Message-ID: <1433177175-16775-4-git-send-email-rshearma@brocade.com>
Date:	Mon, 1 Jun 2015 17:46:15 +0100
From:	Robert Shearman <rshearma@...cade.com>
To:	<netdev@...r.kernel.org>
CC:	"Eric W. Biederman" <ebiederm@...ssion.com>,
	roopa <roopa@...ulusnetworks.com>, Thomas Graf <tgraf@...g.ch>,
	Robert Shearman <rshearma@...cade.com>
Subject: [RFC net-next 3/3] mpls: new ipmpls device for encapsulating IP packets as mpls

Allow creating an mpls device for the purposes of encapsulating IP
packets with:

  ip link add type ipmpls

This device defines its per-nexthop encapsulation data as a stack of
labels, in the same format as for RTA_NEWST. It uses the encap data
which will have been stored in the IP route to encapsulate the packet
with that stack of labels, with the last label corresponding to a
local label that defines how the packet will be sent out. The device
sends packets over loopback to the local MPLS forwarding logic which
performs all of the work.

Stats are implemented, although any error in the sending via the real
interface will be handled by the main mpls forwarding code and so not
accounted by the interface.

This implementation is based on an alternative earlier implementation
by Eric W. Biederman.

Signed-off-by: Robert Shearman <rshearma@...cade.com>
---
 include/uapi/linux/if_arp.h |   1 +
 net/mpls/Kconfig            |   5 +
 net/mpls/Makefile           |   1 +
 net/mpls/af_mpls.c          |   2 +
 net/mpls/ipmpls.c           | 284 ++++++++++++++++++++++++++++++++++++++++++++
 5 files changed, 293 insertions(+)
 create mode 100644 net/mpls/ipmpls.c

diff --git a/include/uapi/linux/if_arp.h b/include/uapi/linux/if_arp.h
index 4d024d75d64b..17d669fd1781 100644
--- a/include/uapi/linux/if_arp.h
+++ b/include/uapi/linux/if_arp.h
@@ -88,6 +88,7 @@
 #define ARPHRD_IEEE80211_RADIOTAP 803	/* IEEE 802.11 + radiotap header */
 #define ARPHRD_IEEE802154	  804
 #define ARPHRD_IEEE802154_MONITOR 805	/* IEEE 802.15.4 network monitor */
+#define ARPHRD_MPLS	806		/* IP and IPv6 over MPLS tunnels */
 
 #define ARPHRD_PHONET	820		/* PhoNet media type		*/
 #define ARPHRD_PHONET_PIPE 821		/* PhoNet pipe header		*/
diff --git a/net/mpls/Kconfig b/net/mpls/Kconfig
index 17bde799c854..5264da94733a 100644
--- a/net/mpls/Kconfig
+++ b/net/mpls/Kconfig
@@ -27,4 +27,9 @@ config MPLS_ROUTING
 	help
 	 Add support for forwarding of mpls packets.
 
+config MPLS_IPTUNNEL
+	tristate "MPLS: IP over MPLS tunnel support"
+	help
+	 A network device that encapsulates ip packets as mpls
+
 endif # MPLS
diff --git a/net/mpls/Makefile b/net/mpls/Makefile
index 65bbe68c72e6..3a93c14b23c5 100644
--- a/net/mpls/Makefile
+++ b/net/mpls/Makefile
@@ -3,5 +3,6 @@
 #
 obj-$(CONFIG_NET_MPLS_GSO) += mpls_gso.o
 obj-$(CONFIG_MPLS_ROUTING) += mpls_router.o
+obj-$(CONFIG_MPLS_IPTUNNEL) += ipmpls.o
 
 mpls_router-y := af_mpls.o
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 7b3f732269e4..68bdfbdddfaf 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -615,6 +615,7 @@ int nla_put_labels(struct sk_buff *skb, int attrtype,
 
 	return 0;
 }
+EXPORT_SYMBOL(nla_put_labels);
 
 int nla_get_labels(const struct nlattr *nla,
 		   u32 max_labels, u32 *labels, u32 label[])
@@ -660,6 +661,7 @@ int nla_get_labels(const struct nlattr *nla,
 	*labels = nla_labels;
 	return 0;
 }
+EXPORT_SYMBOL(nla_get_labels);
 
