mount系统调用

mount命令常用于挂载文件系统，它调用的内核函数是sys_mount，sys_mount主要功能是将用户的命令行参数从用户空间传递到内核空间，并调用do_mount解析参数，完成mount过程。其实现源码如下：

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);//拷贝用户参数
	if (ret < 0)
		goto out_type;

	kernel_dir = getname(dir_name);
	if (IS_ERR(kernel_dir)) {
		ret = PTR_ERR(kernel_dir);
		goto out_dir;
	}

	ret = copy_mount_string(dev_name, &kernel_dev);
	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,//实际执行挂载操作
		(void *) data_page);

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

这里主要调用了do_mount来执行具体的挂载操作

/*
 * 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))
		return -EINVAL;

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

	/* ... and get the mountpoint */
	retval = kern_path(dir_name, LOOKUP_FOLLOW, &path);//查找挂载到目录的path对象?
	if (retval)
		return retval;

	retval = security_sb_mount(dev_name, &path,//安全检查
				   type_page, flags, data_page);
	if (retval)
		goto dput_out;

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

	/* Separate the per-mountpoint flags */
	if (flags & MS_NOSUID)
		mnt_flags |= MNT_NOSUID;
	if (flags & MS_NODEV)
		mnt_flags |= MNT_NODEV;
	if (flags & MS_NOEXEC)
		mnt_flags |= MNT_NOEXEC;
	if (flags & MS_NOATIME)
		mnt_flags |= MNT_NOATIME;
	if (flags & MS_NODIRATIME)
		mnt_flags |= MNT_NODIRATIME;
	if (flags & MS_STRICTATIME)
		mnt_flags &= ~(MNT_RELATIME | MNT_NOATIME);
	if (flags & MS_RDONLY)
		mnt_flags |= MNT_READONLY;

	flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE | MS_BORN |
		   MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT |
		   MS_STRICTATIME);

	if (flags & MS_REMOUNT)
		retval = do_remount(&path, flags & ~MS_REMOUNT, mnt_flags,
				    data_page);
	else if (flags & MS_BIND)
		retval = do_loopback(&path, dev_name, flags & MS_REC);
	else if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE))
		retval = do_change_type(&path, flags);
	else if (flags & MS_MOVE)
		retval = do_move_mount(&path, dev_name);
	else
		retval = do_new_mount(&path, type_page, flags, mnt_flags,//一般是执行一个新的挂载操作
				      dev_name, data_page);
dput_out:
	path_put(&path);
	return retval;
}

在do_mount执行一些参数的检查，以及挂载标志的设置， 函数会根据调用参数 flags 来决定调用以下四个函数之一：do_remount()、 do_loopback()、do_move_mount()、do_add_mount()。这里调用do_new_mount来执行一新的挂载操作：

/*
 * create a new mount for userspace and request it to be added into the
 * namespace's tree
 */
static int do_new_mount(struct path *path, char *type, int flags,
			int mnt_flags, char *name, void *data)
{
	struct vfsmount *mnt;

	if (!type)
		return -EINVAL;

	/* we need capabilities... */
	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	lock_kernel();
	mnt = do_kern_mount(type, flags, name, data);//执行真正的挂载操作
	unlock_kernel();
	if (IS_ERR(mnt))
		return PTR_ERR(mnt);

	return do_add_mount(mnt, path, mnt_flags, NULL);//添加到挂载树
}

struct vfsmount *
do_kern_mount(const char *fstype, int flags, const char *name, void *data)
{
	struct file_system_type *type = get_fs_type(fstype);
	struct vfsmount *mnt;
	if (!type)
		return ERR_PTR(-ENODEV);
	mnt = vfs_kern_mount(type, flags, name, data);/*初始化vfsmount结构，并对其进行赋值*/  
	if (!IS_ERR(mnt) && (type->fs_flags & FS_HAS_SUBTYPE) &&
	    !mnt->mnt_sb->s_subtype)
		mnt = fs_set_subtype(mnt, fstype);//赋值文件系统类型
	put_filesystem(type);
	return mnt;
}

do_kern_mount()处理实际的安装操作并返回一个新安装文件系统描述符的地址, 这里定义了一脸上vfsmount指针，vfsmount结构描述的是一个独立文件系统的挂载信息，每个不同挂载点对应一个独立的vfsmount结构，属于同一文件系统的所有目录和文件隶属于同一个vfsmount，该vfsmount结构对应于该文件系统顶层目录，即挂载目录。

