start_kernel()函数

Start_kernel()中调用了一系列初始化函数，以完成kernel本身的设置。这些动作有的是公共的，有的则是需要配置的才会执行的。

在start_kernel()函数中，

输出Linux版本信息（printk(linux_banner)）

设置与体系结构相关的环境（setup_arch()）

页表结构初始化（paging_init()）

使用"arch/alpha/kernel/entry.S"中的入口点设置系统自陷入口（trap_init()）

使用alpha_mv结构和entry.S入口初始化系统IRQ（init_IRQ()）

核心进程调度器初始化（包括初始化几个缺省的Bottom-half，sched_init()）

时间、定时器初始化（包括读取CMOS时钟、估测主频、初始化定时器中断等，time_init()）

提取并分析核心启动参数（从环境变量中读取参数，设置相应标志位等待处理，（parse_options()）

控制台初始化（为输出信息而先于PCI初始化，console_init()）

剖析器数据结构初始化（prof_buffer和prof_len变量）

核心Cache初始化（描述Cache信息的Cache，kmem_cache_init()）

延迟校准（获得时钟jiffies与CPU主频ticks的延迟，calibrate_delay()）

内存初始化（设置内存上下界和页表项初始值，mem_init()）

创建和设置内部及通用cache（"slab_cache"，kmem_cache_sizes_init()）

创建uid taskcount SLAB cache（"uid_cache"，uidcache_init()）

创建文件cache（"files_cache"，filescache_init()）

创建目录cache（"dentry_cache"，dcache_init()）

创建与虚存相关的cache（"vm_area_struct"，"mm_struct"，vma_init()）

块设备读写缓冲区初始化（同时创建"buffer_head"cache用户加速访问，buffer_init()）

创建页cache（内存页hash表初始化，page_cache_init()）

创建信号队列cache（"signal_queue"，signals_init()）

初始化内存inode表（inode_init()）

创建内存文件描述符表（"filp_cache"，file_table_init()）

检查体系结构漏洞（对于alpha，此函数为空，check_bugs()）

SMP机器其余CPU（除当前引导CPU）初始化（对于没有配置SMP的内核，此函数为空，smp_init()）

启动init过程（创建第一个核心线程，调用init()函数，原执行序列调用cpu_idle() 等待调度，init()）

至此start_kernel()结束，基本的核心环境已经建立起来了。

asmlinkage void __init start_kernel(void)

{

 char * command_line;

 unsigned long mempages;

 extern char saved_command_line[];

/*

 * Interrupts are still disabled. Do necessary setups, then

 * enable them

 */

 /*锁内核*/

 lock_kernel();

 /*打印内核的版本和编译的信息*/

 printk(linux_banner);

 /*解析内核的命令行中与内存相关的信息和内存分布信息*/

 setup_arch(&command_line); 

 /*打印命令行信息*/

 printk("Kernel command line: %s\n", saved_command_line);

 /*解析传递给内核的命令行中的0号进程的程序名和环境变量*/

 parse_options(command_line);

 /*常用中断，异常的初始化*/

 trap_init();

 /*非常用的中断初始化*/

 init_IRQ();

 /*调度相关的计时器和底半部的初始化*/

 sched_init();

 /*时钟初始化*/

 time_init();

 /*软中断tasklet初始化*/

 softirq_init();

 /*

 * 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.

 */

 /*终端初始化*/

 console_init();

#ifdef CONFIG_MODULES

 /*初始化模块symbol表大小*/

 init_modules();

#endif

 if (prof_shift) {

 unsigned int size;

 /* only text is profiled */

 prof_len = (unsigned long) &_etext - (unsigned long) &_stext;

 prof_len >>= prof_shift;

 size = prof_len * sizeof(unsigned int) + PAGE_SIZE-1;

 prof_buffer = (unsigned int *) alloc_bootmem(size);

 }

 /*初始化slab分配器*/

 kmem_cache_init();

 sti();

 calibrate_delay();

#ifdef CONFIG_BLK_DEV_INITRD

 if (initrd_start && !initrd_below_start_ok &&

 initrd_start < min_low_pfn << PAGE_SHIFT) {

 printk(KERN_CRIT "initrd overwritten (0x%08lx < 0x%08lx) - "

