Going into protmode in the boot sector is extremely early. Most OSs I've seen will stay in realmode (or "unreal" mode) for a little bit longer, so they can use the BIOS to setup some more stuff before making that leap.

Also noticed a minor optimisation:

    mov AL, [SI]    ; pega um byte da string e carrega em al 
    inc SI 

Could've been replaced with a 'lodsb', saving 2 bytes. Ditto for MOV BH/MOV BL with MOV BX. :-)

Going down the size optimization rabbit hole a little bit (not criticism, I just enjoy this sort of puzzle).

Two bytes shorter:

  call print_str
  ret
  =>
  jmp print_str

Three bytes shorter; this one may be a little too clever, since it depends on the low bit of CR0 being 0 initially:

  mov EAX, CR0
  or EAX, 1
  =>
  mov EAX, CR0
  inc AX

Could've been replaced with a 'cld' and 'lodsb', saving 1 byte.

Actually, I really prefer writing that in C rather than asm: You can use bitfields to define the GDT, IDT, Page Directories and so on. Doing everything is ASM is a PITA, for debugging and for readability.

(I am a teaching assistant at one of these courses and hate when students do everything in asm.. but they are allowed to do as they want, as long as it works as specified).

Why is debugging a pita?

I agree... I did a similar thing here:

https://github.com/aosmith/toy-os

The x86 code seems like a bear but once it's explained it is fairly simple.