下面的代码基于amlogic的SDK的code示例。
start.S为整个u-boot的入口
start.S(arch\arm\cpu\armv8\start.S)
#include <asm-offsets.h>
#include <config.h>
#include <version.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:
/*
* 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 */
ldr x0, =COUNTER_FREQUENCY
msr cntfrq_el0, x0 /* Initialize CNTFRQ */
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:
/*
* 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
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
*/
master_cpu:
bl _main
主要的流程如下:
(1)根据当前的EL级别,配置中断向量、MMU、Endian、i/d Cache等。
(2)配置ARM的勘误表,具体可参考apply_core_errata函数。
(3)调用lowlevel_init。
(4)如果是多CPU的场景,处理其它的CPU的boot。
(5)跳转到arm公共的_main中执行。
跳转到crt0_64.S(arch\arm\lib\crt0_64.S)中:
#include <config.h>
#include <asm-offsets.h>
#include <asm/macro.h>
#include <linux/linkage.h>
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)
主要流程如下(源码注释翻译):
(1)设置board_init_f()初始化环境。
(2)调用board_init_f()。
如果是非SPL,则执行(3)-(6)
(3)设置board_init_f()在系统内存中分配的堆栈和GD中间环境,BSS 和非常量数据任然不可用。
(4)调用relocate_code()。
(5)设置calling board_init_r()调用环境。
(6)调用calling board_init_r()。
后续board_init_f()及board_init_r()都是C语言实现了,汇编部分到此为止,喜欢深入研究的可以多了解,下节我们分析C语言实现部分,也是我们日常经常需要修改的地方。