open.c

包括初始化、进程管理、进程通信、内存管理、设备管理、中断、文件系统、系统调用等精选源码分析。

	set_fs_root(current->fs, nd.mnt, nd.dentry);
	set_fs_altroot();
	error = 0;
dput_and_out:
	path_release(&nd);
out:
	return error;
}

asmlinkage long sys_fchmod(unsigned int fd, mode_t mode)
{
	struct inode * inode;
	struct dentry * dentry;
	struct file * file;
	int err = -EBADF;
	struct iattr newattrs;

	file = fget(fd);
	if (!file)
		goto out;

	dentry = file->f_dentry;
	inode = dentry->d_inode;

	err = -EROFS;
	if (IS_RDONLY(inode))
		goto out_putf;
	err = -EPERM;
	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
		goto out_putf;
	if (mode == (mode_t) -1)
		mode = inode->i_mode;
	newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO);
	newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
	err = notify_change(dentry, &newattrs);

out_putf:
	fput(file);
out:
	return err;
}

asmlinkage long sys_chmod(const char * filename, mode_t mode)
{
	struct nameidata nd;
	struct inode * inode;
	int error;
	struct iattr newattrs;

	error = user_path_walk(filename, &nd);
	if (error)
		goto out;
	inode = nd.dentry->d_inode;

	error = -EROFS;
	if (IS_RDONLY(inode))
		goto dput_and_out;

	error = -EPERM;
	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
		goto dput_and_out;

	if (mode == (mode_t) -1)
		mode = inode->i_mode;
	newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO);
	newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
	error = notify_change(nd.dentry, &newattrs);

dput_and_out:
	path_release(&nd);
out:
	return error;
}

static int chown_common(struct dentry * dentry, uid_t user, gid_t group)
{
	struct inode * inode;
	int error;
	struct iattr newattrs;

	error = -ENOENT;
	if (!(inode = dentry->d_inode)) {
		printk("chown_common: NULL inode\n");
		goto out;
	}
	error = -EROFS;
	if (IS_RDONLY(inode))
		goto out;
	error = -EPERM;
	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
		goto out;
	if (user == (uid_t) -1)
		user = inode->i_uid;
	if (group == (gid_t) -1)
		group = inode->i_gid;
	newattrs.ia_mode = inode->i_mode;
	newattrs.ia_uid = user;
	newattrs.ia_gid = group;
	newattrs.ia_valid =  ATTR_UID | ATTR_GID | ATTR_CTIME;
	/*
	 * If the user or group of a non-directory has been changed by a
	 * non-root user, remove the setuid bit.
	 * 19981026	David C Niemi <[e-mail]>
	 *
	 * Changed this to apply to all users, including root, to avoid
	 * some races. This is the behavior we had in 2.0. The check for
	 * non-root was definitely wrong for 2.2 anyway, as it should
	 * have been using CAP_FSETID rather than fsuid -- 19990830 SD.
	 */
	if ((inode->i_mode & S_ISUID) == S_ISUID &&
		!S_ISDIR(inode->i_mode))
	{
		newattrs.ia_mode &= ~S_ISUID;
		newattrs.ia_valid |= ATTR_MODE;
	}
	/*
	 * Likewise, if the user or group of a non-directory has been changed
	 * by a non-root user, remove the setgid bit UNLESS there is no group
	 * execute bit (this would be a file marked for mandatory locking).
	 * 19981026	David C Niemi <[e-mail]>
	 *
	 * Removed the fsuid check (see the comment above) -- 19990830 SD.
	 */
	if (((inode->i_mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) 
		&& !S_ISDIR(inode->i_mode))
	{
		newattrs.ia_mode &= ~S_ISGID;
		newattrs.ia_valid |= ATTR_MODE;
	}
	error = DQUOT_TRANSFER(dentry, &newattrs);
out:
	return error;
}

asmlinkage long sys_chown(const char * filename, uid_t user, gid_t group)
{
	struct nameidata nd;
	int error;

	error = user_path_walk(filename, &nd);
	if (!error) {
		error = chown_common(nd.dentry, user, group);
		path_release(&nd);
	}
	return error;
}

asmlinkage long sys_lchown(const char * filename, uid_t user, gid_t group)
{
	struct nameidata nd;
	int error;

	error = user_path_walk_link(filename, &nd);
	if (!error) {
		error = chown_common(nd.dentry, user, group);
		path_release(&nd);
	}
	return error;
}


asmlinkage long sys_fchown(unsigned int fd, uid_t user, gid_t group)
{
	struct file * file;
	int error = -EBADF;

	file = fget(fd);
	if (file) {
		error = chown_common(file->f_dentry, user, group);
		fput(file);
	}
	return error;
}

/*
 * Note that while the flag value (low two bits) for sys_open means:
 *	00 - read-only
 *	01 - write-only
 *	10 - read-write
 *	11 - special
 * it is changed into
 *	00 - no permissions needed
 *	01 - read-permission
 *	10 - write-permission
 *	11 - read-write
 * for the internal routines (ie open_namei()/follow_link() etc). 00 is
 * used by symlinks.
 */
struct file *filp_open(const char * filename, int flags, int mode)
{
	int namei_flags, error;
	struct nameidata nd;

	namei_flags = flags;
	if ((namei_flags+1) & O_ACCMODE)
		namei_flags++;
	if (namei_flags & O_TRUNC)
		namei_flags |= 2;

	error = open_namei(filename, namei_flags, mode, &nd);
	if (!error)
		return dentry_open(nd.dentry, nd.mnt, flags);

