Re: [RFC PATCH net-next 2/5] vxlan: make COLLECT_METADATA mode bridge friendly

On 1/22/17, 3:40 AM, Nikolay Aleksandrov wrote:

On 21/01/17 06:46, Roopa Prabhu wrote:

quoted

From: Roopa Prabhu <redacted>

This patch series makes vxlan COLLECT_METADATA mode bridge
and layer2 network friendly. Vxlan COLLECT_METADATA mode today
solves the per-vni netdev scalability problem in l3 networks.
When vxlan collect metadata device participates in bridging
vlan to vn-segments, It can only get the vlan mapped vni in
the xmit tunnel dst metadata. It will need the vxlan driver to
continue learn, hold forwarding state and remote destination
information similar to how it already does for non COLLECT_METADATA
vxlan netdevices today.

Changes introduced by this patch:
    - allow learning and forwarding database state to vxlan netdev in
      COLLECT_METADATA mode. Current behaviour is not changed
      by default. tunnel info flag IP_TUNNEL_INFO_BRIDGE is used
      to support the new bridge friendly mode.
    - A single fdb table hashed by (mac, vni) to allow fdb entries with
      multiple vnis in the same fdb table
    - rx path already has the vni
    - tx path expects a vni in the packet with dst_metadata
    - prior to this series, fdb remote_dsts carried remote vni and
      the vxlan device carrying the fdb table represented the
      source vni. With the vxlan device now representing multiple vnis,
      this patch adds a src vni attribute to the fdb entry. The remote
      vni already uses NDA_VNI attribute. This patch introduces
      NDA_SRC_VNI netlink attribute to represent the src vni in a multi
      vni fdb table.

Signed-off-by: Roopa Prabhu <redacted>
---

[snip]

quoted

@@ -2173,23 +2221,29 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 	bool did_rsc = false;
 	struct vxlan_rdst *rdst, *fdst = NULL;
 	struct vxlan_fdb *f;
+	__be32 vni = 0;
 
 	info = skb_tunnel_info(skb);
 
 	skb_reset_mac_header(skb);
 
 	if (vxlan->flags & VXLAN_F_COLLECT_METADATA) {
-		if (info && info->mode & IP_TUNNEL_INFO_TX)
-			vxlan_xmit_one(skb, dev, NULL, false);
-		else
-			kfree_skb(skb);
-		return NETDEV_TX_OK;
+		if (info && info->mode & IP_TUNNEL_INFO_BRIDGE &&
+		    info->mode & IP_TUNNEL_INFO_TX) {

nit: parentheses around the IP_TUNNEL_INFO_TX check

quoted

+			vni = tunnel_id_to_key32(info->key.tun_id);
+		} else {
+			if (info && info->mode & IP_TUNNEL_INFO_TX)

nit: parentheses around the IP_TUNNEL_INFO_TX check

ack

quoted

+				vxlan_xmit_one(skb, dev, vni, NULL, false);
+			else
+				kfree_skb(skb);
+			return NETDEV_TX_OK;
+		}
 	}
 
 	if (vxlan->flags & VXLAN_F_PROXY) {
 		eth = eth_hdr(skb);
 		if (ntohs(eth->h_proto) == ETH_P_ARP)
-			return arp_reduce(dev, skb);
+			return arp_reduce(dev, skb, vni);
 #if IS_ENABLED(CONFIG_IPV6)
 		else if (ntohs(eth->h_proto) == ETH_P_IPV6 &&
 			 pskb_may_pull(skb, sizeof(struct ipv6hdr)

@@ -2200,13 +2254,13 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 				msg = (struct nd_msg *)skb_transport_header(skb);
 				if (msg->icmph.icmp6_code == 0 &&
 				    msg->icmph.icmp6_type == NDISC_NEIGHBOUR_SOLICITATION)
-					return neigh_reduce(dev, skb);
+					return neigh_reduce(dev, skb, vni);
 		}
 #endif
 	}
 
 	eth = eth_hdr(skb);
-	f = vxlan_find_mac(vxlan, eth->h_dest);
+	f = vxlan_find_mac(vxlan, eth->h_dest, vni);
 	did_rsc = false;
 
 	if (f && (f->flags & NTF_ROUTER) && (vxlan->flags & VXLAN_F_RSC) &&

@@ -2214,11 +2268,11 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 	     ntohs(eth->h_proto) == ETH_P_IPV6)) {
 		did_rsc = route_shortcircuit(dev, skb);
 		if (did_rsc)
-			f = vxlan_find_mac(vxlan, eth->h_dest);
+			f = vxlan_find_mac(vxlan, eth->h_dest, vni);
 	}
 
 	if (f == NULL) {
-		f = vxlan_find_mac(vxlan, all_zeros_mac);
+		f = vxlan_find_mac(vxlan, all_zeros_mac, vni);
 		if (f == NULL) {
 			if ((vxlan->flags & VXLAN_F_L2MISS) &&
 			    !is_multicast_ether_addr(eth->h_dest))

