Linux内核源代码情景分析-系统调用mknod

    普通文件可以用open或者create创建,FIFO文件可以用pipe创建,mknod主要用于设备文件的创建。

    在内核中,mknod是由sys_mknod实现的,代码如下:

asmlinkage long sys_mknod(const char * filename, int mode, dev_t dev) //比如filename为/tmp/server_socket,dev是设备号
{
	int error = 0;
	char * tmp;
	struct dentry * dentry;
	struct nameidata nd;

	if (S_ISDIR(mode))
		return -EPERM;
	tmp = getname(filename);
	if (IS_ERR(tmp))
		return PTR_ERR(tmp);

	if (path_init(tmp, LOOKUP_PARENT, &nd))//寻找父节点,这里就是/tmp节点
		error = path_walk(tmp, &nd);
	if (error)
		goto out;
	dentry = lookup_create(&nd, 0);//寻找/tmp/server_socket节点,返回该节点的dentry结构,但是dentry->d_inode为NULL
	error = PTR_ERR(dentry);
	if (!IS_ERR(dentry)) {
		switch (mode & S_IFMT) {
		case 0: case S_IFREG://普通文件
			error = vfs_create(nd.dentry->d_inode,dentry,mode);
			break;
		case S_IFCHR: case S_IFBLK: case S_IFIFO: case S_IFSOCK://字符设备,块设备,管道,socket文件
			error = vfs_mknod(nd.dentry->d_inode,mode,dev);//创建/tmp/server_socket节点的inode结构,并关联到文件系统中
			break;
		case S_IFDIR:
			error = -EPERM;
			break;
		default:
			error = -EINVAL;
		}
		dput(dentry);
	}
	up(&nd.dentry->d_inode->i_sem);
	path_release(&nd);
out:
	putname(tmp);

	return error;
}

    lookup_create,寻找/tmp/server_socket节点,代码如下:

static struct dentry *lookup_create(struct nameidata *nd, int is_dir)
{
	struct dentry *dentry;

	down(&nd->dentry->d_inode->i_sem);
	dentry = ERR_PTR(-EEXIST);
	if (nd->last_type != LAST_NORM)
		goto fail;
	dentry = lookup_hash(&nd->last, nd->dentry);//nd->last是server_socket
	if (IS_ERR(dentry))
		goto fail;
	if (!is_dir && nd->last.name[nd->last.len] && !dentry->d_inode)
		goto enoent;
	return dentry;
enoent:
	dput(dentry);
	dentry = ERR_PTR(-ENOENT);
fail:
	return dentry;
}
struct dentry * lookup_hash(struct qstr *name, struct dentry * base)//name为server_socket,base为父节点/tmp的dentry结构
{
	struct dentry * dentry;
	struct inode *inode;
	int err;

	inode = base->d_inode;//父节点/tmp的i节点
	err = permission(inode, MAY_EXEC);
	dentry = ERR_PTR(err);
	if (err)
		goto out;

	/*
	 * See if the low-level filesystem might want
	 * to use its own hash..
	 */
	if (base->d_op && base->d_op->d_hash) {
		err = base->d_op->d_hash(base, name);
		dentry = ERR_PTR(err);
		if (err < 0)
			goto out;
	}

	dentry = cached_lookup(base, name, 0);
	if (!dentry) {
		struct dentry *new = d_alloc(base, name);//创建/tmp/server_socket节点的dentry结构
		dentry = ERR_PTR(-ENOMEM);
		if (!new)
			goto out;
		lock_kernel();
		dentry = inode->i_op->lookup(inode, new);//dentry为NULL
		unlock_kernel();
		if (!dentry)
			dentry = new;//刚刚创建的new赋值给dentry,但是dentry->d_inode为NULL
		else
			dput(new);
	}
out:
	return dentry;
}
    vfs_mknod,创建/tmp/server_socket节点的inode结构,并关联到文件系统中,代码如下:

int vfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev)//dir为/tmp父节点的inode结构,dentry为/tmp/server_socket节点的dentry结构
{
	int error = -EPERM;

	mode &= ~current->fs->umask;

	down(&dir->i_zombie);
	if ((S_ISCHR(mode) || S_ISBLK(mode)) && !capable(CAP_MKNOD))//检验当前进程是否允许创建设备节点,此项检验仅用于待创建节点为设备节点时
		goto exit_lock;

	error = may_create(dir, dentry);
	if (error)
		goto exit_lock;

	error = -EPERM;
	if (!dir->i_op || !dir->i_op->mknod)
		goto exit_lock;

