点击(此处)折叠或打开
asmlinkage void __init start_kernel(void) { char * command_line; //地址指针，指向内核启动参数在内存中的位置（虚拟地址） extern const struct kernel_param __start___param[], __stop___param[]; smp_setup_processor_id(); //针对SMP处理器，如果不是，则是弱引用函数 /* * Need to run as early as possible, to initialize the * lockdep hash: */ lockdep_init(); //内核调试模块，用于检查内核互斥机制潜在的死锁问题 debug_objects_early_init(); /* * Set up the the initial canary ASAP: */ boot_init_stack_canary(); //初始化栈canary值，canary值用于防止栈溢出攻击的堆栈的保护字 cgroup_init_early(); //一组进程的行为控制，做数据结构和其中链表的初始化 local_irq_disable(); //关闭系统总中断 early_boot_irqs_disabled = true; /* * Interrupts are still disabled. Do necessary setups, then * enable them */ tick_init(); //初始化内核时钟系统 boot_cpu_init(); //激活当前CPU page_address_init(); //高端内存相关，未定义的话为空函数 printk(KERN_NOTICE "%s", linux_banner); //打印内核版本信息，内核启动的第一行信息就来自这 setup_arch(&command_line); //1 内核架构相关初始化函数 mm_init_owner(&init_mm, &init_task); //初始化init_mm结构体 mm_init_cpumask(&init_mm); setup_command_line(command_line); //对command_line进行备份与保存 setup_nr_cpu_ids(); //一下三个函数针对SMP处理器，不是SMP处理器都为空函数 setup_per_cpu_areas(); smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */ build_all_zonelists(NULL); //设置内存相关节点和其中的内存域数据结构 page_alloc_init(); //2 打印与解析内核启动参数 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); //使用bootmem分配一个启动信息的缓冲区 pidhash_init(); //使用bootmem分配并初始化PID散列表 vfs_caches_init_early(); //前期VFS缓存初始化 sort_main_extable(); //对内核异常表进行排序 trap_init(); //对内核陷阱异常经行初始化，ARM架构中位空函数 mm_init(); //初始化内核内存分配器，启动信息中的内存信息来自此函数中的mem_init函数 /* * 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(); //初始化调度器数据结构并创建运行队列 /* * Disable preemption - early bootup scheduling is extremely * fragile until we cpu_idle() for the first time. */ preempt_disable(); //禁用抢占和中断，早期启动时期，调度是极其脆弱的 if (!irqs_disabled()) { printk(KERN_WARNING "start_kernel(): bug: interrupts were " "enabled *very* early, fixing it\n"); local_irq_disable(); } idr_init_cache(); //为IDR机制分配缓存 perf_event_init(); //CPU性能检测机制初始化 rcu_init(); //内核RCU机制初始化 radix_tree_init(); //内核radix树算法初始化 /* init some links before init_ISA_irqs() */ early_irq_init(); //前期外部中断描述符初始化 init_IRQ(); //架构相关中断初始化 prio_tree_init(); //基于radix树的优先级搜索树(PST)初始化 init_timers(); //以下5个函数是软中断和内核时钟机制初始化 hrtimers_init(); softirq_init(); timekeeping_init(); time_init(); profile_init(); //profile子系统初始化，内核的性能调试工具 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(); //开启总中断 /* Interrupts are enabled now so all GFP allocations are safe. */ gfp_allowed_mask = __GFP_BITS_MASK; kmem_cache_init_late(); //slab分配器后期初始化 /* * HACK 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(); //初始化控制台 if (panic_later) //检查内核恐慌标准，如果有问题，打印信息 panic(panic_later, panic_param); lockdep_info(); //打印lockdep调试模块信息 /* * 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(); //检查initrd的位置是否符合要求 #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 (0xlx < 0xlx) - " "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(); //使能页分配的调试标志 debug_objects_mem_init(); kmemleak_init(); //内存泄露检测机制的初始化 setup_per_cpu_pageset(); //设置每个CPU的页组并初始化 numa_policy_init(); //分一致性内存访问(NUMA)初始化 if (late_time_init) late_time_init(); sched_clock_init(); //初始化调度时钟 calibrate_delay(); pidmap_init(); //PID分配映射初始化 anon_vma_init(); //匿名虚拟内存域初始化 #ifdef CONFIG_X86 if (efi_enabled) efi_enter_virtual_mode(); #endif thread_info_cache_init(); cred_init(); //任务信用系统初始化 fork_init(totalram_pages); //进程创建机制初始化 proc_caches_init(); buffer_init(); //缓存系统初始化，创建缓存头空间，并检查其大小限制 key_init(); //内核密钥管理系统初始化 security_init(); //内核安全框架初始化 dbg_late_init(); //内核调试系统后期初始化 vfs_caches_init(totalram_pages); //虚拟文件系统缓存初始化 signals_init(); //信号管理系统初始化 /* rootfs populating might need page-writeback */ page_writeback_init(); //页回写机制初始化 #ifdef CONFIG_PROC_FS proc_root_init(); //proc文件系统初始化 #endif cgroup_init(); //control group正式初始化 cpuset_init(); //CPUSET初始化 taskstats_init_early(); //任务状态早期初始化函数，为任务获取高速缓存并初始化互斥机制 delayacct_init(); //任务延迟机制初始化 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(); //3 剩余的初始化 } 2、setup_arch函数 下面分析架构相关的初始化函数setup_arch函数。点击(此处)折叠或打开
