对技术执着
分类: LINUX
2015-03-14 15:39:02
------------------------------------
本文系本站原创,欢迎转载!
由bootload进入linux后由head.s进入了start_kernel了.
asmlinkage void __init start_kernel(void)
{
char * command_line;
extern struct kernel_param __start___param[], __stop___param[];
………………..
setup_arch(&command_line);
………….
………..
vfs_caches_init(num_physpages); ………….
…………...
rest_init();
}
重要函数解释
1.Setup_arch是解释bootloader传过来的参数,并附相关参数。
void __init setup_arch(char **cmdline_p)
{
struct tag *tags = (struct tag *)&init_tags;
struct machine_desc *mdesc;
char *from = default_command_line;
setup_processor();
mdesc = setup_machine(machine_arch_type);
machine_name = mdesc->name;
if (mdesc->soft_reboot)
reboot_setup("s");
if (mdesc->boot_params)
tags = phys_to_virt(mdesc->boot_params);
/*
* If we have the old style parameters, convert them to
* a tag list.
*/
if (tags->hdr.tag != ATAG_CORE)
convert_to_tag_list(tags);
if (tags->hdr.tag != ATAG_CORE)
tags = (struct tag *)&init_tags;
if (mdesc->fixup)
mdesc->fixup(mdesc, tags, &from, &meminfo);
if (tags->hdr.tag == ATAG_CORE) {
if (meminfo.nr_banks != 0)
squash_mem_tags(tags);
parse_tags(tags);
}
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;
memcpy(saved_command_line, from, COMMAND_LINE_SIZE);
saved_command_line[COMMAND_LINE_SIZE-1] = '\0';
parse_cmdline(cmdline_p, from);
paging_init(&meminfo, mdesc);
request_standard_resources(&meminfo, mdesc);
cpu_init();
/*
* Set up various architecture-specific pointers
*/
init_arch_irq = mdesc->init_irq;
system_timer = mdesc->timer;
init_machine = mdesc->init_machine;
#ifdef CONFIG_VT
#if defined(CONFIG_VGA_CONSOLE)
conswitchp = &vga_con;
#elif defined(CONFIG_DUMMY_CONSOLE)
conswitchp = &dummy_con;
#endif
#endif
}
到这里就不得不说__setup宏。
__setup宏来注册关键字及相关联的处理函数,__setup宏在include/linux/init.h中定义,其原型如下:
__setup(string, function_handler)
其
中:string是关键字,function_handler是关联处理函数。__setup只是告诉内核在启动时输入串中含有string时,内核要去
执行function_handler。String必须以“=”符结束以使parse_args更方便解析。紧随“=”后的任何文本都会作为输入传给
function_handler。
下面的例子来自于init/do_mounts.c,其中root_dev_setup作为处理程序被注册给“root=”关键字:
__setup("root=", root_dev_setup);
比如我们在启动向参数终有
noinitrd root=/dev/mtdblock2 console=/linuxrc
setup_arch解释时会发现root=/dev/mtdblock2,然后它就会调用root_dev_setup
static int __init root_dev_setup(char *line)
{
strlcpy(saved_root_name, line, sizeof(saved_root_name));
return 1;
}
我们容易看出,这个函数就是给saved_root_name赋值,saved_root_name这个全局变量非常重要,在后面的根目录加载还会讲到。
同理,其他参数也会做相应处理。
2. vfs_caches_init
void __init vfs_caches_init(unsigned long mempages)
{
unsigned long reserve;
/* Base hash sizes on available memory, with a reserve equal to
150% of current kernel size */
reserve = min((mempages - nr_free_pages()) * 3/2, mempages - 1);
mempages -= reserve;
names_cachep = kmem_cache_create("names_cache", PATH_MAX, 0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL);
filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC, filp_ctor, filp_dtor);
dcache_init(mempages);
inode_init(mempages);
files_init(mempages);
mnt_init(mempages);
bdev_cache_init();
chrdev_init();
}
Mnt_init会创建一个rootfs,这个是虚拟的rootfs,是内存文件系统(和ramfs),后面还会指向具体的根文件系统。
void __init mnt_init(unsigned long mempages)
{
struct list_head *d;
unsigned int nr_hash;
int i;
mnt_cache = kmem_cache_create("mnt_cache", sizeof(struct vfsmount),
