nbd.c

Linux块设备驱动源码

			}
		}
	}
	return req;
harderror:
	lo->harderror = result;
	return NULL;
}

static void nbd_do_it(struct nbd_device *lo)
{
	struct request *req;

	BUG_ON(lo->magic != LO_MAGIC);

	while ((req = nbd_read_stat(lo)) != NULL)
		nbd_end_request(req);
	return;
}

static void nbd_clear_que(struct nbd_device *lo)
{
	struct request *req;

	BUG_ON(lo->magic != LO_MAGIC);

	do {
		req = NULL;
		spin_lock(&lo->queue_lock);
		if (!list_empty(&lo->queue_head)) {
			req = list_entry(lo->queue_head.next, struct request, queuelist);
			list_del_init(&req->queuelist);
		}
		spin_unlock(&lo->queue_lock);
		if (req) {
			req->errors++;
			nbd_end_request(req);
		}
	} while (req);
}

/*
 * We always wait for result of write, for now. It would be nice to make it optional
 * in future
 * if ((req->cmd == WRITE) && (lo->flags & NBD_WRITE_NOCHK)) 
 *   { printk( "Warning: Ignoring result!\n"); nbd_end_request( req ); }
 */

static void do_nbd_request(request_queue_t * q)
{
	struct request *req;
	
	while ((req = elv_next_request(q)) != NULL) {
		struct nbd_device *lo;

		blkdev_dequeue_request(req);
		dprintk(DBG_BLKDEV, "%s: request %p: dequeued (flags=%lx)\n",
				req->rq_disk->disk_name, req, req->flags);

		if (!(req->flags & REQ_CMD))
			goto error_out;

		lo = req->rq_disk->private_data;

		BUG_ON(lo->magic != LO_MAGIC);

		if (!lo->file) {
			printk(KERN_ERR "%s: Request when not-ready\n",
					lo->disk->disk_name);
			goto error_out;
		}
		nbd_cmd(req) = NBD_CMD_READ;
		if (rq_data_dir(req) == WRITE) {
			nbd_cmd(req) = NBD_CMD_WRITE;
			if (lo->flags & NBD_READ_ONLY) {
				printk(KERN_ERR "%s: Write on read-only\n",
						lo->disk->disk_name);
				goto error_out;
			}
		}

		req->errors = 0;
		spin_unlock_irq(q->queue_lock);

		spin_lock(&lo->queue_lock);

		if (!lo->file) {
			spin_unlock(&lo->queue_lock);
			printk(KERN_ERR "%s: failed between accept and semaphore, file lost\n",
					lo->disk->disk_name);
			req->errors++;
			nbd_end_request(req);
			spin_lock_irq(q->queue_lock);
			continue;
		}

		list_add(&req->queuelist, &lo->queue_head);
		spin_unlock(&lo->queue_lock);

		if (nbd_send_req(lo, req) != 0) {
			printk(KERN_ERR "%s: Request send failed\n",
					lo->disk->disk_name);
			if (nbd_find_request(lo, (char *)&req) != NULL) {
				/* we still own req */
				req->errors++;
				nbd_end_request(req);
			} else /* we're racing with nbd_clear_que */
				printk(KERN_DEBUG "nbd: can't find req\n");
		}

		spin_lock_irq(q->queue_lock);
		continue;

error_out:
		req->errors++;
		spin_unlock(q->queue_lock);
		nbd_end_request(req);
		spin_lock(q->queue_lock);
	}
	return;
}

static int nbd_ioctl(struct inode *inode, struct file *file,
		     unsigned int cmd, unsigned long arg)
{
	struct nbd_device *lo = inode->i_bdev->bd_disk->private_data;
	int error;
	struct request sreq ;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	BUG_ON(lo->magic != LO_MAGIC);

