如题,Linux系统体系架构初始化过程一般按照如下流程
start_kernel() ==> setup_arch(&command_line) ==> mdesc = setup_machine_fdt(__atags_pointer)==> for_each_machine_desc(mdesc) ==> return mdesc_best;
1、在linux中,内核启动后调用的第一个C函数是位于linux/init/main.c的Start_kernel()函数,具体实现如下:
asmlinkage void __init start_kernel(void)
{
char * command_line;
extern const struct kernel_param __start___param[], __stop___param[];
smp_setup_processor_id();
/*
* Need to run as early as possible, to initialize the
* lockdep hash:
*/
lockdep_init();
debug_objects_early_init();
/*
* Set up the the initial canary ASAP:
*/
boot_init_stack_canary();
cgroup_init_early();
local_irq_disable();
early_boot_irqs_disabled = true;
/*
* Interrupts are still disabled. Do necessary setups, then
* enable them
*/
tick_init();
boot_cpu_init();
page_address_init();
printk(KERN_NOTICE "%s", linux_banner);
setup_arch(&command_line);
mm_init_owner(&init_mm, &init_task);
mm_init_cpumask(&init_mm);
setup_command_line(command_line);
setup_nr_cpu_ids();
setup_per_cpu_areas();
smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */
build_all_zonelists(NULL);
page_alloc_init();
printk(KERN_NOTICE "Kernel command line: %s\n", boot_command_line);
parse_early_param();
parse_args("Booting kernel", static_command_line, __start___param,
__stop___param - __start___param,
&unknown_bootoption);
jump_label_init();
/*
* These use large bootmem allocations and must precede
* kmem_cache_init()
*/
setup_log_buf(0);
pidhash_init();
vfs_caches_init_early();
sort_main_extable();
trap_init();
mm_init();
/*
* Set up the scheduler prior starting any interrupts (such as the
* timer interrupt). Full topology setup happens at smp_init()
* time - but meanwhile we still have a functioning scheduler.
*/
sched_init();
/*
* Disable preemption - early bootup scheduling is extremely
* fragile until we cpu_idle() for the first time.
*/
preempt_disable();
if (!irqs_disabled()) {
printk(KERN_WARNING "start_kernel(): bug: interrupts were "
"enabled *very* early, fixing it\n");
local_irq_disable();
}
idr_init_cache();
perf_event_init();
rcu_init();
radix_tree_init();
/* init some links before init_ISA_irqs() */
early_irq_init();
init_IRQ();
prio_tree_init();
init_timers();
hrtimers_init();
softirq_init();
timekeeping_init();
time_init();
profile_init();
call_function_init();
if (!irqs_disabled())
printk(KERN_CRIT "start_kernel(): bug: interrupts were "
"enabled early\n");
early_boot_irqs_disabled = false;
local_irq_enable();
/* Interrupts are enabled now so all GFP allocations are safe. */
gfp_allowed_mask = __GFP_BITS_MASK;
kmem_cache_init_late();
/*
* HACK ALERT! This is early. We're enabling the console before
* we've done PCI setups etc, and console_init() must be aware of
* this. But we do want output early, in case something goes wrong.