0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL);
sysfs_init();
init_rootfs();//注册rootfs文件系统。
init_mount_tree();//创建rootfs文件系统
}
static void __init init_mount_tree(void)
{
struct vfsmount *mnt;
struct namespace *namespace;
struct task_struct *g, *p;
mnt = do_kern_mount("rootfs", 0, "rootfs", NULL);//创建了文件系统
if (IS_ERR(mnt))
panic("Can't create rootfs");
namespace = kmalloc(sizeof(*namespace), GFP_KERNEL);
if (!namespace)
panic("Can't allocate initial namespace");
atomic_set(&namespace->count, 1);
INIT_LIST_HEAD(&namespace->list);
init_rwsem(&namespace->sem);
list_add(&mnt->mnt_list, &namespace->list);
namespace->root = mnt;
mnt->mnt_namespace = namespace;
init_task.namespace = namespace;
read_lock(&tasklist_lock);
do_each_thread(g, p) {
get_namespace(namespace);
p->namespace = namespace;
} while_each_thread(g, p);
read_unlock(&tasklist_lock);
set_fs_pwd(current->fs, namespace->root, namespace->root->mnt_root);
set_fs_root(current->fs, namespace->root, namespace->root->mnt_root);//将rootfs设为根文件系统,这里只是暂时的。
}
大家可能会会说为什么要这样一个过程了,为什么不直接将我们设置的root=/dev/mtdblock2设备做为根文件系统挂载啊。
首先有两方面的原因
1.可能内核中没有根文件系统设备的驱动(usb,sata硬盘的驱动),需要像initrd,initramdisk,cpio-initrd
2.因为我们的root设备往往以设备文件的形式给出,如果没有文件系统,怎么会有设备文件之说呢,内核怎么知道如何访问根文件系统设备,这就是鸡蛋和鸡的问题,也许有人又说哪这个虚拟的根文件系统的设备文件在哪。其实由于其是虚拟的,叫内存文件系统,也就是人为的给它一个设备号(0,255),人为的创建内存根目录。
3.rest_init
static void noinline rest_init(void)
__releases(kernel_lock)
{
kernel_thread(init, NULL, CLONE_FS | CLONE_SIGHAND);//大名鼎鼎的init进程
numa_default_policy();
unlock_kernel();
preempt_enable_no_resched();
/*
* The boot idle thread must execute schedule()
* at least one to get things moving:
*/
schedule();
cpu_idle();
}
下面我们就来Init函数
static int init(void * unused)
{
……………
………….
populate_rootfs();//检测initrd,initramdisk,cpio-initrd等
do_basic_setup();
/*
* check if there is an early userspace init. If yes, let it do all
* the work
*/
if (sys_access((const char __user *) "/init", 0) == 0)//
execute_command = "/init";
else
prepare_namespace();//挂载真正的根文件系统
//这之后真正的根文件系统已经建立
* 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..
*/
free_initmem();
unlock_kernel();
system_state = SYSTEM_RUNNING;
numa_default_policy();
if (sys_open((const char __user *) "/dev/console", O_RDWR, 0) < 0)
printk(KERN_WARNING "Warning: unable to open an initial console.\n");
(void) sys_dup(0);
(void) sys_dup(0);
/*
* 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);
run_init_process("/sbin/init");
run_init_process("/etc/init");
run_init_process("/bin/init");
run_init_process("/bin/sh");
panic("No init found. Try passing init= option to kernel.");
}
下面分析上面重要的函数
1. populate_rootfs负责检测initrd。
void __init populate_rootfs(void)
{
char *err = unpack_to_rootfs(__initramfs_start,
__initramfs_end - __initramfs_start, 0);
if (err)
panic(err);
#ifdef CONFIG_BLK_DEV_INITRD
if (initrd_start) {//initrd检测
int fd;
printk(KERN_INFO "checking if image is initramfs...");
err = unpack_to_rootfs((char *)initrd_start,
initrd_end - initrd_start, 1);
if (!err) {
printk(" it is\n");
unpack_to_rootfs((char *)initrd_start,
initrd_end - initrd_start, 0);
free_initrd_mem(initrd_start, initrd_end);
return;
}
printk("it isn't (%s); looks like an initrd\n", err);
fd = sys_open("/initrd.image", O_WRONLY|O_CREAT, 700);
if (fd >= 0) {
sys_write(fd, (char *)initrd_start,
