netpoll.c

linux 内核源代码

		return;

	skb_reset_network_header(send_skb);
	arp = (struct arphdr *) skb_put(send_skb, size);
	send_skb->dev = skb->dev;
	send_skb->protocol = htons(ETH_P_ARP);

	/* Fill the device header for the ARP frame */
	if (dev_hard_header(send_skb, skb->dev, ptype,
			    sha, np->local_mac,
			    send_skb->len) < 0) {
		kfree_skb(send_skb);
		return;
	}

	/*
	 * Fill out the arp protocol part.
	 *
	 * we only support ethernet device type,
	 * which (according to RFC 1390) should always equal 1 (Ethernet).
	 */

	arp->ar_hrd = htons(np->dev->type);
	arp->ar_pro = htons(ETH_P_IP);
	arp->ar_hln = np->dev->addr_len;
	arp->ar_pln = 4;
	arp->ar_op = htons(type);

	arp_ptr=(unsigned char *)(arp + 1);
	memcpy(arp_ptr, np->dev->dev_addr, np->dev->addr_len);
	arp_ptr += np->dev->addr_len;
	memcpy(arp_ptr, &tip, 4);
	arp_ptr += 4;
	memcpy(arp_ptr, sha, np->dev->addr_len);
	arp_ptr += np->dev->addr_len;
	memcpy(arp_ptr, &sip, 4);

	netpoll_send_skb(np, send_skb);
}

int __netpoll_rx(struct sk_buff *skb)
{
	int proto, len, ulen;
	struct iphdr *iph;
	struct udphdr *uh;
	struct netpoll_info *npi = skb->dev->npinfo;
	struct netpoll *np = npi->rx_np;

	if (!np)
		goto out;
	if (skb->dev->type != ARPHRD_ETHER)
		goto out;

	/* check if netpoll clients need ARP */
	if (skb->protocol == htons(ETH_P_ARP) &&
	    atomic_read(&trapped)) {
		skb_queue_tail(&npi->arp_tx, skb);
		return 1;
	}

	proto = ntohs(eth_hdr(skb)->h_proto);
	if (proto != ETH_P_IP)
		goto out;
	if (skb->pkt_type == PACKET_OTHERHOST)
		goto out;
	if (skb_shared(skb))
		goto out;

	iph = (struct iphdr *)skb->data;
	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
		goto out;
	if (iph->ihl < 5 || iph->version != 4)
		goto out;
	if (!pskb_may_pull(skb, iph->ihl*4))
		goto out;
	if (ip_fast_csum((u8 *)iph, iph->ihl) != 0)
		goto out;

	len = ntohs(iph->tot_len);
	if (skb->len < len || len < iph->ihl*4)
		goto out;

	/*
	 * Our transport medium may have padded the buffer out.
	 * Now We trim to the true length of the frame.
	 */
	if (pskb_trim_rcsum(skb, len))
		goto out;

	if (iph->protocol != IPPROTO_UDP)
		goto out;

	len -= iph->ihl*4;
	uh = (struct udphdr *)(((char *)iph) + iph->ihl*4);
	ulen = ntohs(uh->len);

	if (ulen != len)
		goto out;
	if (checksum_udp(skb, uh, ulen, iph->saddr, iph->daddr))
		goto out;
	if (np->local_ip && np->local_ip != ntohl(iph->daddr))
		goto out;
	if (np->remote_ip && np->remote_ip != ntohl(iph->saddr))
		goto out;
	if (np->local_port && np->local_port != ntohs(uh->dest))
		goto out;

	np->rx_hook(np, ntohs(uh->source),
		    (char *)(uh+1),
		    ulen - sizeof(struct udphdr));

	kfree_skb(skb);
	return 1;

out:
	if (atomic_read(&trapped)) {
		kfree_skb(skb);
		return 1;
	}

	return 0;
}

void netpoll_print_options(struct netpoll *np)
{
	DECLARE_MAC_BUF(mac);
	printk(KERN_INFO "%s: local port %d\n",
			 np->name, np->local_port);
	printk(KERN_INFO "%s: local IP %d.%d.%d.%d\n",
			 np->name, HIPQUAD(np->local_ip));
	printk(KERN_INFO "%s: interface %s\n",
			 np->name, np->dev_name);
	printk(KERN_INFO "%s: remote port %d\n",
			 np->name, np->remote_port);
	printk(KERN_INFO "%s: remote IP %d.%d.%d.%d\n",
			 np->name, HIPQUAD(np->remote_ip));
	printk(KERN_INFO "%s: remote ethernet address %s\n",
	                 np->name, print_mac(mac, np->remote_mac));
}

