;*---------------------------------------------------------------------------
;  :Modul.	GravityHD.asm
;  :Contents.	Gravity slave
;  :Author.	JOTD
;  :Original.
;  :Version.	
;  :History.	
;		
;  :Requires.	68000 or higher
;  :Copyright.	Public Domain
;  :Language.	68000 Assembler
;  :Translator.	Barfly V2.9
;  :To Do.
;---------------------------------------------------------------------------*

	INCDIR	Include:
	INCDIR	osemu:
	INCLUDE	whdload.i
	INCLUDE	whdmacros.i

	IFD BARFLY
	OUTPUT	"Gravity.Slave"
	IFND	DEBUG
	BOPT	O+				;enable optimizing
	BOPT	OG+				;enable optimizing
	BOPT	ODd-				;disable mul optimizing
	BOPT	ODe-				;disable mul optimizing
	ENDC
	BOPT	w4-				;disable 64k warnings
	BOPT	wo-			;disable optimizer warnings
	SUPER
	ENDC

;============================================================================

	IFD	DEBUG
CHIPMEMSIZE	= $FF000
FASTMEMSIZE	= $0000
	ELSE
CHIPMEMSIZE	= $80000
FASTMEMSIZE	= $40000
	ENDC

NUMDRIVES	= 1
WPDRIVES	= %1111

DISKSONBOOT
;HDINIT
;HRTMON
;MEMFREE	= $100
;NEEDFPU
;SETPATCH
BOOTBLOCK

;============================================================================


slv_Version	= 16
slv_Flags	= WHDLF_NoError|WHDLF_Examine|WHDLF_EmulDivZero|WHDLF_EmulTrap
slv_keyexit	= $5D	; num '*'

	INCLUDE	kick13.s

;============================================================================

	IFND	.passchk
	DOSCMD	"WDate  >T:date"
.passchk
	ENDC

DECL_VERSION:MACRO
	dc.b	"2.1"
	IFD BARFLY
		dc.b	" "
		INCBIN	"T:date"
	ENDC
	ENDM

	dc.b	"$","VER: slave "
	DECL_VERSION
	dc.b	$A,$D,0


slv_name		dc.b	"Gravity"
	IFD	DEBUG
	dc.b	" (DEBUG MODE)"
	ENDC
		dc.b	0
slv_copy	dc.b	"1989 Imageworks",0
slv_info	dc.b	"adapted & fixed by CFou! & JOTD",10,10
		dc.b	"Set CUSTOM1=1 to disable stars background",10,10
		dc.b	"Version "
		DECL_VERSION
		dc.b	0
slv_CurrentDir
		dc.b	0
	EVEN

;============================================================================


_bootblock:
	movem.l	a0-a2/a6/d0-d1,-(A7)
	;get tags
	lea	(tags,pc),a0
	move.l	_resload(pc),a2
	jsr	(resload_Control,a2)
	
	move.l	custom1(pc),d0
	beq.b	.skip

	;eat some memory to prevent stars to be displayed
	move.l	#$10000,d0
	move.l	#MEMF_CHIP,d1
	move.l	$4.W,a6
	jsr	_LVOAllocMem(a6)
.skip

	movem.l	(a7)+,a0-a2/a6/d0-d1

	jsr	($C,a4)
	movem.l	a0-a2/a6/d0-d1,-(A7)

	move.l	a0,a1
	lea	pl_boot(pc),a0
	move.l	_resload(pc),a2
	jsr	resload_Patch(a2)

	movem.l	(a7)+,a0-a2/a6/d0-d1

	moveq.l	#0,D0
	rts


_quit
	PEA	TDREASON_OK
	MOVE.L	_resload(PC),-(A7)
	add.l	#resload_Abort,(a7)
	rts


pl_boot
	PL_START
	PL_PS	$A564-$A498,check_copylock	; Rixa: remove this
	PL_P	$B98E-$A498,end_disk_read	; Rixa: needs change to $148E
	PL_END