initrd_end - initrd_start);
//将内存中的initrd(通常由bootload加载到内存中)赋值到initrd.image中,以释放其占用的内存资源。
sys_close(fd);
free_initrd_mem(initrd_start, initrd_end);//释放内存资源
}
}
#endif
}
2.然后就是
prepare_namespace(),它负责具体根文件系统挂载。
void __init prepare_namespace(void)
{
int is_floppy;
mount_devfs();//挂载devfs文件系统到/dev目录。这个是必须的,因为initrd要放到/dev/ram0里
if (root_delay) {
printk(KERN_INFO "Waiting %dsec before mounting root device...\n",
root_delay);
ssleep(root_delay);
}
md_run_setup();
if (saved_root_name[0]) {
root_device_name = saved_root_name;
ROOT_DEV = name_to_dev_t(root_device_name);
if (strncmp(root_device_name, "/dev/", 5) == 0)
root_device_name += 5;
}
is_floppy = MAJOR(ROOT_DEV) == FLOPPY_MAJOR;
if (initrd_load())
goto out;
if (is_floppy && rd_doload && rd_load_disk(0))
ROOT_DEV = Root_RAM0;//
//如果我们在bootoption哟参数root=/dev/mtdblock2,ROOT_DEV就为/dev/mtdblock设备号。
mount_root();
out:
umount_devfs("/dev"); //devfs从虚拟的根文件系统的/dev umount
sys_mount(".", "/", NULL, MS_MOVE, NULL);//将挂载点从当前目录 【/root】(在mount_root函数中设置的)移到根目录
sys_chroot("."); //将当前目录即【/root】(真正文件系统挂载的目录)做为系统根目录, security_sb_post_mountroot();
mount_devfs_fs ();//将devfs挂到真正根文件系统的/dev
}
void __init mount_root(void)
{
#ifdef CONFIG_ROOT_NFS
if (MAJOR(ROOT_DEV) == UNNAMED_MAJOR) {
if (mount_nfs_root())
return;
printk(KERN_ERR "VFS: Unable to mount root fs via NFS, trying floppy.\n");
ROOT_DEV = Root_FD0;
}
#endif
#ifdef CONFIG_BLK_DEV_FD
if (MAJOR(ROOT_DEV) == FLOPPY_MAJOR) {
/* rd_doload is 2 for a dual initrd/ramload setup */
if (rd_doload==2) {
if (rd_load_disk(1)) {
ROOT_DEV = Root_RAM1;
root_device_name = NULL;
}
} else
change_floppy("root floppy");
}
#endif
create_dev("/dev/root", ROOT_DEV, root_device_name);//创建ROOT_DEV设备文件即为根文件系统设备文件。
mount_block_root("/dev/root", root_mountflags);//挂载根文件系统,root_mountflags为文件系统类型。
}
void __init mount_block_root(char *name, int flags)
{
char *fs_names = __getname();
char *p;
char b[BDEVNAME_SIZE];
get_fs_names(fs_names);//获得文件系统类型,如果在bootoption里有,则就为这个文件系统类型,如果没有指定,则返回filesytem链上所有类型,下面再对每个进行尝试.
retry:
for (p = fs_names; *p; p += strlen(p)+1) {
int err = do_mount_root(name, p, flags, root_mount_data);//将文件系统挂到/root目录,p为文件系统类型,由get_fs_names得到
switch (err) {
case 0:
goto out;
case -EACCES:
flags |= MS_RDONLY;
goto retry;
case -EINVAL:
continue;
}
/*
* Allow the user to distinguish between failed sys_open
* and bad superblock on root device.
*/
__bdevname(ROOT_DEV, b);
printk("VFS: Cannot open root device \"%s\" or %s\n",
root_device_name, b);
printk("Please append a correct \"root=\" boot option\n");
panic("VFS: Unable to mount root fs on %s", b);
}
panic("VFS: Unable to mount root fs on %s", __bdevname(ROOT_DEV, b));
out:
putname(fs_names);
}
static int __init do_mount_root(char *name, char *fs, int flags, void *data)
{
int err = sys_mount(name, "/root", fs, flags, data);
if (err)
return err;
sys_chdir("/root");/将当前目录设为/root目录
ROOT_DEV = current->fs->pwdmnt->mnt_sb->s_dev;
printk("VFS: Mounted root (%s filesystem)%s.\n",
current->fs->pwdmnt->mnt_sb->s_type->name,
current->fs->pwdmnt->mnt_sb->s_flags & MS_RDONLY ?
" readonly" : "");
return 0;
}
到此根文件系统挂载完成。
整个函数调用路径如下
Start_kernel->rest_init->init-> prepare_namespace-> mount_root-> mount_block_root do_mount_root-> sys_mount(name, "/root", fs, flags, data)-> sys_chroot(".");