操作系统基础：Linux内核启动过程

操作系统基础：Linux内核启动过程

林亮生 + 原创作品转载请注明出处 + 《Linux内核分析》MOOC课程

http://mooc.study.163.com/course/USTC-1000029000

1.gdb跟踪调试内核
qemu -kernel linux-3.18.6/arch/x86/boot/bzImage -initrd rootfs.img -s -S




此时进入调试模式，显示为一片黑屏。

2.gdb
(gdb) file linux-3.18.6/vmlinux  #将文件加载进来
(gdb) target remote:1234         #建立连接
(gdb) break start-kernel           #设置断点
(gdb) c                                     #Continue
(gdb) list                                  #查看代码
(gdb) rest_init
(gdb) c
(gdb) list


进入gdb调试界面


连接调试，打断点在start_kernel，并让程序执行


程序执行后会在start_kernel停下，这是停下后的界面


程序执行到rest_init停下的界面


程序执行结束界面

3.内核源码
start_kernel

asmlinkage __visible void __init start_kernel(void)
{
	char *command_line;
	char *after_dashes;

	set_task_stack_end_magic(&init_task);
	smp_setup_processor_id();
	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
 */
	boot_cpu_init();
	page_address_init();
	pr_notice("%s", linux_banner);
	setup_arch(&command_line);
	mm_init_cpumask(&init_mm);
	setup_command_line(command_line);
	setup_nr_cpu_ids();
	setup_per_cpu_areas();
	boot_cpu_state_init();
	smp_prepare_boot_cpu();	/* arch-specific boot-cpu hooks */

	build_all_zonelists(NULL, NULL);
	page_alloc_init();

	pr_notice("Kernel command line: %s\n", boot_command_line);
	parse_early_param();
	after_dashes = parse_args("Booting kernel",
				  static_command_line, __start___param,
				  __stop___param - __start___param,
				  -1, -1, NULL, &unknown_bootoption);
	if (!IS_ERR_OR_NULL(after_dashes))
		parse_args("Setting init args", after_dashes, NULL, 0, -1, -1,
			   NULL, set_init_arg);

	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 (WARN(!irqs_disabled(),
		 "Interrupts were enabled *very* early, fixing it\n"))
		local_irq_disable();
	idr_init_cache();
	rcu_init();

	/* trace_printk() and trace points may be used after this */
	trace_init();

	context_tracking_init();
	radix_tree_init();
	/* init some links before init_ISA_irqs() */
	early_irq_init();
	init_IRQ();
	tick_init();
	rcu_init_nohz();
	init_timers();
	hrtimers_init();
	softirq_init();
	timekeeping_init();
	time_init();
	sched_clock_postinit();
	printk_nmi_init();
	perf_event_init();
	profile_init();
	call_function_init();
	WARN(!irqs_disabled(), "Interrupts were enabled early\n");
	early_boot_irqs_disabled = false;
	local_irq_enable();

	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("Too many boot %s vars at `%s'", 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) {
		pr_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_ext_init();
	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();
	acpi_early_init();
#ifdef CONFIG_X86
	if (efi_enabled(EFI_RUNTIME_SERVICES))
		efi_enter_virtual_mode();
#endif
#ifdef CONFIG_X86_ESPFIX64
	/* Should be run before the first non-init thread is created */
	init_espfix_bsp();
#endif
	thread_stack_cache_init();
	cred_init();
	fork_init();
	proc_caches_init();
	buffer_init();
	key_init();
	security_init();
	dbg_late_init();
	vfs_caches_init();
	signals_init();
	/* rootfs populating might need page-writeback */
	page_writeback_init();
	proc_root_init();
	nsfs_init();
	cpuset_init();
	cgroup_init();
	taskstats_init_early();
	delayacct_init();

	check_bugs();

	acpi_subsystem_init();
	sfi_init_late();

	if (efi_enabled(EFI_RUNTIME_SERVICES)) {
		efi_late_init();
		efi_free_boot_services();
	}

	ftrace_init();

	/* Do the rest non-__init'ed, we're now alive */
	rest_init();
}

比较关心的几个地方：

set_task_stack_end_magic(&init_task);

创建了0号进程

trap_init();

中断的初始化

mm_init();

内存管理的初始化

sched_init();

调度的初始化

rest_init();

其它的初始化

rest_init方法体

static noinline void __init_refok rest_init(void)
{
	int pid;

	rcu_scheduler_starting();
	/*
	 * We need to spawn init first so that it obtains pid 1, however
	 * the init task will end up wanting to create kthreads, which, if
	 * we schedule it before we create kthreadd, will OOPS.
	 */
	kernel_thread(kernel_init, NULL, CLONE_FS);
	numa_default_policy();
	pid = kernel_thread(kthreadd, NULL, CLONE_FS | CLONE_FILES);
	rcu_read_lock();
	kthreadd_task = find_task_by_pid_ns(pid, &init_pid_ns);
	rcu_read_unlock();
	complete(&kthreadd_done);

	/*
	 * The boot idle thread must execute schedule()
	 * at least once to get things moving:
	 */
	init_idle_bootup_task(current);
	schedule_preempt_disabled();
	/* Call into cpu_idle with preempt disabled */
	cpu_startup_entry(CPUHP_ONLINE);
}

其中

kernel_thread(kernel_init, NULL, CLONE_FS);

kernel_init是个方法，方法体为

static int __ref kernel_init(void *unused)
{
	int ret;

	kernel_init_freeable();
	/* need to finish all async __init code before freeing the memory */
	async_synchronize_full();
	free_initmem();
	mark_rodata_ro();
	system_state = SYSTEM_RUNNING;
	numa_default_policy();

	flush_delayed_fput();

	if (ramdisk_execute_command) {
		ret = run_init_process(ramdisk_execute_command);
		if (!ret)
			return 0;
		pr_err("Failed to execute %s (error %d)\n",
		       ramdisk_execute_command, ret);
	}

	/*
	 * We try each of these until one succeeds.
	 *
	 * The Bourne shell can be used instead of init if we are
	 * trying to recover a really broken machine.
	 */
	if (execute_command) {
		ret = run_init_process(execute_command);
		if (!ret)
			return 0;
		panic("Requested init %s failed (error %d).",
		      execute_command, ret);
	}
	if (!try_to_run_init_process("/sbin/init") ||
	    !try_to_run_init_process("/etc/init") ||
	    !try_to_run_init_process("/bin/init") ||
	    !try_to_run_init_process("/bin/sh"))
		return 0;

	panic("No working init found.  Try passing init= option to kernel. "
	      "See Linux Documentation/init.txt for guidance.");
}

其中

ret = run_init_process(ramdisk_execute_command);

而init_process就是Linux系统中的1号进程，也是第一个用户态进程；ramdisk_execute_command表明了根目录下的程序，找不到会继续往sbin，etc等目录下去寻找。

pid = kernel_thread(kthreadd, NULL, CLONE_FS | CLONE_FILES);

创建内核线程

cpu_startup_entry(CPUHP_ONLINE);

里面是一个while(1)的死循环，当系统没有进程需要执行时就调度到该idle进程。