end_disk_read
	movem.l	(a7)+,d1-d7/a0-a6	; stolen
	
	; patch if executable found

	movem.l	d0-d1/a0-a2,-(a7)
	move.l	d2,a0		; start of loaded file

	move.w	(a0)+,d0
	cmp.w	#$601A,d0	; all code chunks start by BRA +$18
	bne.b	.out

	move.l	_resload(pc),a2
	move.l	d2,a1

	move.l	(a0)+,d0	; length/signature

	cmp.l	#$BAE,d0
	beq.b	.st_replay

	cmp.l	#$375A,d0
	beq.b	.code_part_2

	cmp.l	#$1100C,d0	; Rixa: Needs change to $11044
	beq.b	.loader

	cmp.l	#$5D80,d0
	beq.b	.in_game_1

	cmp.l	#$4B1C,d0
	beq.b	.in_game_2

	cmp.l	#$1240,d0
	beq.b	.in_game_3

	cmp.l	#$C80,d0
	beq.b	.in_game_4

	cmp.l	#$5CC,d0
	beq.b	.in_game_5

	bsr	_flushcache
;;	ILLEGAL	; unknown program
.out
	movem.l	(a7)+,d0-d1/a0-a2

	tst.l	d0
	rts

.patch
	jsr	resload_Patch(a2)
	bra.b	.out

; around $8Cxxx

.in_game_5
.in_game_4
.in_game_3
.in_game_2
.in_game_1
	bsr	_flushcache
	bra.b	.out

.loader
	pea	add_a0(pc)

	move.l	(a7)+,$80.W
	pea	trap_1(pc)
	move.l	(a7)+,$84.W
	pea	trap_2(pc)
	move.l	(a7)+,$88.W
	pea	trap_3(pc)
	move.l	(a7)+,$8C.W
	pea	trap_4(pc)
	move.l	(a7)+,$90.W


	patch	$100,emulate_sub_d7_to_d4

	move.l	attnflags(pc),d0
	btst	#AFB_68010,d0
	beq.b	.68000

	; JOTD: don't do it on 68000 because it would crash badly

	lea	pl_loader(pc),a0
	bra.b	.patch
.68000
	lea	pl_loader_68000(pc),a0
	bra.b	.patch
.st_replay
	pea	smc_bra_replay(pc)
	move.l	(a7)+,$94.W

	lea	pl_replay(pc),a0
	bra.b	.patch

.code_part_2
	lea	pl_code_2(pc),a0
	bra.b	.patch

pl_replay
	PL_START
	PL_PS	$309EC-$300B6,fix_dbf_replay
	PL_L	$3067C-$300B6,$4E714E71
	PL_W	$3085E-$300B6,$4E45

	PL_END

; 68010+ only

pl_loader
	PL_START

	; stack-leak error

	PL_PS	$174DA-$C558,fix_stackframe_error	; Rixa: needs change to $AFBA

	PL_I	$17520	; RTE return: does not happen	; Rixa: needs change to $17558?

	PL_NEXT	pl_loader_68000

pl_loader_68000
	PL_START

	; SMC fix	

	PL_W	$1B5F4-$C558,$4E40	; TRAP #0 to simulate SMC ; Rixa: needs change to $F0D4
	PL_W	$1B694-$C558,$4E40	; TRAP #0 to simulate SMC ; Rixa: needs change to $F174
	PL_PS	$1B896-$C558,smc_link	; Rixa: needs change to $F376

	PL_W	$18E72-$C558,$4E44	; Rixa: needs change to $C952
	PL_W	$18EC2-$C558,$4E44	; Rixa: needs change to $C9A2
	PL_W	$18F82-$C558,$4E44	; Rixa: needs change to $CA62
	PL_W	$1902C-$C558,$4E44	; Rixa: needs change to $CB0C
	PL_W	$19A24-$C558,$4E44	; Rixa: needs change to $D504

	PL_L	$1933E-$C558,$4EB80100	; Rixa: needs change to $CE1E

	; copylock check (already disabled BTW)
	; if wrong copylock, clicking on the
	; buttons during the game has no effect!