	/* Anyone capable of this syscall can do *real bad* things */
	dprintk(DBG_IOCTL, "%s: nbd_ioctl cmd=%s(0x%x) arg=%lu\n",
			lo->disk->disk_name, ioctl_cmd_to_ascii(cmd), cmd, arg);

	switch (cmd) {
	case NBD_DISCONNECT:
	        printk(KERN_INFO "%s: NBD_DISCONNECT\n", lo->disk->disk_name);
		sreq.flags = REQ_SPECIAL;
		nbd_cmd(&sreq) = NBD_CMD_DISC;
		/*
		 * Set these to sane values in case server implementation
		 * fails to check the request type first and also to keep
		 * debugging output cleaner.
		 */
		sreq.sector = 0;
		sreq.nr_sectors = 0;
                if (!lo->sock)
			return -EINVAL;
                nbd_send_req(lo, &sreq);
                return 0;
 
	case NBD_CLEAR_SOCK:
		error = 0;
		down(&lo->tx_lock);
		lo->sock = NULL;
		up(&lo->tx_lock);
		spin_lock(&lo->queue_lock);
		file = lo->file;
		lo->file = NULL;
		spin_unlock(&lo->queue_lock);
		nbd_clear_que(lo);
		spin_lock(&lo->queue_lock);
		if (!list_empty(&lo->queue_head)) {
			printk(KERN_ERR "nbd: disconnect: some requests are in progress -> please try again.\n");
			error = -EBUSY;
		}
		spin_unlock(&lo->queue_lock);
		if (file)
			fput(file);
		return error;
	case NBD_SET_SOCK:
		if (lo->file)
			return -EBUSY;
		error = -EINVAL;
		file = fget(arg);
		if (file) {
			inode = file->f_dentry->d_inode;
			if (S_ISSOCK(inode->i_mode)) {
				lo->file = file;
				lo->sock = SOCKET_I(inode);
				error = 0;
			} else {
				fput(file);
			}
		}
		return error;
	case NBD_SET_BLKSIZE:
		lo->blksize = arg;
		lo->bytesize &= ~(lo->blksize-1);
		inode->i_bdev->bd_inode->i_size = lo->bytesize;
		set_blocksize(inode->i_bdev, lo->blksize);
		set_capacity(lo->disk, lo->bytesize >> 9);
		return 0;
	case NBD_SET_SIZE:
		lo->bytesize = arg & ~(lo->blksize-1);
		inode->i_bdev->bd_inode->i_size = lo->bytesize;
		set_blocksize(inode->i_bdev, lo->blksize);
		set_capacity(lo->disk, lo->bytesize >> 9);
		return 0;
	case NBD_SET_SIZE_BLOCKS:
		lo->bytesize = ((u64) arg) * lo->blksize;
		inode->i_bdev->bd_inode->i_size = lo->bytesize;
		set_blocksize(inode->i_bdev, lo->blksize);
		set_capacity(lo->disk, lo->bytesize >> 9);
		return 0;
	case NBD_DO_IT:
		if (!lo->file)
			return -EINVAL;
		nbd_do_it(lo);
		/* on return tidy up in case we have a signal */
		/* Forcibly shutdown the socket causing all listeners
		 * to error
		 *
		 * FIXME: This code is duplicated from sys_shutdown, but
		 * there should be a more generic interface rather than
		 * calling socket ops directly here */
		down(&lo->tx_lock);
		if (lo->sock) {
			printk(KERN_WARNING "%s: shutting down socket\n",
				lo->disk->disk_name);
			lo->sock->ops->shutdown(lo->sock,
				SEND_SHUTDOWN|RCV_SHUTDOWN);
			lo->sock = NULL;
		}
		up(&lo->tx_lock);
		spin_lock(&lo->queue_lock);
		file = lo->file;
		lo->file = NULL;
		spin_unlock(&lo->queue_lock);
		nbd_clear_que(lo);
		printk(KERN_WARNING "%s: queue cleared\n", lo->disk->disk_name);
		if (file)
			fput(file);
		return lo->harderror;
	case NBD_CLEAR_QUE:
		down(&lo->tx_lock);
		if (lo->sock) {
			up(&lo->tx_lock);
			return 0; /* probably should be error, but that would
				   * break "nbd-client -d", so just return 0 */
		}
		up(&lo->tx_lock);
		nbd_clear_que(lo);
		return 0;
	case NBD_PRINT_DEBUG:
		printk(KERN_INFO "%s: next = %p, prev = %p, head = %p\n",
			inode->i_bdev->bd_disk->disk_name,
			lo->queue_head.next, lo->queue_head.prev,
			&lo->queue_head);
		return 0;
	}
	return -EINVAL;
}

static struct block_device_operations nbd_fops =
{
	.owner =	THIS_MODULE,
	.ioctl =	nbd_ioctl,
};

