I know that OS X is 16 byte stack align, but I don't really understand why it is causing an error here.
All I am doing here is to pass an object size (which is 24) to %rdi, and call malloc. Does this error mean I have to ask for 32 bytes ?
And the error message is:
libdyld.dylib`stack_not_16_byte_aligned_error: -> 0x7fffc12da2fa <+0>: movdqa %xmm0, (%rsp) 0x7fffc12da2ff <+5>: int3
libdyld.dylib`_dyld_func_lookup: 0x7fffc12da300 <+0>: pushq %rbp 0x7fffc12da301 <+1>: movq %rsp, %rbp
Here is the code:
Object_copy:
pushq %rbp
movq %rbp, %rsp
subq $8, %rsp
movq %rdi, 8(%rsp) # save self address
movq obj_size(%rdi), %rax # get object size
imul $8, %rax
movq %rax, %rdi
callq _malloc <------------------- error in this call
# rsi old object address
# rax new object address
# rdi object size, mutiple of 8
# rcx temp reg
# copy object tag
movq 0(%rsi), %rcx
movq %rcx, 0(%rax)
# set rdx to counter, starting from 8
movq $8, %rdx
# add 8 to object size, since we are starting from 8
addq $8, %rdi
start_loop:
cmpq %rdx, %rdi
jle end_loop
movq (%rdx, %rsi, 1), %rcx
movq %rcx, (%rdx, %rax, 1)
addq $8, %rdx
jmp start_loop
end_loop:
leave
ret
Main_protoObj:
.quad 5 ; object tag
.quad 3 ; object size
.quad Main_dispatch_table ; dispatch table
_main:
leaq Main_protoObj(%rip), %rdi
callq Object_copy # copy main proto object
subq $8, %rsp # save the main object on the stack
movq %rax, 8(%rsp)
movq %rax, %rdi # set rdi point to SELF
callq Main_init
callq Main_main
addq $8, %rsp # restore stack
leaq _term_msg(%rip), %rax
callq _print_string
pushq %rbp
places an additional 8 bytes on stack so stack is now aligned back to 16-byte boundary. You then dosubq $8, %rsp
which means RSP is now misaligned by 8 again. Then you callmalloc
with misaligned stack. Rather thansubq $8, %rsp
trysubq $16, %rsp
to keep 16-byte alignment. – Michael Petch