/*
 * crt0 - C-runtime startup Code for AArch64 U-Boot
 *
 * (C) Copyright 2013
 * David Feng <fenghua@phytium.com.cn>
 *
 * (C) Copyright 2012
 * Albert ARIBAUD <albert.u.boot@aribaud.net>
 *
 * SPDX-License-Identifier:	GPL-2.0+
 */

#include <config.h>
#include <asm-offsets.h>
#include <asm/macro.h>
#include <linux/linkage.h>

/*
 * This file handles the target-independent stages of the U-Boot
 * start-up where a C runtime environment is needed. Its entry point
 * is _main and is branched into from the target's start.S file.
 *
 * _main execution sequence is:
 *
 * 1. Set up initial environment for calling board_init_f().
 *    This environment only provides a stack and a place to store
 *    the GD ('global data') structure, both located in some readily
 *    available RAM (SRAM, locked cache...). In this context, VARIABLE
 *    global data, initialized or not (BSS), are UNAVAILABLE; only
 *    CONSTANT initialized data are available.
 *
 * 2. Call board_init_f(). This function prepares the hardware for
 *    execution from system RAM (DRAM, DDR...) As system RAM may not
 *    be available yet, , board_init_f() must use the current GD to
 *    store any data which must be passed on to later stages. These
 *    data include the relocation destination, the future stack, and
 *    the future GD location.
 *
 * (the following applies only to non-SPL builds)
 *
 * 3. Set up intermediate environment where the stack and GD are the
 *    ones allocated by board_init_f() in system RAM, but BSS and
 *    initialized non-const data are still not available.
 *
 * 4. Call relocate_code(). This function relocates U-Boot from its
 *    current location into the relocation destination computed by
 *    board_init_f().
 *
 * 5. Set up final environment for calling board_init_r(). This
 *    environment has BSS (initialized to 0), initialized non-const
 *    data (initialized to their intended value), and stack in system
 *    RAM. GD has retained values set by board_init_f(). Some CPUs
 *    have some work left to do at this point regarding memory, so
 *    call c_runtime_cpu_setup.
 *
 * 6. Branch to board_init_r().
 */

ENTRY(_main)

/*
 * Set up initial C runtime environment and call board_init_f(0).
 */
	ldr	x0, =(CONFIG_SYS_INIT_SP_ADDR)
	sub	x0, x0, #GD_SIZE	/* allocate one GD above SP */
	bic	sp, x0, #0xf	/* 16-byte alignment for ABI compliance */
	mov	x18, sp			/* GD is above SP */
	mov	x0, #0
	bl	board_init_f

/*
 * Set up intermediate environment (new sp and gd) and call
 * relocate_code(addr_moni). Trick here is that we'll return
 * 'here' but relocated.
 */
	ldr	x0, [x18, #GD_START_ADDR_SP]	/* x0 <- gd->start_addr_sp */
	bic	sp, x0, #0xf	/* 16-byte alignment for ABI compliance */
	ldr	x18, [x18, #GD_BD]		/* x18 <- gd->bd */
	sub	x18, x18, #GD_SIZE		/* new GD is below bd */

	adr	lr, relocation_return
	ldr	x9, [x18, #GD_RELOC_OFF]	/* x9 <- gd->reloc_off */
	add	lr, lr, x9	/* new return address after relocation */
	ldr	x0, [x18, #GD_RELOCADDR]	/* x0 <- gd->relocaddr */
	b	relocate_code

relocation_return:

/*
 * Set up final (full) environment
 */
	bl	c_runtime_cpu_setup		/* still call old routine */

/*
 * Clear BSS section
 */
	ldr	x0, =__bss_start		/* this is auto-relocated! */
	ldr	x1, =__bss_end			/* this is auto-relocated! */
	mov	x2, #0
clear_loop:
	str	x2, [x0]
	add	x0, x0, #8
	cmp	x0, x1
	b.lo	clear_loop

	/* call board_init_r(gd_t *id, ulong dest_addr) */
	mov	x0, x18				/* gd_t */
	ldr	x1, [x18, #GD_RELOCADDR]	/* dest_addr */
	b	board_init_r			/* PC relative jump */

	/* NOTREACHED - board_init_r() does not return */

ENDPROC(_main)