 "disabling it.\n",initrd_start,min_low_pfn << PAGE_SHIFT);

 initrd_start = 0;

 }

#endif

 /*设置高端内存和内存的标志位*/

 mem_init(); 

 /*初始化内部和一般的slab分配器*/

 kmem_cache_sizes_init();

#ifdef CONFIG_3215_CONSOLE

 con3215_activate();

#endif

#ifdef CONFIG_PROC_FS

 /*建立proc文件系统的目录*/

 proc_root_init();

#endif

 mempages = num_physpages;

 /*初始化最大线程数*/

 fork_init(mempages);

 /*创建一些常用的slab分配器的数据结构*/

 proc_caches_init();

 vfs_caches_init(mempages);

 /*初始化buffer数据结构*/

 buffer_init(mempages);

 /*初始化页表的缓冲结构*/

 page_cache_init(mempages);

 kiobuf_setup();

 /*创建signal的slab数据结构*/

 signals_init();

 bdev_init();

 /*初始化文件系统的inode结构*/

 inode_init(mempages);

#if defined(CONFIG_SYSVIPC)

 /*初始化sysv的信号量，消息，共享内存*/

 ipc_init();

#endif

#if defined(CONFIG_QUOTA)

 dquot_init_hash();

#endif

 check_bugs();

 printk("POSIX conformance testing by UNIFIX\n");

 /* 

 * We count on the initial thread going ok 

 * Like idlers init is an unlocked kernel thread, which will

 * make syscalls (and thus be locked).

 */

 /*初始化SMP,主要是APIC的初始化*/

 smp_init();

 /*创建init进程*/

 kernel_thread(init, NULL, CLONE_FS | CLONE_FILES | CLONE_SIGNAL);

 unlock_kernel();

 current->need_resched = 1;

 /*运行idle进程，进行调度*/

 cpu_idle();

} 

void __init setup_arch(char **cmdline_p)

{

 unsigned long bootmap_size;

 unsigned long start_pfn, max_pfn, max_low_pfn;

 int i;

#ifdef CONFIG_VISWS

 visws_get_board_type_and_rev();

#endif

 /*将rootfs转化成kdev的表示形式，这里跟传统的表示没有不同*/

 ROOT_DEV = to_kdev_t(ORIG_ROOT_DEV);

 drive_info = DRIVE_INFO;

 screen_info = SCREEN_INFO;

 apm_info.bios = APM_BIOS_INFO;

 /*将系统的描述信息写入全局变量中*/

 if( SYS_DESC_TABLE.length != 0 ) {

 MCA_bus = SYS_DESC_TABLE.table[3] &0x2;

 machine_id = SYS_DESC_TABLE.table[0];

 machine_submodel_id = SYS_DESC_TABLE.table[1];

 BIOS_revision = SYS_DESC_TABLE.table[2];

 }

 aux_device_present = AUX_DEVICE_INFO;

#ifdef CONFIG_BLK_DEV_RAM

 /*设置RAMDISK的标志*/

 rd_image_start = RAMDISK_FLAGS & RAMDISK_IMAGE_START_MASK;

 rd_prompt = ((RAMDISK_FLAGS & RAMDISK_PROMPT_FLAG) != 0);

 rd_doload = ((RAMDISK_FLAGS & RAMDISK_LOAD_FLAG) != 0);

#endif

 setup_memory_region();

 if (!MOUNT_ROOT_RDONLY)

 root_mountflags &= ~MS_RDONLY;

 /*在init_mm存放数据段，代码段和堆栈段的起始地址,结束地址*/

 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;

 /*存放内核和数据段的起始和结束地址，这里是转化为物理地址存放的*/

 code_resource.start = virt_to_bus(&_text);

 code_resource.end = virt_to_bus(&_etext)-1;

 data_resource.start = virt_to_bus(&_etext);

 data_resource.end = virt_to_bus(&_edata)-1;

 /*解析命令行中的"mem="参数*/

 parse_mem_cmdline(cmdline_p);