void __init setup_arch(char **cmdline_p) { struct machine_desc *mdesc; //设备描述结构体 setup_processor(); //再次检测处理器类型，并初始化处理器相关的底层变量，内核启动时处理器信息就是通过该函数打印 mdesc = setup_machine_fdt(__atags_pointer); //检测bootloader传递的Machine ID与机器ID是否匹配。若匹配打印Machine ID，处理tagged_list；若不匹配，给出出错信息，死循环。 if (!mdesc) mdesc = setup_machine_tags(machine_arch_type); machine_desc = mdesc; machine_name = mdesc->name; #ifdef CONFIG_ZONE_DMA if (mdesc->dma_zone_size) { extern unsigned long arm_dma_zone_size; arm_dma_zone_size = mdesc->dma_zone_size; } #endif if (mdesc->soft_reboot) //设置重启类型，“s”软件重启，“h”硬件重启 reboot_setup("s"); init_mm.start_code = (unsigned long) _text; //init_mm部分数据初始化 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(); sanity_check_meminfo(); arm_memblock_init(&meminfo, mdesc); paging_init(mdesc); request_standard_resources(mdesc); 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、rest_init函数 rest_init函数的主要功能是创建并启动内核线程init。点击(此处)折叠或打开
/* * We need to finalize in a non-__init function or else race conditions * between the root thread and the init thread may cause start_kernel to * be reaped by free_initmem before the root thread has proceeded to * cpu_idle. * * gcc-3.4 accidentally inlines this function, so use noinline. */ //定义一个complete变量告诉init线程：kthreads线程已经创建完成。 static __initdata DECLARE_COMPLETION(kthreadd_done); static noinline void __init_refok rest_init(void) { int pid; rcu_scheduler_starting(); //内核RCU锁机制调度启动 /* * 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 | CLONE_SIGHAND); //创建kernel_init内核线程，PID=1 numa_default_policy(); pid = kernel_thread(kthreadd, NULL, CLONE_FS | CLONE_FILES); //创建kthread内核线程,PID=2 rcu_read_lock(); kthreadd_task = find_task_by_pid_ns(pid, &init_pid_ns); //获取kthread线程信息 rcu_read_unlock(); complete(&kthreadd_done); //通过complete通知kernel_init线程kthread线程已创建成功 /* * The boot idle thread must execute schedule() * at least once to get things moving: */ init_idle_bootup_task(current); //设置当前进程为idle进程类 preempt_enable_no_resched(); //使能抢占，但不重新调度 schedule(); //执行调度，切换进程 /* Call into cpu_idle with preempt disabled */ preempt_disable(); //进程调度完成，禁用抢占 cpu_idle(); //内核本体进入idle状态，用循环消耗空闲的CPU时间 } 4、kernel_init函数 kernel_init函数是内核init线程运行的函数：完成设备驱动程序的初始化，并调用init_post函数启动用户空间的init进程。点击(此处)折叠或打开
static int __init kernel_init(void * unused) { /* * Wait until kthreadd is all set-up. */ wait_for_completion(&kthreadd_done); /* * init can allocate pages on any node */ set_mems_allowed(node_states[N_HIGH_MEMORY]); /* * init can run on any cpu. */ set_cpus_allowed_ptr(current, cpu_all_mask); cad_pid = task_pid(current); smp_prepare_cpus(setup_max_cpus); do_pre_smp_initcalls(); lockup_detector_init(); smp_init(); sched_init_smp(); do_basic_setup(); //重要函数，主要是初始化设备驱动程序 /* Open the /dev/console on the rootfs, this should never fail */ //这里要打开/dev/console节点，在此出错可能的原因是： //1. 制作文件系统时忘记创建/dev/console节点； //2. 文件系统挂载问题，挂载的文件系统不是什么都没有就是挂错了节点。 if (sys_open((const char __user *) "/dev/console", O_RDWR, 0) < 0) printk(KERN_WARNING "Warning: unable to open an initial console.\n"); //复制两次标准输入（0），一个作为标准输出（1），一个作为标准出错（2）。 //完成后，标准输入、标准输出、标准出错都是/dev/console了 (void) sys_dup(0); (void) sys_dup(0); /* * check if there is an early userspace init. If yes, let it do all * the work */ if (!ramdisk_execute_command) ramdisk_execute_command = "/init"; if (sys_access((const char __user *) ramdisk_execute_command, 0) != 0) { ramdisk_execute_command = NULL; prepare_namespace(); } /* * Ok, we have completed the initial bootup, and * we're essentially up and running. Get rid of the * initmem segments and start the user-mode stuff.. */ init_post(); //启动用户空间init进程 return 0; } 5、init_post函数 init_post真正启动用户空间init进程。点击(此处)折叠或打开
/* This is a non __init function. Force it to be noinline otherwise gcc * makes it inline to init() and it becomes part of init.text section */ static noinline int init_post(void) { /* need to finish all async __init code before freeing the memory */ async_synchronize_full(); free_initmem(); //释放所有init.*段中的内存 mark_rodata_ro(); system_state = SYSTEM_RUNNING; //设置系统状态为运行状态 numa_default_policy(); current->signal->flags |= SIGNAL_UNKILLABLE; //设置当前进程（init）为不可杀进程 if (ramdisk_execute_command) { run_init_process(ramdisk_execute_command); printk(KERN_WARNING "Failed to execute %s\n", ramdisk_execute_command); } /* * 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) { run_init_process(execute_command); printk(KERN_WARNING "Failed to execute %s. Attempting " "defaults...\n", execute_command); } run_init_process("/sbin/init"); run_init_process("/etc/init"); run_init_process("/bin/init"); run_init_process("/bin/sh"); //检查完ramdisk_execute_command和execute_command为空的情况下，顺序执行四个初始化程序。 //如果都没有找到就打印出错信息，出现该错误的可能原因是： //1. 启动参数配置有问题：指定了init进程，但是没找到，默认四个程序不在文件系统中； //2. 文件系统挂载有问题； //3. init程序没有执行权限。 panic("No init found. Try passing init= option to kernel. " "See Linux Documentation/init.txt for guidance."); } 6、do_basic_setup函数 内核init线程调用了do_basic_setup函数，这个函数也做了很多内核与驱动的初始化工作。点击(此处)折叠或打开
/* * Ok, the machine is now initialized. None of the devices * have been touched yet, but the CPU subsystem is up and * running, and memory and process management works. * * Now we can finally start doing some real work.. */ static void __init do_basic_setup(void) { cpuset_init_smp(); //对于非SMP处理器，该函数为空 usermodehelper_init(); //创建单线程工作队列khelper shmem_init(); driver_init(); //初始化驱动模型中的各个子系统 init_irq_proc(); //在proc文件系统中创建irq目录 do_ctors(); //调用链接到所有的构造函数 usermodehelper_enable(); //使能单线程工作队列khelper /* * 1. 调用所有编译进内核的驱动的初始化函数，按照各个内核模块初始化函数所定义的启动级别（1~7）， 按顺序调用初始化函数； * 2. 对于同一级别的初始化函数，安装编译是链接的顺序调用，和内核的Makefile编写有关； * 3. 基于某一子系统的驱动，其初始化函数的级别必须低于该子系统初始化函数的级别，如果编写的模块必须和依赖的模块在同一级，就必须Makefile的编写了。 */ do_initcalls(); } 7、driver_init函数 driver_init函数的作用是驱动模型的子系统初始化，位于drivers/base/init.c。点击(此处)折叠或打开
/** * driver_init - initialize driver model. * * Call the driver model init functions to initialize their * subsystems. Called early from init/main.c. */ void __init driver_init(void) { /* These are the core pieces */ devtmpfs_init();点击(此处)折叠或打开
初始化devtmpfs文件系统，驱动核心设备将在这个文件系统中添加它们的设备节点。 这个文件系统可以由内核在挂载根文件系统之后自动挂载到/dev下，也可以在文件系统的启动脚本中手动挂载。 devices_init();点击(此处)折叠或打开
初始化驱动模型中的部分子系统和kobject： devices dev dev/block dev/char buses_init(); //初始化驱动模型中的bus子系统 classes_init(); //初始化驱动模型中的class子系统 firmware_init(); //初始化驱动模型中的firmware子系统 hypervisor_init(); //初始化驱动模型中的hypervisor子系统 /* These are also core pieces, but must come after the * core core pieces. */ platform_bus_init(); //初始化驱动模型中的bus/platform子系统 system_bus_init(); //初始化驱动模型中的devices/system子系统 cpu_dev_init(); //初始化驱动模型中的devices/system/cpu子系统 memory_dev_init(); //初始化驱动模型中的devices/system/memory子系统 }