1. 程式人生 > >Linux核心原始碼情景分析-系統呼叫mknod

Linux核心原始碼情景分析-系統呼叫mknod

    普通檔案可以用open或者create建立,FIFO檔案可以用pipe建立,mknod主要用於裝置檔案的建立。

    在核心中,mknod是由sys_mknod實現的,程式碼如下:

asmlinkage long sys_mknod(const char * filename, int mode, dev_t dev) //比如filename為/tmp/server_socket,dev是裝置號
{
	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))//尋找父節點,這裡就是/tmp節點
		error = path_walk(tmp, &nd);
	if (error)
		goto out;
	dentry = lookup_create(&nd, 0);//尋找/tmp/server_socket節點,返回該節點的dentry結構,但是dentry->d_inode為NULL
	error = PTR_ERR(dentry);
	if (!IS_ERR(dentry)) {
		switch (mode & S_IFMT) {
		case 0: case S_IFREG://普通檔案
			error = vfs_create(nd.dentry->d_inode,dentry,mode);
			break;
		case S_IFCHR: case S_IFBLK: case S_IFIFO: case S_IFSOCK://字元裝置,塊裝置,管道,socket檔案
			error = vfs_mknod(nd.dentry->d_inode,mode,dev);//建立/tmp/server_socket節點的inode結構,並關聯到檔案系統中
			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,尋找/tmp/server_socket節點,程式碼如下:

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為server_socket,base為父節點/tmp的dentry結構
{
	struct dentry * dentry;
	struct inode *inode;
	int err;

	inode = base->d_inode;//父節點/tmp的i節點
	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);//建立/tmp/server_socket節點的dentry結構
		dentry = ERR_PTR(-ENOMEM);
		if (!new)
			goto out;
		lock_kernel();
		dentry = inode->i_op->lookup(inode, new);//dentry為NULL
		unlock_kernel();
		if (!dentry)
			dentry = new;//剛剛建立的new賦值給dentry,但是dentry->d_inode為NULL
		else
			dput(new);
	}
out:
	return dentry;
}
    vfs_mknod,建立/tmp/server_socket節點的inode結構,並關聯到檔案系統中,程式碼如下:
int vfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev)//dir為/tmp父節點的inode結構,dentry為/tmp/server_socket節點的dentry結構
{
	int error = -EPERM;

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

	down(&dir->i_zombie);
	if ((S_ISCHR(mode) || S_ISBLK(mode)) && !capable(CAP_MKNOD))//檢驗當前程序是否允許建立裝置節點,此項檢驗僅用於待建立節點為裝置節點時
		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);//對於Ext2,這個函式是ext2_mknod
	unlock_kernel();
exit_lock:
	up(&dir->i_zombie);
	if (!error)
		inode_dir_notify(dir, DN_CREATE);
	return error;
}

    may_create,檢查目標節點的inode結構是否存在。

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

    對於Ext2,dir->i_op->mknod是ext2_mknod,程式碼如下:

static int ext2_mknod (struct inode * dir, struct dentry *dentry, int mode, int rdev)
{
	struct inode * inode = ext2_new_inode (dir, mode);//分配了一個inode結構
	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關聯到檔案系統中,也就是通過父節點inode結構,能夠找到新建立的子節點的inode結構
	if (err)
		goto out_no_entry;
	mark_inode_dirty(inode);//新建立的inode結構設定成"髒"
	d_instantiate(dentry, inode);//將新建立的inode結構與dentry結構相關聯
	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)) {//字元裝置
		inode->i_fop = &def_chr_fops;
		inode->i_rdev = to_kdev_t(rdev);
	} else if (S_ISBLK(mode)) {//塊裝置
		inode->i_fop = &def_blk_fops;
		inode->i_rdev = to_kdev_t(rdev);
		inode->i_bdev = bdget(rdev);
	} else if (S_ISFIFO(mode))//FIFO裝置
		inode->i_fop = &def_fifo_fops;
	else if (S_ISSOCK(mode))//socket裝置
		inode->i_fop = &bad_sock_fops;
	else
		printk(KERN_DEBUG "init_special_inode: bogus imode (%o)\n", mode);
}
    由於新建立的inode結構設定成了“髒”,核心在"同步"記憶體中的inode結構與磁碟上的索引節點的時候,就會將這個inode結構的內容寫到磁碟上分配給這個檔案的索引節點,即ext2_inode資料結構中。由於ext2_inode結構中並不存在i_rdev這麼個成分,而對於裝置檔案卻又不需要使用i_block[]陣列,所以就挪用其i_block[0]來儲存裝置號。要了解這一點,主要看ext2_update_inode程式碼中一個片段:
	if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode))//FIFO裝置和SOCKET裝置沒有裝置號
		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];
    反過來,當通過ext2_read_inode從磁碟上讀入索引節點,併為之在記憶體中建立相應的inode結構時,則先將i_block[]陣列全部複製到i_data[]陣列中。如果是裝置檔案就呼叫init_special_inode將i_block[0]的內容填入inode結構的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]));
    

    我們回過頭想一想,在Linux核心原始碼情景分析-檔案系統的安裝/dev/sdb1,就是通過mknod建立的。