#define PFN_UP(x) (((x) + PAGE_SIZE-1) >> PAGE_SHIFT)

#define PFN_DOWN(x) ((x) >> PAGE_SHIFT)

#define PFN_PHYS(x) ((x) << PAGE_SHIFT)

/*

 * 128MB for vmalloc and initrd

 */

#define VMALLOC_RESERVE (unsigned long)(128 << 20)

#define MAXMEM (unsigned long)(-PAGE_OFFSET-VMALLOC_RESERVE)

#define MAXMEM_PFN PFN_DOWN(MAXMEM)

#define MAX_NONPAE_PFN (1 << 20)

 /*

 * partially used pages are not usable - thus

 * we are rounding upwards:

 */

 /*找到起始物理页号*/ 

 start_pfn = PFN_UP(__pa(&_end));

 /*

 * Find the highest page frame number we have available

 */

 /*从E820中找到最高物理页号*/

 max_pfn = 0;

 for (i = 0; i < e820.nr_map; i++) {

 unsigned long start, end;

 /* RAM? */

 if (e820.map[i].type != E820_RAM)

 continue;

 start = PFN_UP(e820.map[i].addr);

 end = PFN_DOWN(e820.map[i].addr + e820.map[i].size);

 if (start >= end)

 continue;

 if (end > max_pfn)

 max_pfn = end;

 }

 /*

 * Determine low and high memory ranges:

 */

 /*找到最高的低端物理页号,既896M对应的物理页号*/ 

 max_low_pfn = max_pfn;

 if (max_low_pfn > MAXMEM_PFN) {

 max_low_pfn = MAXMEM_PFN;

#ifndef CONFIG_HIGHMEM

 /* Maximum memory usable is what is directly addressable */

 printk(KERN_WARNING "Warning only %ldMB will be used.\n",

 MAXMEM>>20);

 if (max_pfn > MAX_NONPAE_PFN)

 printk(KERN_WARNING "Use a PAE enabled kernel.\n");

 else

 printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n");

#else /* !CONFIG_HIGHMEM */

#ifndef CONFIG_X86_PAE

 if (max_pfn > MAX_NONPAE_PFN) {

 max_pfn = MAX_NONPAE_PFN;

 printk(KERN_WARNING "Warning only 4GB will be used.\n");

 printk(KERN_WARNING "Use a PAE enabled kernel.\n");

 }

#endif /* !CONFIG_X86_PAE */

#endif /* !CONFIG_HIGHMEM */

 }

 /*设置高端内存的起始和结束地址*/

#ifdef CONFIG_HIGHMEM

 highstart_pfn = highend_pfn = max_pfn;

 if (max_pfn > MAXMEM_PFN) {

 highstart_pfn = MAXMEM_PFN;

 printk(KERN_NOTICE "%ldMB HIGHMEM available.\n",

 pages_to_mb(highend_pfn - highstart_pfn));

 }

#endif

 /*

 * Initialize the boot-time allocator (with low memory only):

 */

 /*初始化896M以下的boot内存*/ 

 bootmap_size = init_bootmem(start_pfn, max_low_pfn);

 /*

 * Register fully available low RAM pages with the bootmem allocator.

 */

 /*将896M以下的内存设为可用状态*/ 

 for (i = 0; i < e820.nr_map; i++) {

 unsigned long curr_pfn, last_pfn, size;

 /*

 * Reserve usable low memory

 */

 if (e820.map[i].type != E820_RAM)

 continue;

 /*

 * We are rounding up the start address of usable memory:

 */

 curr_pfn = PFN_UP(e820.map[i].addr);

 if (curr_pfn >= max_low_pfn)

 continue;

 /*

 * ... and at the end of the usable range downwards:

 */

 last_pfn = PFN_DOWN(e820.map[i].addr + e820.map[i].size);

 if (last_pfn > max_low_pfn)

 last_pfn = max_low_pfn;

 /*

 * .. finally, did all the rounding and playing

 * around just make the area go away?