*/
console_init();
if (panic_later)
panic(panic_later, panic_param);
lockdep_info();
/*
* Need to run this when irqs are enabled, because it wants
* to self-test [hard/soft]-irqs on/off lock inversion bugs
* too:
*/
locking_selftest();
#ifdef CONFIG_BLK_DEV_INITRD
if (initrd_start && !initrd_below_start_ok &&
page_to_pfn(virt_to_page((void *)initrd_start)) < min_low_pfn) {
printk(KERN_CRIT "initrd overwritten (0x%08lx < 0x%08lx) - "
"disabling it.\n",
page_to_pfn(virt_to_page((void *)initrd_start)),
min_low_pfn);
initrd_start = 0;
}
#endif
page_cgroup_init();
enable_debug_pagealloc();
debug_objects_mem_init();
kmemleak_init();
setup_per_cpu_pageset();
numa_policy_init();
if (late_time_init)
late_time_init();
sched_clock_init();
calibrate_delay();
pidmap_init();
anon_vma_init();
#ifdef CONFIG_X86
if (efi_enabled)
efi_enter_virtual_mode();
#endif
thread_info_cache_init();
cred_init();
fork_init(totalram_pages);
proc_caches_init();
buffer_init();
key_init();
security_init();
dbg_late_init();
vfs_caches_init(totalram_pages);
signals_init();
/* rootfs populating might need page-writeback */
page_writeback_init();
#ifdef CONFIG_PROC_FS
proc_root_init();
#endif
cgroup_init();
cpuset_init();
taskstats_init_early();
delayacct_init();
check_bugs();
acpi_early_init(); /* before LAPIC and SMP init */
sfi_init_late();
ftrace_init();
/* Do the rest non-__init'ed, we're now alive */
rest_init();
}
2、首先看Start_kernel()函数第33行setup_arch(&command_line)函数;
setup_arch函数在linux/arch/arm/kernel/setup.c中,定义如下:
void __init setup_arch(char **cmdline_p)
{
struct machine_desc *mdesc;
setup_processor();
mdesc = setup_machine_fdt(__atags_pointer);
if (!mdesc)
mdesc = setup_machine_tags(machine_arch_type);
machine_desc = mdesc;
machine_name = mdesc->name;
if (mdesc->restart_mode)
reboot_setup(&mdesc->restart_mode);
init_mm.start_code = (unsigned long) _text;
init_mm.end_code = (unsigned long) _etext;
init_mm.end_data = (unsigned long) _edata;
init_mm.brk = (unsigned long) _end;
/* populate cmd_line too for later use, preserving boot_command_line */
strlcpy(cmd_line, boot_command_line, COMMAND_LINE_SIZE);
*cmdline_p = cmd_line;
parse_early_param();
sort(&meminfo.bank, meminfo.nr_banks, sizeof(meminfo.bank[0]), meminfo_cmp, NULL);
sanity_check_meminfo();
arm_memblock_init(&meminfo, mdesc);
paging_init(mdesc);
request_standard_resources(mdesc);
if (mdesc->restart)
arm_pm_restart = mdesc->restart;
unflatten_device_tree();
#ifdef CONFIG_SMP
if (is_smp())
smp_init_cpus();
#endif
reserve_crashkernel();
tcm_init();
#ifdef CONFIG_MULTI_IRQ_HANDLER
handle_arch_irq = mdesc->handle_irq;
#endif
#ifdef CONFIG_VT
#if defined(CONFIG_VGA_CONSOLE)
conswitchp = &vga_con;
#elif defined(CONFIG_DUMMY_CONSOLE)
conswitchp = &dummy_con;
#endif
#endif
early_trap_init();
if (mdesc->init_early)
mdesc->init_early();
}
3、看setup_arch函数第六行mdesc = setup_machine_fdt(__atags_pointer);
这里用的一个重要的结构体struct machine_desc *mdesc;内核通过machine_desc结构体来控制系统体系架构相关部分的初始化。machine_desc结构体通过MACHINE_START宏来初始化
首先来看setup_machine_fdt源码:
/**
* setup_machine_fdt - Machine setup when an dtb was passed to the kernel
* @dt_phys: physical address of dt blob
*
* If a dtb was passed to the kernel in r2, then use it to choose the
* correct machine_desc and to setup the system.