	return ERR_PTR(error);
}

struct file *dentry_open(struct dentry *dentry, struct vfsmount *mnt, int flags)
{
	struct file * f;
	struct inode *inode;
	int error;

	error = -ENFILE;
	f = get_empty_filp();
	if (!f)
		goto cleanup_dentry;
	f->f_flags = flags;
	f->f_mode = (flags+1) & O_ACCMODE;
	inode = dentry->d_inode;
	if (f->f_mode & FMODE_WRITE) {
		error = get_write_access(inode);
		if (error)
			goto cleanup_file;
	}

	f->f_dentry = dentry;
	f->f_vfsmnt = mnt;
	f->f_pos = 0;
	f->f_reada = 0;
	f->f_op = fops_get(inode->i_fop);
	if (inode->i_sb)
		file_move(f, &inode->i_sb->s_files);
	if (f->f_op && f->f_op->open) {
		error = f->f_op->open(inode,f);
		if (error)
			goto cleanup_all;
	}
	f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC);

	return f;

cleanup_all:
	fops_put(f->f_op);
	if (f->f_mode & FMODE_WRITE)
		put_write_access(inode);
	f->f_dentry = NULL;
	f->f_vfsmnt = NULL;
cleanup_file:
	put_filp(f);
cleanup_dentry:
	dput(dentry);
	mntput(mnt);
	return ERR_PTR(error);
}

/*
 * Find an empty file descriptor entry, and mark it busy.
 */
int get_unused_fd(void)
{
	struct files_struct * files = current->files;
	int fd, error;

  	error = -EMFILE;
	write_lock(&files->file_lock);

repeat:
 	fd = find_next_zero_bit(files->open_fds, 
				files->max_fdset, 
				files->next_fd);

	/*
	 * N.B. For clone tasks sharing a files structure, this test
	 * will limit the total number of files that can be opened.
	 */
	if (fd >= current->rlim[RLIMIT_NOFILE].rlim_cur)
		goto out;

	/* Do we need to expand the fdset array? */
	if (fd >= files->max_fdset) {
		error = expand_fdset(files, fd);
		if (!error) {
			error = -EMFILE;
			goto repeat;
		}
		goto out;
	}
	
	/* 
	 * Check whether we need to expand the fd array.
	 */
	if (fd >= files->max_fds) {
		error = expand_fd_array(files, fd);
		if (!error) {
			error = -EMFILE;
			goto repeat;
		}
		goto out;
	}

	FD_SET(fd, files->open_fds);
	FD_CLR(fd, files->close_on_exec);
	files->next_fd = fd + 1;
#if 1
	/* Sanity check */
	if (files->fd[fd] != NULL) {
		printk("get_unused_fd: slot %d not NULL!\n", fd);
		files->fd[fd] = NULL;
	}
#endif
	error = fd;

out:
	write_unlock(&files->file_lock);
	return error;
}

asmlinkage long sys_open(const char * filename, int flags, int mode)
{
	char * tmp;
	int fd, error;

#if BITS_PER_LONG != 32
	flags |= O_LARGEFILE;
#endif
	tmp = getname(filename);
	fd = PTR_ERR(tmp);
	if (!IS_ERR(tmp)) {
		fd = get_unused_fd();
		if (fd >= 0) {
			struct file *f = filp_open(tmp, flags, mode);
			error = PTR_ERR(f);
			if (IS_ERR(f))
				goto out_error;
			fd_install(fd, f);
		}
out:
		putname(tmp);
	}
	return fd;

out_error:
	put_unused_fd(fd);
	fd = error;
	goto out;
}

#ifndef __alpha__

/*
 * For backward compatibility?  Maybe this should be moved
 * into arch/i386 instead?
 */
asmlinkage long sys_creat(const char * pathname, int mode)
{
	return sys_open(pathname, O_CREAT | O_WRONLY | O_TRUNC, mode);
}

#endif

/*
 * "id" is the POSIX thread ID. We use the
 * files pointer for this..
 */
int filp_close(struct file *filp, fl_owner_t id)
{
	int retval;

	if (!file_count(filp)) {
		printk("VFS: Close: file count is 0\n");
		return 0;
	}
	retval = 0;
	if (filp->f_op && filp->f_op->flush) {
		lock_kernel();
		retval = filp->f_op->flush(filp);
		unlock_kernel();
	}
	fcntl_dirnotify(0, filp, 0);
	locks_remove_posix(filp, id);
	fput(filp);
	return retval;
}

/*
 * Careful here! We test whether the file pointer is NULL before
 * releasing the fd. This ensures that one clone task can't release
 * an fd while another clone is opening it.
 */
asmlinkage long sys_close(unsigned int fd)
{
	struct file * filp;
	struct files_struct *files = current->files;

	write_lock(&files->file_lock);
	if (fd >= files->max_fds)
		goto out_unlock;
	filp = files->fd[fd];
	if (!filp)
		goto out_unlock;
	files->fd[fd] = NULL;
	FD_CLR(fd, files->close_on_exec);
	__put_unused_fd(files, fd);
	write_unlock(&files->file_lock);
	return filp_close(filp, files);

out_unlock:
	write_unlock(&files->file_lock);
	return -EBADF;
}

/*
 * This routine simulates a hangup on the tty, to arrange that users
 * are given clean terminals at login time.
 */
asmlinkage long sys_vhangup(void)
{
	if (capable(CAP_SYS_TTY_CONFIG)) {
		tty_vhangup(current->tty);
		return 0;
	}
	return -EPERM;
}