/*
 * Startup Code for MIPS CPU
 *
 * Copyright (C) 2011 Antony Pavlov <antonynpavlov@gmail.com>
 * Used code copyrighted (C) 2009 by Shinya Kuribayashi <skuribay@pobox.com>
 *
 * This file is part of barebox.
 * See file CREDITS for list of people who contributed to this project.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2
 * as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 */

#include <asm/regdef.h>
#include <asm/mipsregs.h>
#include <asm/asm.h>
#include <asm-generic/memory_layout.h>
#include <generated/compile.h>
#include <generated/utsrelease.h>

	/*
	 * ADR macro instruction (inspired by ARM)
	 *
	 * ARM architecture doesn't have PC-relative jump instruction
	 * like MIPS' B/BAL insns.  When ARM makes PC-relative jumps,
	 * it uses ADR insn.  ADR is used to get a destination address
	 * of 'label' against current PC.  With this, ARM can safely
	 * make PC-relative jumps.
	 */
	.macro	ADR rd label temp
	.set	push
	.set	noreorder
	move	\temp, ra			# preserve ra beforehand
	bal	_pc
	 nop
_pc:	addiu	\rd, ra, \label - _pc		# label is assumed to be
	move	ra, \temp			# within pc +/- 32KB
	.set	pop
	.endm

	.set noreorder
	.text
	.section ".text_bare_init"
	.align 4

EXPORT(_start)

	b	__start
	 nop

	.org	0x10
	.ascii	"barebox " UTS_RELEASE " " UTS_VERSION
	.byte	0

	.align 4
__start:
	/* disable watchpoints */
	mtc0	zero, CP0_WATCHLO
	mtc0	zero, CP0_WATCHHI

	/* disable interrupts */
	mfc0	k0, CP0_STATUS
	li	k1, ~ST0_IE
	and	k0, k1
	mtc0	k0, CP0_STATUS

	/* copy barebox to link location */
	ADR	a0, _start, t1	/* a0 <- pc-relative position of _start */

	la	a1, _start	/* link (RAM) _start address */

	beq	a0, a1, stack_setup
	 nop

	la	t0, _start
	la	t1, __bss_start
	subu	t2, t1, t0	/* t2 <- size of barebox */
	addu	a2, a0, t2	/* a2 <- source end address */

#define LONGSIZE	4

copy_loop:
	/* copy from source address [a0] */
	lw		t4, LONGSIZE * 0(a0)
	lw		t5, LONGSIZE * 1(a0)
	lw		t6, LONGSIZE * 2(a0)
	lw		t7, LONGSIZE * 3(a0)
	/* copy fo target address [a1] */
	sw		t4, LONGSIZE * 0(a1)
	sw		t5, LONGSIZE * 1(a1)
	sw		t6, LONGSIZE * 2(a1)
	sw		t7, LONGSIZE * 3(a1)
	addi		a0, LONGSIZE * 4
	subu		t3, a0, a2
	blez		t3, copy_loop
	addi		a1, LONGSIZE * 4

	/*
	 * Dominic Sweetman, See MIPS Run, Morgan Kaufmann, 2nd edition, 2006
	 *
	 * 11.2.2 Stack Argument Structure in o32
	 * ...
	 * At the point where a function is called, sp must be
	 * eight-byte-aligned, matching the alignment of the largest
	 * basic types -- a long long integer or a floating-point double.
	 * The eight-byte alignment is not required by 32-bit MIPS integer
	 * hardware, but it's essential for compatibility with CPUs with
	 * 64-bit registers, and thus part of the rules. Subroutines fit
	 * in with this by always adjusting the stack pointer by a multiple
	 * of eight.
	 * ...
	 * SGI's n32 and n64 standards call for the stack to be maintained
	 * with 16-byte alignment.
	 *
	 */

#if (STACK_BASE + STACK_SIZE) % 16 != 0
#error stack pointer must be 16-byte-aligned
#endif

stack_setup:
	la	sp, STACK_BASE + STACK_SIZE

	/* reserve four 32-bit argument slots */
	addiu	sp, -16

	la	v0, main_entry
	jal     v0
	 nop

	/* No return */

__error:
	b __error
	 nop