主要工作有二：一是获得一个新的安装区域块，二是将该新的安装区域块加入了安装系统链表

看一下vfs_kern_mount：

struct vfsmount *
vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data)
{
	struct vfsmount *mnt;
	char *secdata = NULL;
	int error;

	if (!type)
		return ERR_PTR(-ENODEV);

	error = -ENOMEM;
	mnt = alloc_vfsmnt(name);//申请了一块该类型的内存空间（struct vfsmount *mnt），并初始化其部分成员变量
	if (!mnt)
		goto out;

	if (flags & MS_KERNMOUNT)
		mnt->mnt_flags = MNT_INTERNAL;

	if (data && !(type->fs_flags & FS_BINARY_MOUNTDATA)) {//文件系统使用的二进制安装数据
		secdata = alloc_secdata();
		if (!secdata)
			goto out_mnt;

		error = security_sb_copy_data(data, secdata);
		if (error)
			goto out_free_secdata;
	}

	error = type->get_sb(type, flags, name, data, mnt);/*调用文件系统控制结构体的get_sb()*/  
	if (error < 0)
		goto out_free_secdata;
	BUG_ON(!mnt->mnt_sb);
	WARN_ON(!mnt->mnt_sb->s_bdi);
	mnt->mnt_sb->s_flags |= MS_BORN;

	error = security_sb_kern_mount(mnt->mnt_sb, flags, secdata);
	if (error)
		goto out_sb;

	/*
	 * filesystems should never set s_maxbytes larger than MAX_LFS_FILESIZE
	 * but s_maxbytes was an unsigned long long for many releases. Throw
	 * this warning for a little while to try and catch filesystems that
	 * violate this rule. This warning should be either removed or
	 * converted to a BUG() in 2.6.34.
	 */
	WARN((mnt->mnt_sb->s_maxbytes < 0), "%s set sb->s_maxbytes to "
		"negative value (%lld)\n", type->name, mnt->mnt_sb->s_maxbytes);

	mnt->mnt_mountpoint = mnt->mnt_root;//设置挂载点的目录项
	mnt->mnt_parent = mnt;// 把新的 vfsmount 结构赋给自身的 parent 这样可以 通过 parent 遍历出所有 mount 的文件系统
	up_write(&mnt->mnt_sb->s_umount);
	free_secdata(secdata);
	return mnt;
out_sb:
	dput(mnt->mnt_root);
	deactivate_locked_super(mnt->mnt_sb);
out_free_secdata:
	free_secdata(secdata);
out_mnt:
	free_vfsmnt(mnt);
out:
	return ERR_PTR(error);
}

get_sb函数主要是获取文件系统的超级块对象

回到do_new_mount函数，接着调用do_add_mount添加到命令空间挂载树上去

/*
 * add a mount into a namespace's mount tree
 * - provide the option of adding the new mount to an expiration list
 */
int do_add_mount(struct vfsmount *newmnt, struct path *path,
		 int mnt_flags, struct list_head *fslist)
{
	int err;

	mnt_flags &= ~(MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL);

	down_write(&namespace_sem);
	/* Something was mounted here while we slept */
	while (d_mountpoint(path->dentry) &&
	       follow_down(path))
		;
	err = -EINVAL;
	if (!(mnt_flags & MNT_SHRINKABLE) && !check_mnt(path->mnt))
		goto unlock;