/*
 * And here should be modules and kernel interface 
 *  (Just smiley confuses emacs :-)
 */

static int __init nbd_init(void)
{
	int err = -ENOMEM;
	int i;

	if (sizeof(struct nbd_request) != 28) {
		printk(KERN_CRIT "nbd: sizeof nbd_request needs to be 28 in order to work!\n" );
		return -EIO;
	}

	if (nbds_max > MAX_NBD) {
		printk(KERN_CRIT "nbd: cannot allocate more than %u nbds; %u requested.\n", MAX_NBD,
				nbds_max);
		return -EINVAL;
	}

	for (i = 0; i < nbds_max; i++) {
		struct gendisk *disk = alloc_disk(1);
		if (!disk)
			goto out;
		nbd_dev[i].disk = disk;
		/*
		 * The new linux 2.5 block layer implementation requires
		 * every gendisk to have its very own request_queue struct.
		 * These structs are big so we dynamically allocate them.
		 */
		disk->queue = blk_init_queue(do_nbd_request, &nbd_lock);
		if (!disk->queue) {
			put_disk(disk);
			goto out;
		}
	}

	if (register_blkdev(NBD_MAJOR, "nbd")) {
		err = -EIO;
		goto out;
	}

	printk(KERN_INFO "nbd: registered device at major %d\n", NBD_MAJOR);
	dprintk(DBG_INIT, "nbd: debugflags=0x%x\n", debugflags);

	devfs_mk_dir("nbd");
	for (i = 0; i < nbds_max; i++) {
		struct gendisk *disk = nbd_dev[i].disk;
		nbd_dev[i].file = NULL;
		nbd_dev[i].magic = LO_MAGIC;
		nbd_dev[i].flags = 0;
		spin_lock_init(&nbd_dev[i].queue_lock);
		INIT_LIST_HEAD(&nbd_dev[i].queue_head);
		init_MUTEX(&nbd_dev[i].tx_lock);
		nbd_dev[i].blksize = 1024;
		nbd_dev[i].bytesize = 0x7ffffc00ULL << 10; /* 2TB */
		disk->major = NBD_MAJOR;
		disk->first_minor = i;
		disk->fops = &nbd_fops;
		disk->private_data = &nbd_dev[i];
		disk->flags |= GENHD_FL_SUPPRESS_PARTITION_INFO;
		sprintf(disk->disk_name, "nbd%d", i);
		sprintf(disk->devfs_name, "nbd/%d", i);
		set_capacity(disk, 0x7ffffc00ULL << 1); /* 2 TB */
		add_disk(disk);
	}

	return 0;
out:
	while (i--) {
		blk_cleanup_queue(nbd_dev[i].disk->queue);
		put_disk(nbd_dev[i].disk);
	}
	return err;
}

static void __exit nbd_cleanup(void)
{
	int i;
	for (i = 0; i < nbds_max; i++) {
		struct gendisk *disk = nbd_dev[i].disk;
		nbd_dev[i].magic = 0;
		if (disk) {
			del_gendisk(disk);
			blk_cleanup_queue(disk->queue);
			put_disk(disk);
		}
	}
	devfs_remove("nbd");
	unregister_blkdev(NBD_MAJOR, "nbd");
	printk(KERN_INFO "nbd: unregistered device at major %d\n", NBD_MAJOR);
}

module_init(nbd_init);
module_exit(nbd_cleanup);

MODULE_DESCRIPTION("Network Block Device");
MODULE_LICENSE("GPL");

module_param(nbds_max, int, 0444);
MODULE_PARM_DESC(nbds_max, "How many network block devices to initialize.");
#ifndef NDEBUG
module_param(debugflags, int, 0644);
MODULE_PARM_DESC(debugflags, "flags for controlling debug output");
#endif