	PL_L	$11CB4-$C558,$4E714E71	; Rixa: needs to be removed

	; 24-bit access fault problem

	; game loads a an address register then masks it
	; with $FFFFFF sometimes causing 24 bit error
	; (but sometimes it is useful)

	PL_PS	$0E480-$C558,fix_24_bit_d1
	PL_PS	$0FB42-$C558,fix_24_bit_d0
	PL_PS	$0FB8E-$C558,fix_24_bit_d0
	PL_PS	$0FBE4-$C558,fix_24_bit_d0
	PL_PS	$15E6C-$C558,fix_24_bit_d0	; Rixa: needs change to $0994C
	PL_PS	$1860C-$C558,fix_24_bit_d0	; Rixa: needs change to $0C0EC
	PL_PS	$1CB64-$C558,fix_24_bit_d0	; Rixa: needs change to $10644
	PL_PS	$1CE04-$C558,fix_24_bit_d0	; Rixa: needs change to $108E4

	PL_END

pl_code_2
	PL_START
	PL_W	$62A54-$6009A,$4E42	; TRAP #2 to simulate SMC
	PL_W	$629CC-$6009A,$4E41	; TRAP #1 to simulate SMC

	PL_W	$62228-$6009A,$4E44
	PL_W	$628D8-$6009A,$4E44

	PL_PS	$62A04-$6009A,emulate_sub_d2_d3

	; BRA emulation

	PL_W	$600BA-$6009A,$4E43
	PL_W	$600BE-$6009A,$4E43
	PL_W	$600C2-$6009A,$4E43
	PL_W	$600C6-$6009A,$4E43
	PL_W	$600CA-$6009A,$4E43
	PL_W	$600CE-$6009A,$4E43
	PL_W	$600D2-$6009A,$4E43

	PL_END

; the routine in the trap #15 handler is really stoopid:
; it pops SR & return address from supervisor state (SSP) and restores
; it in user state (USP).
; There is not really an immediate stackframe error since the game uses RTR
; instruction, which does not have stackframe check/pop (not like RTE)
;
; BUT the problem is that SSP state is reached using TRAP, and on 68020+ one more
; word is added (stackframe). So SSP value decreases at each call, and ends up
; trashing the code in the title screen, or later.
;
; this is really a vicious bug


fix_stackframe_error
	; first, store return address
	move.l	a0,-(a7)
	lea	.return_address(pc),a0
	move.l	4(a7),(a0)
	move.l	(a7)+,a0
	
	addq.l	#4,a7	; pop the stack to simulate a JMP below

	MOVE	(A7)+,-(A0)		;174DA: 311F	; pop/save SR/CCR from SSP
	MOVE.L	(A7)+,-(A0)		;174DC: 211F	; pop/save return address from SSP

	addq.l	#2,a7			; fix remove stackframe if 68020+

	MOVE.L	A0,-(A7)		;174DE: 2F08

	; return to program

	move.l	.return_address(pc),-(a7)
	rts

.return_address:
	dc.l	0


smc_bra_replay
	movem.l	a0,-(a7)
	move.l	6(a7),a0	; return address
	cmp.l	#$4E714E71,(a0)
	movem.l	(a7)+,a0
	bne.b	.jsr
	; was BRA: branch
	RTE
.jsr
	; tricky: first, recover from the RTE

	movem.l	A0/A1,-(A7)
	move.l	10(A7),A0	; return PC
	lea	.return_address(pc),a1
	move.l	a0,(a1)		; save return address for later on
	lea	.jsr_address(pc),a1
	move.l	(a0),(a1)	; save jsr address for later on
	lea	.recov(pc),a1
	move.l	a1,10(a7)	; change return PC
	movem.l	(A7)+,A0/A1
	rte
.recov
	; now we're in user mode: first push return address
	
	move.l	.return_address(pc),-(a7)
	addq.l	#4,(a7)		; skip JSR operand
	
	; then push JSR operand
	move.l	.jsr_address(pc),-(a7)

	; go
	rts

.return_address
	dc.l	0
.jsr_address
	dc.l	0

	
emulate_sub_d2_d3
	move	d1,d3
	asr	#5,d2
	asr	#5,d3

	movem.l	d0/a0,-(a7)
	move.l	8(a7),a0	; return address
	sub.w	(2,A0),d2
	sub.w	(6,A0),d3
	movem.l	(a7)+,d0/a0

	rts

emulate_sub_d7_to_d4
	move	6(a0),d7	; original

	movem.l	d0/a0,-(a7)
	move.l	8(a7),a0	; return address
	sub.w	($2,A0),d7
	sub.w	($12,A0),d6
	sub.w	($20,A0),d5
	sub.w	($2E,A0),d4
	movem.l	(a7)+,d0/a0

	rts

fix_dbf_replay
	move.w	#12,d0
.bd_loop1
	move.w  d0,-(a7)
        move.b	$dff006,d0	; VPOS
.bd_loop2
	cmp.b	$dff006,d0
	beq.s	.bd_loop2
	move.w	(a7)+,d0
	dbf	d0,.bd_loop1
	addq.l	#4,(a7)
	rts


add_a0
	move.l	a1,-(a7)
	move.l	6(a7),a1	; return address
	add.w	(a1),a0		; simulate lea x(a0),a0 (x depends because of smc grrrr)
	move.l	(a7)+,a1
	add.l	#2,2(a7)	; skip lea opcode
	rte