 static int rtm_to_route_config(struct sk_buff *skb,  struct nlmsghdr *nlh,
 			       struct mpls_route_config *cfg)
diff --git a/net/mpls/ipmpls.c b/net/mpls/ipmpls.c
new file mode 100644
index 000000000000..cf6894ae0c61
--- /dev/null
+++ b/net/mpls/ipmpls.c
@@ -0,0 +1,284 @@
+#include <linux/types.h>
+#include <linux/netdevice.h>
+#include <linux/if_vlan.h>
+#include <linux/if_arp.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/module.h>
+#include <linux/mpls.h>
+#include "internal.h"
+
+static LIST_HEAD(ipmpls_dev_list);
+
+#define MAX_NEW_LABELS 2
+
+struct ipmpls_dev_priv {
+	struct net_device *out_dev;
+	struct list_head list;
+	struct net_device *dev;
+};
+
+static netdev_tx_t ipmpls_dev_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct ipmpls_dev_priv *priv = netdev_priv(dev);
+	struct net_device *out_dev = priv->out_dev;
+	struct mpls_shim_hdr *hdr;
+	bool bottom_of_stack = true;
+	int len = skb->len;
+	const void *encap;
+	int num_labels;
+	unsigned ttl;
+	const u32 *labels;
+	int ret;
+	int i;
+
+	num_labels = dst_get_encap(skb, &encap) / 4;
+	if (!num_labels)
+		goto drop;
+
+	labels = encap;
+
+	/* Obtain the ttl */
+	if (skb->protocol == htons(ETH_P_IP)) {
+		ttl = ip_hdr(skb)->ttl;
+	} else if (skb->protocol == htons(ETH_P_IPV6)) {
+		ttl = ipv6_hdr(skb)->hop_limit;
+	} else if (skb->protocol == htons(ETH_P_MPLS_UC)) {
+		ttl = mpls_entry_decode(mpls_hdr(skb)).ttl;
+		bottom_of_stack = false;
+	} else {
+		goto drop;
+	}
+
+	/* Now that the encap has been retrieved, there's no longer
+	 * any need to keep the dst around so clear it out.
+	 */
+	skb_dst_drop(skb);
+	skb_orphan(skb);
+
+	skb->inner_protocol = skb->protocol;
+	skb->inner_network_header = skb->network_header;
+
+	skb_push(skb, num_labels * sizeof(*hdr));
+	skb_reset_network_header(skb);
+	hdr = mpls_hdr(skb);
+
+	for (i = num_labels - 1; i >= 0; i--) {
+		hdr[i] = mpls_entry_encode(labels[i], ttl, 0, bottom_of_stack);
+		bottom_of_stack = false;
+	}
+
+	skb->dev = out_dev;
+	skb->protocol = htons(ETH_P_MPLS_UC);
+
+	ret = dev_hard_header(skb, out_dev, ETH_P_MPLS_UC,
+			      out_dev->dev_addr, NULL, len);
+	if (ret >= 0)
+		ret = dev_queue_xmit(skb);
+	if (ret)
+		goto drop;
+
+	dev->stats.tx_packets++;
+	dev->stats.tx_bytes += len;
+
+	return 0;
+
+drop:
+	dev->stats.tx_dropped++;
+	kfree_skb(skb);
+	return NETDEV_TX_OK;
+}
+
+static int ipmpls_dev_init(struct net_device *dev)
+{
+	struct ipmpls_dev_priv *priv = netdev_priv(dev);
+
+	list_add_tail(&priv->list, &ipmpls_dev_list);
+
+	return 0;
+}
+
+static void ipmpls_dev_uninit(struct net_device *dev)
+{
+	struct ipmpls_dev_priv *priv = netdev_priv(dev);
+
+	list_del_init(&priv->list);
+}
+
+static void ipmpls_dev_free(struct net_device *dev)
+{
+	free_netdev(dev);
+}
+
+static const struct net_device_ops ipmpls_netdev_ops = {
+	.ndo_init		= ipmpls_dev_init,
+	.ndo_start_xmit		= ipmpls_dev_xmit,
+	.ndo_uninit		= ipmpls_dev_uninit,
+};
+
+#define IPMPLS_FEATURES (NETIF_F_SG |			\
+			 NETIF_F_FRAGLIST |		\
+			 NETIF_F_HIGHDMA |		\
+			 NETIF_F_VLAN_CHALLENGED)
+
+static void ipmpls_dev_setup(struct net_device *dev)
+{
+	dev->netdev_ops		= &ipmpls_netdev_ops;
+
+	dev->type		= ARPHRD_MPLS;
+	dev->flags		= IFF_NOARP;
+	netif_keep_dst(dev);
+	dev->addr_len		= 0;
+	dev->features		|= NETIF_F_LLTX;
+	dev->features		|= IPMPLS_FEATURES;
+	dev->hw_features	|= IPMPLS_FEATURES;
+	dev->vlan_features	= 0;
+
+	dev->destructor = ipmpls_dev_free;
+}
+
+static int ipmpls_dev_validate(struct nlattr *tb[], struct nlattr *data[])
