 'main' is not `int'
GAS LISTING C:\DOCUME~1\Ross\LOCALS~1\Temp/ccLg8pWC.s page 1
1 .file "q3654898.c"
2 .text
3 .globl _function
4 .def _function; .scl 2; .type
32; .endef
5 _function:
6 0000 55 pushl %ebp
7 0001 89E5 movl %esp, %ebp
8 0003 83EC28 subl $40, %esp
9 0006 C9 leave
10 0007 C3 ret
11 .def ___main; .scl 2; .type
32; .endef
12 .globl _main
13 .def _main; .scl 2; .type 32;
.endef
14 _main:
15 0008 55 pushl %ebp
16 0009 89E5 movl %esp, %ebp
17 000b 83EC18 subl $24, %esp
18 000e 83E4F0 andl $-16, %esp
19 0011 B8000000 movl $0, %eax
19 00
20 0016 83C00F addl $15, %eax
21 0019 83C00F addl $15, %eax
22 001c C1E804 shrl $4, %eax
23 001f C1E004 sall $4, %eax
24 0022 8945FC movl %eax, -4(%ebp)
25 0025 8B45FC movl -4(%ebp), %eax
26 0028 E8000000 call __alloca
26 00
27 002d E8000000 call ___main
27 00
28 0032 C7442408 movl $3, 8(%esp)
28 03000000
29 003a C7442404 movl $2, 4(%esp)
29 02000000
30 0042 C7042401 movl $1, (%esp)
30 000000
31 0049 E8B2FFFF call _function
31 FF
32 004e C9 leave
33 004f C3 ret
C:\Documents and Settings\Ross\My Documents\testing>
Here we see an output listing produced by the assembler. (Its name is GAS, because it is Gnu's version of the classic *nix assembler as. There's humor there somewhere.)
Each line has most of the following fields: a line number, an address in the current section, bytes stored at that address, and the source text from the assembly source file.
The addresses are offsets into that portion of each section provided by this module. This particular module only has content in the .text section which stores executable code. You will typically find mention of sections named .data and .bss as well. Lots of other names are used and some have special purposes. Read the manual for the linker if you really want to know.
It will be better to try the -fno-stack-protector flag with gcc to disable the canary and see your results.
I'd like to add that for simple stuff, GCC's assembly output is often easier to read if you turn on a little optimization. Here's the sample code again...
void function(int a, int b, int c) {
char buffer1[5];
char buffer2[10];
}
/* corrected calling convention of main() */
int main() {
function(1,2,3);
return 0;
}
this is what I get without optimization (OSX 10.6, gcc 4.2.1+Apple patches)
.globl _function
_function:
pushl %ebp
movl %esp, %ebp
pushl %ebx
subl $36, %esp
call L4
"L00000000001$pb":
L4:
popl %ebx
leal L___stack_chk_guard$non_lazy_ptr-"L00000000001$pb"(%ebx), %eax
movl (%eax), %eax
movl (%eax), %edx
movl %edx, -12(%ebp)
xorl %edx, %edx
leal L___stack_chk_guard$non_lazy_ptr-"L00000000001$pb"(%ebx), %eax
movl (%eax), %eax
movl -12(%ebp), %edx
xorl (%eax), %edx
je L3
call ___stack_chk_fail
L3:
addl $36, %esp
popl %ebx
leave
ret
.globl _main
_main:
pushl %ebp
movl %esp, %ebp
subl $24, %esp
movl $3, 8(%esp)
movl $2, 4(%esp)
movl $1, (%esp)
call _function
movl $0, %eax
leave
ret
Whew, one heck of a mouthful! But look what happens with -O on the command line...
.text
.globl _function
_function:
pushl %ebp
movl %esp, %ebp
leave
ret
.globl _main
_main:
pushl %ebp
movl %esp, %ebp
movl $0, %eax
leave
ret
Of course, you do run the risk of your code being rendered completely unrecognizable, especially at higher optimization levels and with more complicated stuff. Even here, we see that the call to function has been discarded as pointless. But I find that not having to read through dozens of unnecessary stack spills is generally more than worth a little extra scratching my head over the control flow.

Resources