/*
 * (C) Copyright 2013
 * David Feng <fenghua@phytium.com.cn>
 *
 * SPDX-License-Identifier:	GPL-2.0+
 */

#include <asm-offsets.h>
#include <config.h>
#include <linux/linkage.h>
#include <asm/macro.h>
#include <asm/armv8/mmu.h>

/*************************************************************************
 *
 * Startup Code (reset vector)
 *
 *************************************************************************/

.globl	_start
_start:
	b	reset

	.align 3

.globl	_TEXT_BASE
_TEXT_BASE:
	.quad	CONFIG_SYS_TEXT_BASE

/*
 * These are defined in the linker script.
 */
.globl	_end_ofs
_end_ofs:
	.quad	_end - _start

.globl	_bss_start_ofs
_bss_start_ofs:
	.quad	__bss_start - _start

.globl	_bss_end_ofs
_bss_end_ofs:
	.quad	__bss_end - _start

reset:
#ifdef CONFIG_SYS_RESET_SCTRL
	bl reset_sctrl
#endif
	/*
	 * Could be EL3/EL2/EL1, Initial State:
	 * Little Endian, MMU Disabled, i/dCache Disabled
	 */
	adr	x0, vectors
	switch_el x1, 3f, 2f, 1f
3:	msr	vbar_el3, x0
	mrs	x0, scr_el3
	orr	x0, x0, #0xf			/* SCR_EL3.NS|IRQ|FIQ|EA */
	msr	scr_el3, x0
	msr	cptr_el3, xzr			/* Enable FP/SIMD */
#ifdef COUNTER_FREQUENCY
	ldr	x0, =COUNTER_FREQUENCY
	msr	cntfrq_el0, x0			/* Initialize CNTFRQ */
#endif
	b	0f
2:	msr	vbar_el2, x0
	mov	x0, #0x33ff
	msr	cptr_el2, x0			/* Enable FP/SIMD */
	b	0f
1:	msr	vbar_el1, x0
	mov	x0, #3 << 20
	msr	cpacr_el1, x0			/* Enable FP/SIMD */
0:

	/* Apply ARM core specific erratas */
	bl	apply_core_errata

	/*
	 * Cache/BPB/TLB Invalidate
	 * i-cache is invalidated before enabled in icache_enable()
	 * tlb is invalidated before mmu is enabled in dcache_enable()
	 * d-cache is invalidated before enabled in dcache_enable()
	 */

	/* Processor specific initialization */
	bl	lowlevel_init

#ifdef CONFIG_ARMV8_MULTIENTRY
	branch_if_master x0, x1, master_cpu

	/*
	 * Slave CPUs
	 */
slave_cpu:
	wfe
	ldr	x1, =CPU_RELEASE_ADDR
	ldr	x0, [x1]
	cbz	x0, slave_cpu
	br	x0			/* branch to the given address */
master_cpu:
	/* On the master CPU */
#endif /* CONFIG_ARMV8_MULTIENTRY */

	bl	_main

#ifdef CONFIG_SYS_RESET_SCTRL
reset_sctrl:
	switch_el x1, 3f, 2f, 1f
3:
	mrs	x0, sctlr_el3
	b	0f
2:
	mrs	x0, sctlr_el2
	b	0f
1:
	mrs	x0, sctlr_el1

0:
	ldr	x1, =0xfdfffffa
	and	x0, x0, x1

	switch_el x1, 6f, 5f, 4f
6:
	msr	sctlr_el3, x0
	b	7f
5:
	msr	sctlr_el2, x0
	b	7f
4:
	msr	sctlr_el1, x0

7:
	dsb	sy
	isb
	b	__asm_invalidate_tlb_all
	ret
#endif

/*-----------------------------------------------------------------------*/

WEAK(apply_core_errata)

	mov	x29, lr			/* Save LR */
	/* For now, we support Cortex-A57 specific errata only */

	/* Check if we are running on a Cortex-A57 core */
	branch_if_a57_core x0, apply_a57_core_errata
0:
	mov	lr, x29			/* Restore LR */
	ret

apply_a57_core_errata:

#ifdef CONFIG_ARM_ERRATA_828024
	mrs	x0, S3_1_c15_c2_0	/* cpuactlr_el1 */
	/* Disable non-allocate hint of w-b-n-a memory type */
	orr	x0, x0, #1 << 49
	/* Disable write streaming no L1-allocate threshold */
	orr	x0, x0, #3 << 25
	/* Disable write streaming no-allocate threshold */
	orr	x0, x0, #3 << 27
	msr	S3_1_c15_c2_0, x0	/* cpuactlr_el1 */
#endif

