Linux|IO|File IO源码剖析

SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags,
		umode_t, mode)
{
	if (force_o_largefile())
		flags |= O_LARGEFILE;
	return do_sys_open(dfd, filename, flags, mode);
}

long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode)
{
	struct open_how how = build_open_how(flags, mode);
	return do_sys_openat2(dfd, filename, &how);
}

static long do_sys_openat2(int dfd, const char __user *filename,
			   struct open_how *how)
{
	struct open_flags op;
	int fd = build_open_flags(how, &op);
	tmp = getname(filename);
	struct file *f = do_filp_open(dfd, tmp, &op);
	putname(tmp);
	return fd;
}

struct file *do_filp_open(int dfd, struct filename *pathname,
		const struct open_flags *op)
{
	struct nameidata nd;
	int flags = op->lookup_flags;
	struct file *filp;
	set_nameidata(&nd, dfd, pathname);
	filp = path_openat(&nd, op, flags | LOOKUP_RCU);
	restore_nameidata();
	return filp;
}

static struct file *path_openat(struct nameidata *nd,
			const struct open_flags *op, unsigned flags)
{
	while (!(error = link_path_walk(s, nd)) &&
		     (s = open_last_lookups(nd, file, op)) != NULL);
	if (!error)
		error = do_open(nd, file, op);
		terminate_walk(nd);
	}
}

static int do_open(struct nameidata *nd,
		   struct file *file, const struct open_flags *op)
{
	error = may_open(&nd->path, acc_mode, open_flag);
	if (!error && !(file->f_mode & FMODE_OPENED))
		error = vfs_open(&nd->path, file);
	if (!error)
		error = ima_file_check(file, op->acc_mode);
	if (!error && do_truncate)
		error = handle_truncate(file);
	if (do_truncate)
		mnt_drop_write(nd->path.mnt);
	return error;
}

int vfs_open(const struct path *path, struct file *file)
{
	file->f_path = *path;
	return do_dentry_open(file, d_backing_inode(path->dentry), NULL);
}

static int do_dentry_open(struct file *f,
			  struct inode *inode,
			  int (*open)(struct inode *, struct file *))
{
	/* normally all 3 are set; ->open() can clear them if needed */
	f->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE;
	if (!open)
		open = f->f_op->open;
	if (open) {
		error = open(inode, f);
		if (error)
			goto cleanup_all;
	}
	f->f_mode |= FMODE_OPENED;
	if ((f->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
		i_readcount_inc(inode);
	if ((f->f_mode & FMODE_READ) &&
	     likely(f->f_op->read || f->f_op->read_iter))
		f->f_mode |= FMODE_CAN_READ;
	if ((f->f_mode & FMODE_WRITE) &&
	     likely(f->f_op->write || f->f_op->write_iter))
		f->f_mode |= FMODE_CAN_WRITE;
}

SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count)
{
	return ksys_read(fd, buf, count);
}

ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count)
{
	struct fd f = fdget_pos(fd);
	ssize_t ret = -EBADF;

	if (f.file) {
		loff_t pos, *ppos = file_ppos(f.file);
		if (ppos) {
			pos = *ppos;
			ppos = &pos;
		}
		ret = vfs_read(f.file, buf, count, ppos);
		if (ret >= 0 && ppos)
			f.file->f_pos = pos;
		fdput_pos(f);
	}
	return ret;
}

ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos)
{
	ssize_t ret;
	if (!(file->f_mode & FMODE_READ))
		return -EBADF;
	if (!(file->f_mode & FMODE_CAN_READ))
		return -EINVAL;
	if (unlikely(!access_ok(buf, count)))
		return -EFAULT;
	ret = rw_verify_area(READ, file, pos, count);
	if (ret)
		return ret;
	if (count > MAX_RW_COUNT)
		count =  MAX_RW_COUNT;
	if (file->f_op->read)
		ret = file->f_op->read(file, buf, count, pos);
	else if (file->f_op->read_iter)
		ret = new_sync_read(file, buf, count, pos);
	else
		ret = -EINVAL;
}

file_start_write(file);
	if (file->f_op->write)
		ret = file->f_op->write(file, buf, count, pos);
	else if (file->f_op->write_iter)
		ret = new_sync_write(file, buf, count, pos);
	else
		ret = -EINVAL;
	if (ret > 0) {
		fsnotify_modify(file);
		add_wchar(current, ret);
	}
	inc_syscw(current);
	file_end_write(file);

/*
 * 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.
 */
SYSCALL_DEFINE1(close, unsigned int, fd)
{
	int retval = __close_fd(current->files, fd);
	/* can't restart close syscall because file table entry was cleared */
	if (unlikely(retval == -ERESTARTSYS ||
		     retval == -ERESTARTNOINTR ||
		     retval == -ERESTARTNOHAND ||
		     retval == -ERESTART_RESTARTBLOCK))
		retval = -EINTR;
	return retval;
}

/*
 * The same warnings as for __alloc_fd()/__fd_install() apply here...
 */
int __close_fd(struct files_struct *files, unsigned fd)
{
	struct file *file;
	struct fdtable *fdt;

	spin_lock(&files->file_lock);
	fdt = files_fdtable(files);
	if (fd >= fdt->max_fds)
		goto out_unlock;
	file = fdt->fd[fd];
	if (!file)
		goto out_unlock;
	rcu_assign_pointer(fdt->fd[fd], NULL);
	__put_unused_fd(files, fd);
	spin_unlock(&files->file_lock);
	return filp_close(file, files);

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

/*
 * "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 = 0;
	if (!file_count(filp)) {
		printk(KERN_ERR "VFS: Close: file count is 0
");
		return 0;
	}
	if (filp->f_op->flush)
		retval = filp->f_op->flush(filp, id);
	if (likely(!(filp->f_mode & FMODE_PATH))) {
		dnotify_flush(filp, id);
		locks_remove_posix(filp, id);
	}
	fput(filp);
	return retval;
}