; < D0: link offset

smc_link
	movem.l	d0/a0/a1,-(a7)
	lea	return_address(pc),a0
	move.l	12(a7),a1
	add.l	#10,a1	; -> leads to adda d0,a6, just after the LINK instruction
	move.l	a1,(a0)+
	ext.l	d0
	move.l	d0,(a0)	; writes required LINK parameter to link_value

	movem.l	(a7)+,d0/a0/a1
	addq.l	#4,a7	; pops up the stack because we're going to LINK

	; LINK emulation

	move.l	a6,-(a7)
	move.l	a7,a6
	add.l	link_value(pc),a7

	; goto next

	move.l	return_address(pc),-(a7)
	rts

; do not separate return_address from link_value variables!
return_address
	dc.l	0
link_value
	dc.l	0

DEF_FIX_24_BIT:MACRO
fix_24_bit_d\1:
	move.l	d7,-(a7)

	move.l	d\1,d7
	rol.l	#8,d7
	tst.b	d7
	beq.b	.out
	cmp.b	_expmem(pc),d7
	beq.b	.out

	; not 0 and not expmem MSB: clear it

	clr.b	d7
	ror.l	#8,d7
	move.l	d7,d\1
.out
	move.l	(a7)+,d7
	rts
	ENDM

	DEF_FIX_24_BIT	0
	DEF_FIX_24_BIT	1

trap_1
	movem.l	d0/a1,-(a7)
	move.l	10(a7),a1	; return address
	add.w	(a1),a3		; simulate lea x(a0),a0 (x depends because of smc grrrr)
	add.w	4(a1),a4	; simulate lea x(a0),a0 (x depends because of smc grrrr)

	move.w	8(a1),d0
	add.w	d0,60(a6)	; simulate addi to 60(a6)
	move.w	(14,a1),d0
	add.w	d0,62(a6)
	movem.l	(a7)+,d0/a1
	add.l	#2+4+6+6,2(a7)	; skip opcodes
	rte

; lea	a5, add d0, add d1

trap_2
	move.l	a1,-(a7)
	move.l	6(a7),a1	; return address

	add.w	(a1),a5	; simulate lea x(a5),a5 (x depends because of smc grrrr)
	add.w	(4,a1),d0	; simulate addi	to d0
	add.w	(8,a1),d1	; simulate addi	to d1

	move.l	(a7)+,a1
	add.l	#2+4+4,2(a7)	; skip opcodes
	rte

; sub #x,d0, sub #x,d1

trap_4
	move.l	a1,-(a7)
	move.l	6(a7),a1	; return address

	sub.w	(a1),d0		; simulate subi	to d0
	sub.w	(4,a1),d1	; simulate subi	to d1

	move.l	(a7)+,a1
	add.l	#2+4,2(a7)	; skip opcodes
	rte

; BRA emulation

trap_3
	movem.l	d0/A0,-(A7)
	move.l	10(A7),A0	; return address
	moveq	#0,d0
	move.w	(a0),d0
	add.l	d0,10(A7)	; RTE -> BRA address
	movem.l	(A7)+,D0/A0
	rte

check_copylock
	move.l	(a7),a0	; A568
	move.l	-80(a0),a0	; lea	$A51A
	cmp.w	#$4AFC,$E(a0)
	bne.b	.nocopylock

	moveq	#0,d0	; original
;;;	move.l	#$DD17A129,d0	; no disk in drive (also one of copylock checksum)
	rts

;	move.l	#$90006,$6198
;	move.l	#$b6c00000,$619C
	
.nocopylock
	jmp	(a0)


tags
	dc.l	WHDLTAG_ATTNFLAGS_GET
attnflags
	dc.l	0
	dc.l	WHDLTAG_CUSTOM1_GET
custom1
	dc.l	0
	dc.l	0

;============================================================================

	END