Message-Id: <201403141749.s2EHnvgc030976@lab1.dls>
Date:	Fri, 14 Mar 2014 13:49:57 -0400
From:	David L Stevens <dlstevens@...ibm.com>
To:	David Miller <davem@...emloft.net>,
	Stephen Hemminger <shemminger@...tta.com>
cc:	netdev@...r.kernel.org
Subject: [PATCH VXLAN] fix nonfunctional neigh_reduce


	The VXLAN neigh_reduce() code is completely non-functional since
check-in. Specific errors:

1) The original code drops all packets with a multicast destination address,
	even though neighbor solicitations are sent to the solicited-node
	address, a multicast address. The code after this check was never run.
2) The neighbor table lookup used the IPv6 header destination, which is the
	solicited node address, rather than the target address from the
	neighbor solicitation. So neighbor lookups would always fail if it
	got this far. Also for L3MISSes.
3) The code calls ndisc_send_na(), which does a send on the tunnel device.
	The context for neigh_reduce() is the transmit path, vxlan_xmit(),
	where the host or a bridge-attached neighbor is trying to transmit
	a neighbor solicitation. To respond to it, the tunnel endpoint needs
	to do a *receive* of the appropriate neighbor advertisement. Doing a
	send, would only try to send the advertisement, encapsulated, to the
	remote destinations in the fdb -- hosts that definitely did not do the
	corresponding solicitation.
4) The code uses the tunnel endpoint IPv6 forwarding flag to determine the
	isrouter flag in the advertisement. This has nothing to do with whether
	or not the target is a router, and generally won't be set since the
	tunnel endpoint is bridging, not routing, traffic.

	The patch below creates a proxy neighbor advertisement to respond to
neighbor solicitions as intended, providing proper IPv6 support for neighbor
reduction.

Signed-Off-By: David L Stevens <dlstevens@...ibm.com>

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index eb59b14..b905d57 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1336,14 +1336,109 @@ out:
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
+
+static struct sk_buff *vxlan_na_create(struct sk_buff *request,
+	struct neighbour *n, bool isrouter)
+{
+	struct net_device *dev = request->dev;
+	struct sk_buff *reply = NULL;
+	struct nd_msg *ns, *na;
+	struct ipv6hdr *pip6 = ipv6_hdr(reply);
+	u8 *daddr;
+	int olen = 8; /* opt hdr + ETH_ALEN for target */
+	int i, len;
+
+	if (dev == NULL)
+		return NULL;
+
+	ns = (struct nd_msg *)skb_transport_header(request);
+
+	len = LL_RESERVED_SPACE(dev) + sizeof(struct ipv6hdr) +
+		sizeof(*na) + olen + dev->needed_tailroom;
+	reply = alloc_skb(len, GFP_ATOMIC);
+	if (reply == NULL)
+		goto out;
+
+	reply->protocol = htons(ETH_P_IPV6);
+	reply->dev = dev;
+	skb_reserve(reply, LL_RESERVED_SPACE(request->dev));
+	skb_push(reply, sizeof(struct ethhdr));
+	skb_set_mac_header(reply, 0);
+
+	daddr = eth_hdr(request)->h_source;
+	olen = request->len - skb_transport_offset(request) - sizeof(*ns);
+	for (i = 0; i < olen-1; i += (ns->opt[i+1]<<3)) {
+		if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) {
+			daddr = ns->opt + i + sizeof(struct nd_opt_hdr);
+			break;
+		}
+	}
+
+	/* Ethernet header */
+	memcpy(eth_hdr(reply)->h_dest, daddr, ETH_ALEN);
+	memcpy(eth_hdr(reply)->h_source, n->ha, ETH_ALEN);
+	eth_hdr(reply)->h_proto = htons(ETH_P_IPV6);
+	reply->protocol = htons(ETH_P_IPV6);
+
+	skb_pull(reply, sizeof(struct ethhdr));
+	skb_set_network_header(reply, 0);
+	skb_put(reply, sizeof(struct ipv6hdr));
+
+	/* IPv6 header */
+
+	pip6 = ipv6_hdr(reply);
+	memset(pip6, 0, sizeof(struct ipv6hdr));
+	pip6->version = 6;
+	pip6->priority = ipv6_hdr(request)->priority;
+	pip6->nexthdr = IPPROTO_ICMPV6;
+	pip6->hop_limit = 255;
+	pip6->daddr = ipv6_hdr(request)->saddr;
+	pip6->saddr = *(struct in6_addr *)n->primary_key;
+
+	skb_pull(reply, sizeof(struct ipv6hdr));
+	skb_set_transport_header(reply, 0);
+
+	olen = 8; /* ND_OPT_TARGET_LL_ADDR */
+	na = (struct nd_msg *)skb_put(reply, sizeof(*na) + olen);
+
+	/* Neighbor Advertisement */
+	memset(na, 0, sizeof(*na)+olen);
+	na->icmph.icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT;
+	na->icmph.icmp6_router = isrouter;
+	na->icmph.icmp6_override = 1;
+	na->icmph.icmp6_solicited = 1;
+	na->target = ns->target;
+	memcpy(&na->opt[2], n->ha, ETH_ALEN);
+	na->opt[0] = ND_OPT_TARGET_LL_ADDR;
+	na->opt[1] = 1; /* 8 bytes */
+
+	na->icmph.icmp6_cksum = csum_ipv6_magic(&pip6->saddr,
+		&pip6->daddr, sizeof(*na)+olen, IPPROTO_ICMPV6, 
+		csum_partial(na, sizeof(*na)+olen, 0));
+
+	pip6->payload_len = htons(sizeof(*na)+olen);
+
+	skb_push(reply, sizeof(struct ipv6hdr));
+
+	reply->ip_summed = CHECKSUM_UNNECESSARY;
+
+	return reply;
+out:
+	if (reply)
+		kfree_skb(reply);
+	return 0;
+}
+
 static int neigh_reduce(struct net_device *dev, struct sk_buff *skb)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_fdb *f;
 	struct neighbour *n;
 	union vxlan_addr ipa;
 	const struct ipv6hdr *iphdr;
 	const struct in6_addr *saddr, *daddr;
 	struct nd_msg *msg;
+	struct sk_buff *reply;
 	struct inet6_dev *in6_dev = NULL;
 
