聊聊文件系统的原理

// 这里是以 ext4本地文件系统为例
const struct inode_operations ext4_dir_inode_operations = {
	// 文件创建函数
	.create		= ext4_create,
	// 查找函数
	.lookup		= ext4_lookup,
	/****** 省略其他的定义的函数*****/
};

const struct file_operations ext4_file_operations = {
	.llseek		= ext4_llseek,
	// 读函数
	.read_iter	= ext4_file_read_iter,
	// 写函数
	.write_iter	= ext4_file_write_iter,
	.unlocked_ioctl = ext4_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl	= ext4_compat_ioctl,
#endif
	.mmap		= ext4_file_mmap,
	.mmap_supported_flags = MAP_SYNC,
	// open函数对应实际文件系统的函数
	.open		= ext4_file_open,
	.release	= ext4_release_file,
	.fsync		= ext4_sync_file,
	.get_unmapped_area = thp_get_unmapped_area,
	.splice_read	= generic_file_splice_read,
	.splice_write	= iter_file_splice_write,
	.fallocate	= ext4_fallocate,
};

// write函数进入内核态的ksys_write
// fd是已经打开的文件描述符，buf是需要写入的数据，count是写入的长度
ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count)
{
	// f 代表打开的文件和打开文件的flag
	struct fd f = fdget_pos(fd);
	ssize_t ret = -EBADF;
	// 如果打开的文件为空，则退出
	if (f.file) {
		// 获取文件读写的位置
		loff_t pos = file_pos_read(f.file);
		// 进入vfs_write的函数，接着处理文件写操作
		ret = vfs_write(f.file, buf, count, &pos);
		if (ret >= 0)
			file_pos_write(f.file, pos);
		fdput_pos(f);
	}

	return ret;
}

// vfs_write包装了ext4_file_write_iter 函数
ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_t *pos)
{
	ssize_t ret;
	// 判断文件是否写入，如果不能则返回错误码
	if (!(file->f_mode & FMODE_WRITE))
		return -EBADF;
	if (!(file->f_mode & FMODE_CAN_WRITE))
		return -EINVAL;
	if (unlikely(!access_ok(VERIFY_READ, buf, count)))
		return -EFAULT;
	// 检查文件系统可写区域以及锁检查
	ret = rw_verify_area(WRITE, file, pos, count);
	if (!ret) {
		if (count > MAX_RW_COUNT)
			count =  MAX_RW_COUNT;
		
		file_start_write(file);
		// 调用ext4_file_write_iter 开始写数据
		ret = __vfs_write(file, buf, count, pos);
		if (ret > 0) {
			fsnotify_modify(file);
			add_wchar(current, ret);
		}
		inc_syscw(current);
		file_end_write(file);
	}

	return ret;
}

// __vfs_write是包装函数
ssize_t __vfs_write(struct file *file, const char __user *p, size_t count,
		    loff_t *pos)
{
	if (file->f_op->write)
		return file->f_op->write(file, p, count, pos);
	else if (file->f_op->write_iter)
		return new_sync_write(file, p, count, pos);
	else
		return -EINVAL;
}

// 把用户需要写入的数据封装为struct iovec,然后把这个iovec和fd对应的struct file，传递给时间文件系统的函数，进行文件写入。
static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos)
{
	struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = len };
	struct kiocb kiocb;
	struct iov_iter iter;
	ssize_t ret;

	init_sync_kiocb(&kiocb, filp);
	kiocb.ki_pos = *ppos;
	iov_iter_init(&iter, WRITE, &iov, 1, len);

	ret = call_write_iter(filp, &kiocb, &iter);
	BUG_ON(ret == -EIOCBQUEUED);
	if (ret > 0)
		*ppos = kiocb.ki_pos;
	return ret;
}

// call_write_iter是直接调用f_op->write_iter函数，这里对应的是 ext4_file_write_iter，到了这里虚拟文件系统层基本已经结束，进入实际文件系统的调用过程。
static inline ssize_t call_write_iter(struct file *file, struct kiocb *kio,
				      struct iov_iter *iter)
{
	return file->f_op->write_iter(kio, iter);
}