int netpoll_parse_options(struct netpoll *np, char *opt)
{
	char *cur=opt, *delim;

	if (*cur != '@') {
		if ((delim = strchr(cur, '@')) == NULL)
			goto parse_failed;
		*delim = 0;
		np->local_port = simple_strtol(cur, NULL, 10);
		cur = delim;
	}
	cur++;

	if (*cur != '/') {
		if ((delim = strchr(cur, '/')) == NULL)
			goto parse_failed;
		*delim = 0;
		np->local_ip = ntohl(in_aton(cur));
		cur = delim;
	}
	cur++;

	if (*cur != ',') {
		/* parse out dev name */
		if ((delim = strchr(cur, ',')) == NULL)
			goto parse_failed;
		*delim = 0;
		strlcpy(np->dev_name, cur, sizeof(np->dev_name));
		cur = delim;
	}
	cur++;

	if (*cur != '@') {
		/* dst port */
		if ((delim = strchr(cur, '@')) == NULL)
			goto parse_failed;
		*delim = 0;
		np->remote_port = simple_strtol(cur, NULL, 10);
		cur = delim;
	}
	cur++;

	/* dst ip */
	if ((delim = strchr(cur, '/')) == NULL)
		goto parse_failed;
	*delim = 0;
	np->remote_ip = ntohl(in_aton(cur));
	cur = delim + 1;

	if (*cur != 0) {
		/* MAC address */
		if ((delim = strchr(cur, ':')) == NULL)
			goto parse_failed;
		*delim = 0;
		np->remote_mac[0] = simple_strtol(cur, NULL, 16);
		cur = delim + 1;
		if ((delim = strchr(cur, ':')) == NULL)
			goto parse_failed;
		*delim = 0;
		np->remote_mac[1] = simple_strtol(cur, NULL, 16);
		cur = delim + 1;
		if ((delim = strchr(cur, ':')) == NULL)
			goto parse_failed;
		*delim = 0;
		np->remote_mac[2] = simple_strtol(cur, NULL, 16);
		cur = delim + 1;
		if ((delim = strchr(cur, ':')) == NULL)
			goto parse_failed;
		*delim = 0;
		np->remote_mac[3] = simple_strtol(cur, NULL, 16);
		cur = delim + 1;
		if ((delim = strchr(cur, ':')) == NULL)
			goto parse_failed;
		*delim = 0;
		np->remote_mac[4] = simple_strtol(cur, NULL, 16);
		cur = delim + 1;
		np->remote_mac[5] = simple_strtol(cur, NULL, 16);
	}

	netpoll_print_options(np);

	return 0;

 parse_failed:
	printk(KERN_INFO "%s: couldn't parse config at %s!\n",
	       np->name, cur);
	return -1;
}

int netpoll_setup(struct netpoll *np)
{
	struct net_device *ndev = NULL;
	struct in_device *in_dev;
	struct netpoll_info *npinfo;
	unsigned long flags;
	int err;

	if (np->dev_name)
		ndev = dev_get_by_name(&init_net, np->dev_name);
	if (!ndev) {
		printk(KERN_ERR "%s: %s doesn't exist, aborting.\n",
		       np->name, np->dev_name);
		return -ENODEV;
	}

	np->dev = ndev;
	if (!ndev->npinfo) {
		npinfo = kmalloc(sizeof(*npinfo), GFP_KERNEL);
		if (!npinfo) {
			err = -ENOMEM;
			goto release;
		}

		npinfo->rx_flags = 0;
		npinfo->rx_np = NULL;

		spin_lock_init(&npinfo->rx_lock);
		skb_queue_head_init(&npinfo->arp_tx);
		skb_queue_head_init(&npinfo->txq);
		INIT_DELAYED_WORK(&npinfo->tx_work, queue_process);

		atomic_set(&npinfo->refcnt, 1);
	} else {
		npinfo = ndev->npinfo;
		atomic_inc(&npinfo->refcnt);
	}

	if (!ndev->poll_controller) {
		printk(KERN_ERR "%s: %s doesn't support polling, aborting.\n",
		       np->name, np->dev_name);
		err = -ENOTSUPP;
		goto release;
	}

	if (!netif_running(ndev)) {
		unsigned long atmost, atleast;

		printk(KERN_INFO "%s: device %s not up yet, forcing it\n",
		       np->name, np->dev_name);

		rtnl_lock();
		err = dev_open(ndev);
		rtnl_unlock();

		if (err) {
			printk(KERN_ERR "%s: failed to open %s\n",
			       np->name, ndev->name);
			goto release;
		}

		atleast = jiffies + HZ/10;
		atmost = jiffies + 4*HZ;
		while (!netif_carrier_ok(ndev)) {
			if (time_after(jiffies, atmost)) {
				printk(KERN_NOTICE
				       "%s: timeout waiting for carrier\n",
				       np->name);
				break;
			}
			cond_resched();
		}

