linux内核mount系统调用源码分析

@Author:  Gordon Wu

@Time : 2014/12

0.摘要

mount是Linux很常见的命令，本文将从用户空间的命令行开始，一步一步切入到内核的源代码，解释一个文件系统是如果挂载的。本文基于linux 2.6.32

1.SYSCALL_DEFINE5, 系统调用

Linux kernel通过系统调用的方式为用户提供陷入到内核，mount的系统调用是SYSCALL_DEFINE5，位于fs/namespace.c:
主要完成把一些安装信息从用户空间拷贝到内核空间, 见代码的中文注释。

SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name,
		char __user *, type, unsigned long, flags, void __user *, data)
{
	int ret;
	char *kernel_type;
	char *kernel_dir;
	char *kernel_dev;
	unsigned long data_page;

	ret = copy_mount_string(type, &kernel_type);       // 把用户空间的挂载类型复制到内核
	if (ret < 0)
		goto out_type;

	kernel_dir = getname(dir_name);                    //通过kmem_cache_alloc从names_cachep一个PATH_MAX大小的内核空间，把用户空间的dir_name复制过去
	if (IS_ERR(kernel_dir)) {
		ret = PTR_ERR(kernel_dir);
		goto out_dir;
	}

	ret = copy_mount_string(dev_name, &kernel_dev);     //复制挂载的设备过去
	if (ret < 0)
		goto out_dev;

	ret = copy_mount_options(data, &data_page);
	if (ret < 0)
		goto out_data;

	ret = do_mount(kernel_dev, kernel_dir, kernel_type, flags,   
		(void *) data_page);                           //数据准备好，开始do_mount

	free_page(data_page);
out_data:
	kfree(kernel_dev);
out_dev:
	putname(kernel_dir);
out_dir:
	kfree(kernel_type);
out_type:
	return ret;
}

2. do_mount

验证挂载的选项Flags，以及获取并填充相应挂载目录dir_name的路径Path结构。 再根据挂载选项Flags来判断，挂载的动作。

/*
 * Flags is a 32-bit value that allows up to 31 non-fs dependent flags to
 * be given to the mount() call (ie: read-only, no-dev, no-suid etc).
 *
 * data is a (void *) that can point to any structure up to
 * PAGE_SIZE-1 bytes, which can contain arbitrary fs-dependent
 * information (or be NULL).
 *
 * Pre-0.97 versions of mount() didn't have a flags word.
 * When the flags word was introduced its top half was required
 * to have the magic value 0xC0ED, and this remained so until 2.4.0-test9.
 * Therefore, if this magic number is present, it carries no information
 * and must be discarded.
 */
long do_mount(char *dev_name, char *dir_name, char *type_page,
		  unsigned long flags, void *data_page)
{
	struct path path;
	int retval = 0;
	int mnt_flags = 0;

	/* Discard magic */
	if ((flags & MS_MGC_MSK) == MS_MGC_VAL)
		flags &= ~MS_MGC_MSK;

	/* Basic sanity checks */

	if (!dir_name || !*dir_name || !memchr(dir_name, 0, PAGE_SIZE))           //挂载目录的有效性， memchr是判断dir_name是否在0~PAGE_SIZE（用户空间）中
		return -EINVAL;                                                  

	if (data_page)
		((char *)data_page)[PAGE_SIZE - 1] = 0;

	/* Default to relatime unless overriden */
	if (!(flags & MS_NOATIME))
		mnt_flags |= MNT_RELATIME;

	/* Separate the per-mountpoint flags */
	if (flags & MS_NOSUID)
		mnt_flags |= MNT_NOSUID;