*/
struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys)
{
struct boot_param_header *devtree;
struct machine_desc *mdesc, *mdesc_best = NULL;
unsigned int score, mdesc_score = ~1;
unsigned long dt_root;
const char *model;
if (!dt_phys)
return NULL;
devtree = phys_to_virt(dt_phys);
/* check device tree validity */
if (be32_to_cpu(devtree->magic) != OF_DT_HEADER)
return NULL;
/* Search the mdescs for the 'best' compatible value match */
initial_boot_params = devtree;
dt_root = of_get_flat_dt_root();
for_each_machine_desc(mdesc) {
score = of_flat_dt_match(dt_root, mdesc->dt_compat);
if (score > 0 && score < mdesc_score) {
mdesc_best = mdesc;
mdesc_score = score;
}
}
if (!mdesc_best) {
const char *prop;
long size;
early_print("\nError: unrecognized/unsupported "
"device tree compatible list:\n[ ");
prop = of_get_flat_dt_prop(dt_root, "compatible", &size);
while (size > 0) {
early_print("'%s' ", prop);
size -= strlen(prop) + 1;
prop += strlen(prop) + 1;
}
early_print("]\n\n");
dump_machine_table(); /* does not return */
}
model = of_get_flat_dt_prop(dt_root, "model", NULL);
if (!model)
model = of_get_flat_dt_prop(dt_root, "compatible", NULL);
if (!model)
model = "<unknown>";
pr_info("Machine: %s, model: %s\n", mdesc_best->name, model);
/* Retrieve various information from the /chosen node */
of_scan_flat_dt(early_init_dt_scan_chosen, boot_command_line);
/* Initialize {size,address}-cells info */
of_scan_flat_dt(early_init_dt_scan_root, NULL);
/* Setup memory, calling early_init_dt_add_memory_arch */
of_scan_flat_dt(early_init_dt_scan_memory, NULL);
/* Change machine number to match the mdesc we're using */
__machine_arch_type = mdesc_best->nr;
return mdesc_best;
}
4、第28-34行
for_each_machine_desc(mdesc)&score = of_flat_dt_match(dt_root, mdesc->dt_compat);
遍历体系架构类型表,找到一个合适的,return mdesc_best;
5、另外,struct machine_desc *mdesc的初始化:
arch/arm/include/asm/mach/arch.h
struct machine_desc {
unsigned int nr; /* architecture number */
const char *name; /* architecture name */
unsigned long atag_offset; /* tagged list (relative) */
const char **dt_compat; /* array of device tree
* 'compatible' strings */
unsigned int nr_irqs; /* number of IRQs */
#ifdef CONFIG_ZONE_DMA
unsigned long dma_zone_size; /* size of DMA-able area */
#endif
unsigned int video_start; /* start of video RAM */
unsigned int video_end; /* end of video RAM */
unsigned char reserve_lp0 :1; /* never has lp0 */
unsigned char reserve_lp1 :1; /* never has lp1 */
unsigned char reserve_lp2 :1; /* never has lp2 */
char restart_mode; /* default restart mode */
void (*fixup)(struct tag *, char **,
struct meminfo *);
void (*reserve)(void);/* reserve mem blocks */
void (*map_io)(void);/* IO mapping function */
void (*init_early)(void);
void (*init_irq)(void);
struct sys_timer *timer; /* system tick timer */
void (*init_machine)(void);
#ifdef CONFIG_MULTI_IRQ_HANDLER
void (*handle_irq)(struct pt_regs *);
#endif
void (*restart)(char, const char *);
};
MACHINE_START和MACHINE_END宏定义
/*
* Set of macros to define architecture features. This is built into
* a table by the linker.
*/
#define MACHINE_START(_type,_name) \
static const struct machine_desc __mach_desc_##_type \
__used \
__attribute__((__section__(".arch.info.init"))) = { \
.nr = MACH_TYPE_##_type, \
.name = _name,
#define MACHINE_END \
};
MACHINE_START(AM335XEVM, "am335xevm")
/* Maintainer: Texas Instruments */
.atag_offset = 0x100,
.map_io = am335x_evm_map_io,
.init_early = am33xx_init_early,
.init_irq = ti81xx_init_irq,
.handle_irq = omap3_intc_handle_irq,
.timer = &omap3_am33xx_timer,
.init_machine = am335x_evm_init,
MACHINE_END
AM335X体系结构初始化
linux/arch/arm/mach-omap2/Board-arm335xevm.c
以上基于linux3.2.0内核版本