#ifdef CONFIG_ARM_ERRATA_826974
	mrs	x0, S3_1_c15_c2_0	/* cpuactlr_el1 */
	/* Disable speculative load execution ahead of a DMB */
	orr	x0, x0, #1 << 59
	msr	S3_1_c15_c2_0, x0	/* cpuactlr_el1 */
#endif

#ifdef CONFIG_ARM_ERRATA_833471
	mrs	x0, S3_1_c15_c2_0	/* cpuactlr_el1 */
	/* FPSCR write flush.
	 * Note that in some cases where a flush is unnecessary this
	    could impact performance. */
	orr	x0, x0, #1 << 38
	msr	S3_1_c15_c2_0, x0	/* cpuactlr_el1 */
#endif

#ifdef CONFIG_ARM_ERRATA_829520
	mrs	x0, S3_1_c15_c2_0	/* cpuactlr_el1 */
	/* Disable Indirect Predictor bit will prevent this erratum
	    from occurring
	 * Note that in some cases where a flush is unnecessary this
	    could impact performance. */
	orr	x0, x0, #1 << 4
	msr	S3_1_c15_c2_0, x0	/* cpuactlr_el1 */
#endif

#ifdef CONFIG_ARM_ERRATA_833069
	mrs	x0, S3_1_c15_c2_0	/* cpuactlr_el1 */
	/* Disable Enable Invalidates of BTB bit */
	and	x0, x0, #0xE
	msr	S3_1_c15_c2_0, x0	/* cpuactlr_el1 */
#endif
	b 0b
ENDPROC(apply_core_errata)

/*-----------------------------------------------------------------------*/

WEAK(lowlevel_init)
	mov	x29, lr			/* Save LR */

#ifndef CONFIG_ARMV8_MULTIENTRY
#if defined(CONFIG_GICV2) || defined(CONFIG_GICV3)
	/*
	 * For single-entry systems the lowlevel init is very simple.
	 */
	ldr	x0, =GICD_BASE
	bl	gic_init_secure
#endif
#else /* CONFIG_ARMV8_MULTIENTRY is set */
#if defined(CONFIG_GICV2) || defined(CONFIG_GICV3)
	branch_if_slave x0, 1f
	ldr	x0, =GICD_BASE
	bl	gic_init_secure
1:
#if defined(CONFIG_GICV3)
	ldr	x0, =GICR_BASE
	bl	gic_init_secure_percpu
#elif defined(CONFIG_GICV2)
	ldr	x0, =GICD_BASE
	ldr	x1, =GICC_BASE
	bl	gic_init_secure_percpu
#endif
#endif

	branch_if_master x0, x1, 2f

	/*
	 * Slave should wait for master clearing spin table.
	 * This sync prevent salves observing incorrect
	 * value of spin table and jumping to wrong place.
	 */
#if defined(CONFIG_GICV2) || defined(CONFIG_GICV3)
#ifdef CONFIG_GICV2
	ldr	x0, =GICC_BASE
#endif
	bl	gic_wait_for_interrupt
#endif

	/*
	 * All slaves will enter EL2 and optionally EL1.
	 */
	bl	armv8_switch_to_el2
#ifdef CONFIG_ARMV8_SWITCH_TO_EL1
	bl	armv8_switch_to_el1
#endif

#endif /* CONFIG_ARMV8_MULTIENTRY */

2:
	mov	lr, x29			/* Restore LR */
	ret
ENDPROC(lowlevel_init)

WEAK(smp_kick_all_cpus)
	/* Kick secondary cpus up by SGI 0 interrupt */
	mov	x29, lr			/* Save LR */
#if defined(CONFIG_GICV2) || defined(CONFIG_GICV3)
	ldr	x0, =GICD_BASE
	bl	gic_kick_secondary_cpus
#endif
	mov	lr, x29			/* Restore LR */
	ret
ENDPROC(smp_kick_all_cpus)

/*-----------------------------------------------------------------------*/

ENTRY(c_runtime_cpu_setup)
	/* Relocate vBAR */
	adr	x0, vectors
	switch_el x1, 3f, 2f, 1f
3:	msr	vbar_el3, x0
	b	0f
2:	msr	vbar_el2, x0
	b	0f
1:	msr	vbar_el1, x0
0:

	ret
ENDPROC(c_runtime_cpu_setup)