 */

 if (last_pfn <= curr_pfn)

 continue;

 size = last_pfn - curr_pfn;

 free_bootmem(PFN_PHYS(curr_pfn), PFN_PHYS(size));

 }

 /*

 * Reserve the bootmem bitmap itself as well. We do this in two

 * steps (first step was init_bootmem()) because this catches

 * the (very unlikely) case of us accidentally initializing the

 * bootmem allocator with an invalid RAM area.

 */

 /*保留bootmem自己的内存*/ 

 reserve_bootmem(HIGH_MEMORY, (PFN_PHYS(start_pfn) +

 bootmap_size + PAGE_SIZE-1) - (HIGH_MEMORY));

 /*

 * reserve physical page 0 - it's a special BIOS page on many boxes,

 * enabling clean reboots, SMP operation, laptop functions.

 */

 /*保留第一个物理页*/ 

 reserve_bootmem(0, PAGE_SIZE);

#ifdef CONFIG_SMP

 /*

 * But first pinch a few for the stack/trampoline stuff

 * FIXME: Don't need the extra page at 4K, but need to fix

 * trampoline before removing it. (see the GDT stuff)

 */

 reserve_bootmem(PAGE_SIZE, PAGE_SIZE);

 smp_alloc_memory(); /* AP processor realmode stacks in low memory*/

#endif

#ifdef CONFIG_X86_IO_APIC

 /*

 * Find and reserve possible boot-time SMP configuration:

 */

 find_smp_config();

#endif

 /*初始化构建页表*/

 paging_init();

#ifdef CONFIG_X86_IO_APIC

 /*

 * get boot-time SMP configuration:

 */

 if (smp_found_config)

 get_smp_config();

#endif

#ifdef CONFIG_X86_LOCAL_APIC

 init_apic_mappings();

#endif

#ifdef CONFIG_BLK_DEV_INITRD

 /*将RAMDISK的空间保留下来*/

 if (LOADER_TYPE && INITRD_START) {

 if (INITRD_START + INITRD_SIZE <= (max_low_pfn << PAGE_SHIFT)) {

 reserve_bootmem(INITRD_START, INITRD_SIZE);

 initrd_start =

 INITRD_START ? INITRD_START + PAGE_OFFSET : 0;

 initrd_end = initrd_start+INITRD_SIZE;

 }

 else {

 printk("initrd extends beyond end of memory "

 "(0x%08lx > 0x%08lx)\ndisabling initrd\n",

 INITRD_START + INITRD_SIZE,

 max_low_pfn << PAGE_SHIFT);

 initrd_start = 0;

 }

 }

#endif

 /*

 * Request address space for all standard RAM and ROM resources

 * and also for regions reported as reserved by the e820.

 */

 /*将ROM加入资源列表中*/ 

 probe_roms();

 /*将RAM等各种资源加入列表中*/

 for (i = 0; i < e820.nr_map; i++) {

 struct resource *res;

 if (e820.map[i].addr + e820.map[i].size > 0x100000000ULL)

 continue;

 res = alloc_bootmem_low(sizeof(struct resource));

 switch (e820.map[i].type) {

 case E820_RAM: res->name = "System RAM"; break;

 case E820_ACPI: res->name = "ACPI Tables"; break;

 case E820_NVS: res->name = "ACPI Non-volatile Storage"; break;

 default: res->name = "reserved";

 }

 res->start = e820.map[i].addr;

 res->end = res->start + e820.map[i].size - 1;

 res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;

 request_resource(&iomem_resource, res);

 if (e820.map[i].type == E820_RAM) {

 /*

 * We dont't know which RAM region contains kernel data,

 * so we try it repeatedly and let the resource manager

 * test it.

 */

 request_resource(res, &code_resource);

 request_resource(res, &data_resource);

 }

 }

 request_resource(&iomem_resource, &vram_resource);

 /* request I/O space for devices used on all i[345]86 PCs */

 for (i = 0; i < STANDARD_IO_RESOURCES; i++)

 request_resource(&ioport_resource, standard_io_resources+i);

#ifdef CONFIG_VT

#if defined(CONFIG_VGA_CONSOLE)

 conswitchp = &vga_con;

#elif defined(CONFIG_DUMMY_CONSOLE)

 conswitchp = &dummy_con;

#endif

#endif

}