	/* Refuse the same filesystem on the same mount point */
	err = -EBUSY;
	if (path->mnt->mnt_sb == newmnt->mnt_sb &&
	    path->mnt->mnt_root == path->dentry)
		goto unlock;

	err = -EINVAL;
	if (S_ISLNK(newmnt->mnt_root->d_inode->i_mode))
		goto unlock;

	newmnt->mnt_flags = mnt_flags;
	if ((err = graft_tree(newmnt, path)))//主要是这个函数
		goto unlock;

	if (fslist) /* add to the specified expiration list */
		list_add_tail(&newmnt->mnt_expire, fslist);

	up_write(&namespace_sem);
	return 0;

unlock:
	up_write(&namespace_sem);
	mntput(newmnt);
	return err;
}

这里主要调用 graft_tree()把vfsmnt结构加入到安装系统链表中，同时 graft_tree() 还要将新分配的 struct vfsmount 类型的变量加入到一个hash表中

static int graft_tree(struct vfsmount *mnt, struct path *path)
{
	int err;
	if (mnt->mnt_sb->s_flags & MS_NOUSER)
		return -EINVAL;

	if (S_ISDIR(path->dentry->d_inode->i_mode) !=
	      S_ISDIR(mnt->mnt_root->d_inode->i_mode))
		return -ENOTDIR;

	err = -ENOENT;
	mutex_lock(&path->dentry->d_inode->i_mutex);
	if (cant_mount(path->dentry))
		goto out_unlock;

	if (!d_unlinked(path->dentry))
		err = attach_recursive_mnt(mnt, path, NULL);//
out_unlock:
	mutex_unlock(&path->dentry->d_inode->i_mutex);
	return err;
}

这里主要调用attach_recursive_mnt

/*
 *  @source_mnt : mount tree to be attached
 *  @nd         : place the mount tree @source_mnt is attached
 *  @parent_nd  : if non-null, detach the source_mnt from its parent and
 *  		   store the parent mount and mountpoint dentry.
 *  		   (done when source_mnt is moved)
 *
 *  NOTE: in the table below explains the semantics when a source mount
 *  of a given type is attached to a destination mount of a given type.
 * ---------------------------------------------------------------------------
 * |         BIND MOUNT OPERATION                                            |
 * |**************************************************************************
 * | source-->| shared        |       private  |       slave    | unbindable |
 * | dest     |               |                |                |            |
 * |   |      |               |                |                |            |
 * |   v      |               |                |                |            |
 * |**************************************************************************
 * |  shared  | shared (++)   |     shared (+) |     shared(+++)|  invalid   |
 * |          |               |                |                |            |
 * |non-shared| shared (+)    |      private   |      slave (*) |  invalid   |
 * ***************************************************************************
 * A bind operation clones the source mount and mounts the clone on the
 * destination mount.
 *
 * (++)  the cloned mount is propagated to all the mounts in the propagation
 * 	 tree of the destination mount and the cloned mount is added to
 * 	 the peer group of the source mount.
 * (+)   the cloned mount is created under the destination mount and is marked
 *       as shared. The cloned mount is added to the peer group of the source
 *       mount.
 * (+++) the mount is propagated to all the mounts in the propagation tree
 *       of the destination mount and the cloned mount is made slave
 *       of the same master as that of the source mount. The cloned mount
 *       is marked as 'shared and slave'.
 * (*)   the cloned mount is made a slave of the same master as that of the
 * 	 source mount.
 *
 * ---------------------------------------------------------------------------
 * |         		MOVE MOUNT OPERATION                                 |
 * |**************************************************************************
 * | source-->| shared        |       private  |       slave    | unbindable |
 * | dest     |               |                |                |            |
 * |   |      |               |                |                |            |
 * |   v      |               |                |                |            |
 * |**************************************************************************
 * |  shared  | shared (+)    |     shared (+) |    shared(+++) |  invalid   |
 * |          |               |                |                |            |
 * |non-shared| shared (+*)   |      private   |    slave (*)   | unbindable |
 * ***************************************************************************
 *
 * (+)  the mount is moved to the destination. And is then propagated to
 * 	all the mounts in the propagation tree of the destination mount.
 * (+*)  the mount is moved to the destination.
 * (+++)  the mount is moved to the destination and is then propagated to
 * 	all the mounts belonging to the destination mount's propagation tree.
 * 	the mount is marked as 'shared and slave'.
 * (*)	the mount continues to be a slave at the new location.
 *
 * if the source mount is a tree, the operations explained above is
 * applied to each mount in the tree.
 * Must be called without spinlocks held, since this function can sleep
 * in allocations.
 */
/*将文件系统添加到父文件系统的命名空间中*/ 
static int attach_recursive_mnt(struct vfsmount *source_mnt,
			struct path *path, struct path *parent_path)
{
	LIST_HEAD(tree_list);
	struct vfsmount *dest_mnt = path->mnt;
	struct dentry *dest_dentry = path->dentry;
	struct vfsmount *child, *p;
	int err;