	DQUOT_INIT(dir);
	lock_kernel();
	error = dir->i_op->mknod(dir, dentry, mode, dev);//对于Ext2,这个函数是ext2_mknod
	unlock_kernel();
exit_lock:
	up(&dir->i_zombie);
	if (!error)
		inode_dir_notify(dir, DN_CREATE);
	return error;
}

    may_create,检查目标节点的inode结构是否存在。

static inline int may_create(struct inode *dir, struct dentry *child) {
	if (child->d_inode)//也就是检查d_inode是否为NULL
		return -EEXIST;
	if (IS_DEADDIR(dir))
		return -ENOENT;
	return permission(dir,MAY_WRITE | MAY_EXEC);
}

    对于Ext2,dir->i_op->mknod是ext2_mknod,代码如下:

static int ext2_mknod (struct inode * dir, struct dentry *dentry, int mode, int rdev)
{
	struct inode * inode = ext2_new_inode (dir, mode);//分配了一个inode结构
	int err = PTR_ERR(inode);

	if (IS_ERR(inode))
		return err;

	inode->i_uid = current->fsuid;
	init_special_inode(inode, mode, rdev);
	err = ext2_add_entry (dir, dentry->d_name.name, dentry->d_name.len, 
			     inode);//inode关联到文件系统中,也就是通过父节点inode结构,能够找到新创建的子节点的inode结构
	if (err)
		goto out_no_entry;
	mark_inode_dirty(inode);//新创建的inode结构设置成"脏"
	d_instantiate(dentry, inode);//将新创建的inode结构与dentry结构相关联
	return 0;

out_no_entry:
	inode->i_nlink--;
	mark_inode_dirty(inode);
	iput(inode);
	return err;
}
void init_special_inode(struct inode *inode, umode_t mode, int rdev)
{
	inode->i_mode = mode;
	if (S_ISCHR(mode)) {//字符设备
		inode->i_fop = &def_chr_fops;
		inode->i_rdev = to_kdev_t(rdev);
	} else if (S_ISBLK(mode)) {//块设备
		inode->i_fop = &def_blk_fops;
		inode->i_rdev = to_kdev_t(rdev);
		inode->i_bdev = bdget(rdev);
	} else if (S_ISFIFO(mode))//FIFO设备
		inode->i_fop = &def_fifo_fops;
	else if (S_ISSOCK(mode))//socket设备
		inode->i_fop = &bad_sock_fops;
	else
		printk(KERN_DEBUG "init_special_inode: bogus imode (%o)\n", mode);
}
    由于新创建的inode结构设置成了“脏”,内核在"同步"内存中的inode结构与磁盘上的索引节点的时候,就会将这个inode结构的内容写到磁盘上分配给这个文件的索引节点,即ext2_inode数据结构中。由于ext2_inode结构中并不存在i_rdev这么个成分,而对于设备文件却又不需要使用i_block[]数组,所以就挪用其i_block[0]来保存设备号。要了解这一点,主要看ext2_update_inode代码中一个片段:

	if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode))//FIFO设备和SOCKET设备没有设备号
		raw_inode->i_block[0] = cpu_to_le32(kdev_t_to_nr(inode->i_rdev));
	else for (block = 0; block < EXT2_N_BLOCKS; block++)
		raw_inode->i_block[block] = inode->u.ext2_i.i_data[block];


    反过来,当通过ext2_read_inode从磁盘上读入索引节点,并为之在内存中创建相应的inode结构时,则先将i_block[]数组全部复制到i_data[]数组中。如果是设备文件就调用init_special_inode将i_block[0]的内容填入inode结构的i_rdev。以下是片段:

for (block = 0; block < EXT2_N_BLOCKS; block++)
		inode->u.ext2_i.i_data[block] = raw_inode->i_block[block];

	if (inode->i_ino == EXT2_ACL_IDX_INO ||
	    inode->i_ino == EXT2_ACL_DATA_INO)
		/* Nothing to do */ ;
	else if (S_ISREG(inode->i_mode)) {
	} else if (S_ISDIR(inode->i_mode)) {
	} else if (S_ISLNK(inode->i_mode)) {
	} else 
		init_special_inode(inode, inode->i_mode,
				   le32_to_cpu(raw_inode->i_block[0]));
    

    我们回过头想一想,在Linux内核源代码情景分析-文件系统的安装,/dev/sdb1,就是通过mknod建立的。

    还有在Linux内核源代码情景分析-基于socket的进程间通信,/tmp/server_socket,也是通过vfs_mknod创建的。

你可能感兴趣的:(Linux内核源代码情景分析)