 	in6_dev = __in6_dev_get(dev);
@@ -1357,8 +1452,7 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb)
 	saddr = &iphdr->saddr;
 	daddr = &iphdr->daddr;
 
-	if (ipv6_addr_loopback(daddr) ||
-	    ipv6_addr_is_multicast(daddr))
+	if (ipv6_addr_loopback(daddr))
 		goto out;
 
 	msg = (struct nd_msg *)skb_transport_header(skb);
@@ -1366,33 +1460,35 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb)
 	    msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION)
 		goto out;
 
-	n = neigh_lookup(ipv6_stub->nd_tbl, daddr, dev);
+	n = neigh_lookup(ipv6_stub->nd_tbl, &msg->target, dev);
 
-	if (n) {
-		struct vxlan_fdb *f;
-
-		if (!(n->nud_state & NUD_CONNECTED)) {
-			neigh_release(n);
-			goto out;
+	if (!n) {
+		if (vxlan->flags & VXLAN_F_L3MISS) {
+			ipa.sin6.sin6_addr = msg->target;
+			ipa.sa.sa_family = AF_INET6;
+			vxlan_ip_miss(dev, &ipa);
 		}
+		goto out;
+	}
 
-		f = vxlan_find_mac(vxlan, n->ha);
-		if (f && vxlan_addr_any(&(first_remote_rcu(f)->remote_ip))) {
-			/* bridge-local neighbor */
-			neigh_release(n);
-			goto out;
-		}
+	if (!(n->nud_state & NUD_CONNECTED)) {
+		neigh_release(n);
+		goto out;
+	}
 
-		ipv6_stub->ndisc_send_na(dev, n, saddr, &msg->target,
-					 !!in6_dev->cnf.forwarding,
-					 true, false, false);
+	f = vxlan_find_mac(vxlan, n->ha);
+	if (f && vxlan_addr_any(&(first_remote_rcu(f)->remote_ip))) {
+		/* bridge-local neighbor */
 		neigh_release(n);
-	} else if (vxlan->flags & VXLAN_F_L3MISS) {
-		ipa.sin6.sin6_addr = *daddr;
-		ipa.sa.sa_family = AF_INET6;
-		vxlan_ip_miss(dev, &ipa);
+		goto out;
 	}
 
+	reply = vxlan_na_create(skb, n, !!(f ? f->flags & NTF_ROUTER : 0));
+
+	neigh_release(n);
+
+	if (reply && netif_rx_ni(reply) == NET_RX_DROP)
+		dev->stats.rx_dropped++;
 out:
 	consume_skb(skb);
 	return NETDEV_TX_OK;

--
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