	if (IS_MNT_SHARED(dest_mnt)) {
		err = invent_group_ids(source_mnt, true);
		if (err)
			goto out;
	}
	err = propagate_mnt(dest_mnt, dest_dentry, source_mnt, &tree_list);
	if (err)
		goto out_cleanup_ids;

	spin_lock(&vfsmount_lock);

	if (IS_MNT_SHARED(dest_mnt)) {
		for (p = source_mnt; p; p = next_mnt(p, source_mnt))
			set_mnt_shared(p);
	}
	if (parent_path) {
		detach_mnt(source_mnt, parent_path);
		attach_mnt(source_mnt, path);
		touch_mnt_namespace(parent_path->mnt->mnt_ns);
	} else {
		/*确保新的vfsmount实例的mnt_parent成员指向父文件系统
        的vfsmount实例，而mnt_mountpoint成员指向装载点在父文件
        系统中的dentry实例*/ 
		mnt_set_mountpoint(dest_mnt, dest_dentry, source_mnt);
		commit_tree(source_mnt);
	}

	list_for_each_entry_safe(child, p, &tree_list, mnt_hash) {
		list_del_init(&child->mnt_hash);
		/*将新的mnt添加到全局散列表以及父文件系统mnt实例中
        的子文件系统链表*/
		commit_tree(child);
	}
	spin_unlock(&vfsmount_lock);
	return 0;

 out_cleanup_ids:
	if (IS_MNT_SHARED(dest_mnt))
		cleanup_group_ids(source_mnt, NULL);
 out:
	return err;
}

这里看一下mnt_set_mountpoint

void mnt_set_mountpoint(struct vfsmount *mnt, struct dentry *dentry,
			struct vfsmount *child_mnt)
{
	child_mnt->mnt_parent = mntget(mnt);
	child_mnt->mnt_mountpoint = dget(dentry);
	dentry->d_mounted++;
}

这里关系到我们在进行路径名查找了，参考一下 http://blog.csdn.net/new_abc/article/details/7688880。在文章的最后，如果找到的某个path是安装点就会找到其最近一次被安装文件系统的指针。当找到该指针后，便将 nd 中的 mnt 成员换成该安装区域块指针，同时将 nd 中的 dentry 成员换成安装区域块中的 dentry 指针。

再来看一 下commit_tree

static void commit_tree(struct vfsmount *mnt)
{
	struct vfsmount *parent = mnt->mnt_parent;
	struct vfsmount *m;
	LIST_HEAD(head);
	struct mnt_namespace *n = parent->mnt_ns;

	BUG_ON(parent == mnt);

	list_add_tail(&head, &mnt->mnt_list);
	list_for_each_entry(m, &head, mnt_list)
		m->mnt_ns = n;
	list_splice(&head, n->list.prev);

	list_add_tail(&mnt->mnt_hash, mount_hashtable +
				hash(parent, mnt->mnt_mountpoint));//添加到父节点链表末
	list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);//添加到父节点mnt_mounts链表末
	touch_mnt_namespace(n);
}

这里会把它添加到一个全局的mount_hashtable,这里的插入点是通过hash(parent, mnt->mnt_mountpoint)，即挂载目录先前的vfsmount结构和dentry结构

到这里，文件系统就已经挂载完成了，当下次再次访问到这个挂载点时，就会使用这个新的安装的文件系统指针。

参考：

http://www.ibm.com/developerworks/cn/linux/l-vfs/