@@ -2239,11 +2293,11 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 		}
 		skb1 = skb_clone(skb, GFP_ATOMIC);
 		if (skb1)
-			vxlan_xmit_one(skb1, dev, rdst, did_rsc);
+			vxlan_xmit_one(skb1, dev, vni, rdst, did_rsc);
 	}
 
 	if (fdst)
-		vxlan_xmit_one(skb, dev, fdst, did_rsc);
+		vxlan_xmit_one(skb, dev, vni, fdst, did_rsc);
 	else
 		kfree_skb(skb);
 	return NETDEV_TX_OK;

@@ -2307,12 +2361,12 @@ static int vxlan_init(struct net_device *dev)
 	return 0;
 }
 
-static void vxlan_fdb_delete_default(struct vxlan_dev *vxlan)
+static void vxlan_fdb_delete_default(struct vxlan_dev *vxlan, __be32 vni)
 {
 	struct vxlan_fdb *f;
 
 	spin_lock_bh(&vxlan->hash_lock);
-	f = __vxlan_find_mac(vxlan, all_zeros_mac);
+	f = __vxlan_find_mac(vxlan, all_zeros_mac, vni);
 	if (f)
 		vxlan_fdb_destroy(vxlan, f);
 	spin_unlock_bh(&vxlan->hash_lock);

@@ -2322,7 +2376,7 @@ static void vxlan_uninit(struct net_device *dev)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 
-	vxlan_fdb_delete_default(vxlan);
+	vxlan_fdb_delete_default(vxlan, vxlan->cfg.vni);
 
 	free_percpu(dev->tstats);
 }

@@ -2536,6 +2590,8 @@ static void vxlan_setup(struct net_device *dev)
 	dev->vlan_features = dev->features;
 	dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_RXCSUM;
 	dev->hw_features |= NETIF_F_GSO_SOFTWARE;
+	dev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX;
+	dev->features |= dev->hw_features;
 	netif_keep_dst(dev);
 	dev->priv_flags |= IFF_NO_QUEUE;
 

@@ -2921,6 +2977,7 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 				       NLM_F_EXCL|NLM_F_CREATE,
 				       vxlan->cfg.dst_port,
 				       vxlan->default_dst.remote_vni,
+				       vxlan->default_dst.remote_vni,
 				       vxlan->default_dst.remote_ifindex,
 				       NTF_SELF);
 		if (err)

@@ -2929,7 +2986,7 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 
 	err = register_netdevice(dev);
 	if (err) {
-		vxlan_fdb_delete_default(vxlan);
+		vxlan_fdb_delete_default(vxlan, vxlan->cfg.vni);
 		return err;
 	}
 

@@ -3023,19 +3080,19 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev,
 		conf.flags |= VXLAN_F_UDP_ZERO_CSUM_TX;
 
 	if (data[IFLA_VXLAN_UDP_ZERO_CSUM6_TX] &&
-	    nla_get_u8(data[IFLA_VXLAN_UDP_ZERO_CSUM6_TX]))
+	    !nla_get_u8(data[IFLA_VXLAN_UDP_ZERO_CSUM6_TX]))
 		conf.flags |= VXLAN_F_UDP_ZERO_CSUM6_TX;
 
 	if (data[IFLA_VXLAN_UDP_ZERO_CSUM6_RX] &&
-	    nla_get_u8(data[IFLA_VXLAN_UDP_ZERO_CSUM6_RX]))
+	    !nla_get_u8(data[IFLA_VXLAN_UDP_ZERO_CSUM6_RX]))
 		conf.flags |= VXLAN_F_UDP_ZERO_CSUM6_RX;
 
 	if (data[IFLA_VXLAN_REMCSUM_TX] &&
-	    nla_get_u8(data[IFLA_VXLAN_REMCSUM_TX]))
+	    !nla_get_u8(data[IFLA_VXLAN_REMCSUM_TX]))
 		conf.flags |= VXLAN_F_REMCSUM_TX;
 
 	if (data[IFLA_VXLAN_REMCSUM_RX] &&
-	    nla_get_u8(data[IFLA_VXLAN_REMCSUM_RX]))
+	    !nla_get_u8(data[IFLA_VXLAN_REMCSUM_RX]))
 		conf.flags |= VXLAN_F_REMCSUM_RX;

Aren't these going to break user-space ? 

correct... ignore these. Not intentional. these were from an incorrect merge with an earlier changelink patch i had.
Did not realize these had crept it.

thanks.