+{
+	return 0;
+}
+
+static int ipmpls_dev_newlink(struct net *src_net, struct net_device *dev,
+			      struct nlattr *tb[], struct nlattr *data[])
+{
+	struct ipmpls_dev_priv *priv = netdev_priv(dev);
+
+	priv->out_dev = src_net->loopback_dev;
+	priv->dev = dev;
+
+	dev->hard_header_len =
+		priv->out_dev->hard_header_len +
+		sizeof(struct mpls_shim_hdr) * MAX_NEW_LABELS;
+
+	return register_netdevice(dev);
+}
+
+static void ipmpls_dev_dellink(struct net_device *dev, struct list_head *head)
+{
+	unregister_netdevice_queue(dev, head);
+}
+
+static int ipmpls_dev_parse_encap(const struct net_device *dev,
+				  const struct nlattr *nla,
+				  void *encap)
+{
+	u32 labels;
+
+	if (nla_len(nla) / 4 > MAX_NEW_LABELS)
+		return -EINVAL;
+
+	if (encap && nla_get_labels(nla, MAX_NEW_LABELS, &labels, encap))
+		return -EINVAL;
+
+	/* Stored encap size is the same as the rtnl encap len */
+	return nla_len(nla);
+}
+
+static int ipmpls_dev_fill_encap(const struct net_device *dev,
+				 struct sk_buff *skb, int encap_len,
+				 const void *encap)
+{
+	return nla_put_labels(skb, RTA_ENCAP, encap_len / 4, encap);
+}
+
+static int ipmpls_dev_match_encap(const struct net_device *dev,
+				  const struct nlattr *nla, int encap_len,
+				  const void *encap)
+{
+	unsigned nla_labels;
+	struct mpls_shim_hdr *nla_label;
+	const u32 *stored_labels = encap;
+	int i;
+
+	/* Stored encap size is the same as the rtnl encap len */
+	if (nla_len(nla) != encap_len)
+		return 1;
+
+	nla_labels = nla_len(nla) / 4;
+	nla_label = nla_data(nla);
+
+	for (i = 0; i < nla_labels; i++) {
+		struct mpls_entry_decoded dec;
+
+		dec = mpls_entry_decode(nla_label + i);
+
+		if (stored_labels[i] != dec.label)
+			return 1;
+	}
+
+	return 0;
+}
+
+static struct rtnl_link_ops ipmpls_ops = {
+	.kind		= "ipmpls",
+	.priv_size	= sizeof(struct ipmpls_dev_priv),
+	.setup		= ipmpls_dev_setup,
+	.validate	= ipmpls_dev_validate,
+	.newlink	= ipmpls_dev_newlink,
+	.dellink	= ipmpls_dev_dellink,
+	.parse_encap	= ipmpls_dev_parse_encap,
+	.fill_encap	= ipmpls_dev_fill_encap,
+	.match_encap	= ipmpls_dev_match_encap,
+};
+
+static int ipmpls_dev_notify(struct notifier_block *this, unsigned long event,
+			     void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+
+	if (event == NETDEV_UNREGISTER) {
+		struct ipmpls_dev_priv *priv, *priv2;
+		LIST_HEAD(list_kill);
+
+		/* Ignore netns device moves */
+		if (dev->reg_state != NETREG_UNREGISTERING)
+			goto done;
+
+		list_for_each_entry_safe(priv, priv2, &ipmpls_dev_list, list) {
+			if (priv->out_dev != dev)
+				continue;
+
+			ipmpls_dev_dellink(priv->dev, &list_kill);
+		}
+		unregister_netdevice_many(&list_kill);
+	}
+done:
+	return NOTIFY_OK;
+}
+
+static struct notifier_block ipmpls_dev_notifier = {
+	.notifier_call = ipmpls_dev_notify,
+};
+
+static int __init ipmpls_init(void)
+{
+	int err;
+
+	err = register_netdevice_notifier(&ipmpls_dev_notifier);
+	if (err)
+		goto out;
+
+	err = rtnl_link_register(&ipmpls_ops);
+	if (err)
+		goto out_unregister_notifier;
+out:
+	return err;
+out_unregister_notifier:
+	unregister_netdevice_notifier(&ipmpls_dev_notifier);
+	goto out;
+}
+module_init(ipmpls_init);
+
+static void __exit ipmpls_exit(void)
+{
+	rtnl_link_unregister(&ipmpls_ops);
+	unregister_netdevice_notifier(&ipmpls_dev_notifier);
+}
+module_exit(ipmpls_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_RTNL_LINK("ipmpls");
-- 
2.1.4

--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Powered by blists - more mailing lists