		/* If carrier appears to come up instantly, we don't
		 * trust it and pause so that we don't pump all our
		 * queued console messages into the bitbucket.
		 */

		if (time_before(jiffies, atleast)) {
			printk(KERN_NOTICE "%s: carrier detect appears"
			       " untrustworthy, waiting 4 seconds\n",
			       np->name);
			msleep(4000);
		}
	}

	if (is_zero_ether_addr(np->local_mac) && ndev->dev_addr)
		memcpy(np->local_mac, ndev->dev_addr, 6);

	if (!np->local_ip) {
		rcu_read_lock();
		in_dev = __in_dev_get_rcu(ndev);

		if (!in_dev || !in_dev->ifa_list) {
			rcu_read_unlock();
			printk(KERN_ERR "%s: no IP address for %s, aborting\n",
			       np->name, np->dev_name);
			err = -EDESTADDRREQ;
			goto release;
		}

		np->local_ip = ntohl(in_dev->ifa_list->ifa_local);
		rcu_read_unlock();
		printk(KERN_INFO "%s: local IP %d.%d.%d.%d\n",
		       np->name, HIPQUAD(np->local_ip));
	}

	if (np->rx_hook) {
		spin_lock_irqsave(&npinfo->rx_lock, flags);
		npinfo->rx_flags |= NETPOLL_RX_ENABLED;
		npinfo->rx_np = np;
		spin_unlock_irqrestore(&npinfo->rx_lock, flags);
	}

	/* fill up the skb queue */
	refill_skbs();

	/* last thing to do is link it to the net device structure */
	ndev->npinfo = npinfo;

	/* avoid racing with NAPI reading npinfo */
	synchronize_rcu();

	return 0;

 release:
	if (!ndev->npinfo)
		kfree(npinfo);
	np->dev = NULL;
	dev_put(ndev);
	return err;
}

static int __init netpoll_init(void)
{
	skb_queue_head_init(&skb_pool);
	return 0;
}
core_initcall(netpoll_init);

void netpoll_cleanup(struct netpoll *np)
{
	struct netpoll_info *npinfo;
	unsigned long flags;

	if (np->dev) {
		npinfo = np->dev->npinfo;
		if (npinfo) {
			if (npinfo->rx_np == np) {
				spin_lock_irqsave(&npinfo->rx_lock, flags);
				npinfo->rx_np = NULL;
				npinfo->rx_flags &= ~NETPOLL_RX_ENABLED;
				spin_unlock_irqrestore(&npinfo->rx_lock, flags);
			}

			if (atomic_dec_and_test(&npinfo->refcnt)) {
				skb_queue_purge(&npinfo->arp_tx);
				skb_queue_purge(&npinfo->txq);
				cancel_rearming_delayed_work(&npinfo->tx_work);

				/* clean after last, unfinished work */
				if (!skb_queue_empty(&npinfo->txq)) {
					struct sk_buff *skb;
					skb = __skb_dequeue(&npinfo->txq);
					kfree_skb(skb);
				}
				kfree(npinfo);
				np->dev->npinfo = NULL;
			}
		}

		dev_put(np->dev);
	}

	np->dev = NULL;
}

int netpoll_trap(void)
{
	return atomic_read(&trapped);
}

void netpoll_set_trap(int trap)
{
	if (trap)
		atomic_inc(&trapped);
	else
		atomic_dec(&trapped);
}

EXPORT_SYMBOL(netpoll_set_trap);
EXPORT_SYMBOL(netpoll_trap);
EXPORT_SYMBOL(netpoll_print_options);
EXPORT_SYMBOL(netpoll_parse_options);
EXPORT_SYMBOL(netpoll_setup);
EXPORT_SYMBOL(netpoll_cleanup);
EXPORT_SYMBOL(netpoll_send_udp);
EXPORT_SYMBOL(netpoll_poll);