global start
global kernel_pml4
global kernel_pdpt_0
global kernel_pd_0
global kernel_pt_0
global paging_pt
global bootstrap_pt
extern kmain
extern amd64_shim
bits 32

section .multiboot
align 8
mb_start:
; header
dd 0xe85250d6
dd 0
dd mb_end - mb_start
dd 0x100000000 - (0xe85250d6 + (mb_end - mb_start))
; null tag
dw 0
dw 0
dd 8
;
mb_end:

section .bss
align 4096
kernel_pml4:			; reserve memory for initial 512 pml4 entires
	resb 4096
kernel_pdpt_0:			; reserve memory for initial 512 pdpt entires
	resb 4096
kernel_pd_0:			; reserve memory for initial 512 pd entries
	resb 4096
kernel_pt_0:			; reserve memory for initial 512 pt entries
	resb 4096
paging_pt:				; reserve pages for pager mappings
	resb 4096
bootstrap_pt:			; reserve pages to bootstrap pager
	resb 4096

align 16
stack_start:
	resb 16384
stack_end:

section .rodata
align 16
; Access bits
PRESENT        equ 1 << 7
NOT_SYS        equ 1 << 4
EXEC           equ 1 << 3
DC             equ 1 << 2
RW             equ 1 << 1
ACCESSED       equ 1 << 0
 
; Flags bits
GRAN_4K       equ 1 << 7
SZ_32         equ 1 << 6
LONG_MODE     equ 1 << 5
 
GDT:
    .Null: equ $ - GDT
        dq 0
    .Code: equ $ - GDT
        dd 0xFFFF                                   ; Limit & Base (low, bits 0-15)
        db 0                                        ; Base (mid, bits 16-23)
        db PRESENT | NOT_SYS | EXEC | RW            ; Access
        db GRAN_4K | LONG_MODE | 0xF                ; Flags & Limit (high, bits 16-19)
        db 0                                        ; Base (high, bits 24-31)
    .Data: equ $ - GDT
        dd 0xFFFF                                   ; Limit & Base (low, bits 0-15)
        db 0                                        ; Base (mid, bits 16-23)
        db PRESENT | NOT_SYS | RW                   ; Access
        db GRAN_4K | SZ_32 | 0xF                    ; Flags & Limit (high, bits 16-19)
        db 0                                        ; Base (high, bits 24-31)
    .TSS: equ $ - GDT
        dd 0x00000068
        dd 0x00CF8900
    .Pointer:
        dw $ - GDT - 1
        dq GDT

section .text
align 8
start:
	cli
	mov esp, stack_end
	mov ebp, stack_end

	push DWORD 0
	push ebx

	mov edi, 0x1000
	mov cr3, edi
	xor eax, eax
	mov ecx, 4096
	rep stosd
	mov edi, cr3

	mov DWORD [edi], kernel_pdpt_0 + 3      ; Set the uint32_t at the destination index to 0x2003.
	mov edi, kernel_pdpt_0                  ; Add 0x1000 to the destination index.
	mov DWORD [edi], kernel_pd_0 + 3        ; Set the uint32_t at the destination index to 0x3003.
	mov edi, kernel_pd_0                    ; Add 0x1000 to the destination index.
	mov DWORD [edi], kernel_pt_0 + 3        ; Set the uint32_t at the destination index to 0x4003.
	mov edi, kernel_pt_0                    ; Add 0x1000 to the destination index.

	mov ebx, 0x00000003          ; Set the B-register to 0x00000003.
	mov ecx, 512                 ; Set the C-register to 512.
 
.SetEntry:
	mov DWORD [edi], ebx         ; Set the uint32_t at the destination index to the B-register.
	add ebx, 0x1000              ; Add 0x1000 to the B-register.
	add edi, 8                   ; Add eight to the destination index.
	loop .SetEntry               ; Set the next entry.

	;push ebx                ; Call our function to set up basic paging
	;call amd64_shim


	mov eax, cr4            ; Enable the PAE bit
	or eax, 1 << 5
	mov cr4, eax

	mov ecx, 0xC0000080     ; Enable long mode
	rdmsr
	or eax, 1 << 8
	wrmsr

	mov eax, cr0            ; Enable paging
	or eax, 1 << 31
	mov cr0, eax

	lgdt [GDT.Pointer]
	jmp GDT.Code:code64

	bits 64
code64:
	pop rdi
	call amd64_shim
	mov rdi, rax
	call kmain
	cli
halt:
	hlt
	jmp halt