bridge: suppress arp pkts on BR_NEIGH_SUPPRESS ports

This patch avoids flooding and proxies arp packets
for BR_NEIGH_SUPPRESS ports.

Moves existing br_do_proxy_arp to br_do_proxy_suppress_arp
to support both proxy arp and neigh suppress.

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/bridge/br_arp_nd_proxy.c

@@ -14,6 +14,14 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/neighbour.h>
+#include <net/arp.h>
+#include <linux/if_vlan.h>
+#include <linux/inetdevice.h>
+#include <net/addrconf.h>
+
 #include "br_private.h"
 
 void br_recalculate_neigh_suppress_enabled(struct net_bridge *br)
@@ -30,3 +38,183 @@ void br_recalculate_neigh_suppress_enabled(struct net_bridge *br)
 
 	br->neigh_suppress_enabled = neigh_suppress;
 }
+
+#if IS_ENABLED(CONFIG_INET)
+static void br_arp_send(struct net_bridge *br, struct net_bridge_port *p,
+			struct net_device *dev, __be32 dest_ip, __be32 src_ip,
+			const unsigned char *dest_hw,
+			const unsigned char *src_hw,
+			const unsigned char *target_hw,
+			__be16 vlan_proto, u16 vlan_tci)
+{
+	struct net_bridge_vlan_group *vg;
+	struct sk_buff *skb;
+	u16 pvid;
+
+	netdev_dbg(dev, "arp send dev %s dst %pI4 dst_hw %pM src %pI4 src_hw %pM\n",
+		   dev->name, &dest_ip, dest_hw, &src_ip, src_hw);
+
+	if (!vlan_tci) {
+		arp_send(ARPOP_REPLY, ETH_P_ARP, dest_ip, dev, src_ip,
+			 dest_hw, src_hw, target_hw);
+		return;
+	}
+
+	skb = arp_create(ARPOP_REPLY, ETH_P_ARP, dest_ip, dev, src_ip,
+			 dest_hw, src_hw, target_hw);
+	if (!skb)
+		return;
+
+	if (p)
+		vg = nbp_vlan_group_rcu(p);
+	else
+		vg = br_vlan_group_rcu(br);
+	pvid = br_get_pvid(vg);
+	if (pvid == (vlan_tci & VLAN_VID_MASK))
+		vlan_tci = 0;
+
+	if (vlan_tci)
+		__vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci);
+
+	if (p) {
+		arp_xmit(skb);
+	} else {
+		skb_reset_mac_header(skb);
+		__skb_pull(skb, skb_network_offset(skb));
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		skb->pkt_type = PACKET_HOST;
+
+		netif_rx_ni(skb);
+	}
+}
+
+static int br_chk_addr_ip(struct net_device *dev, void *data)
+{
+	__be32 ip = *(__be32 *)data;
+	struct in_device *in_dev;
+	__be32 addr = 0;
+
+	in_dev = __in_dev_get_rcu(dev);
+	if (in_dev)
+		addr = inet_confirm_addr(dev_net(dev), in_dev, 0, ip,
+					 RT_SCOPE_HOST);
+
+	if (addr == ip)
+		return 1;
+
+	return 0;
+}
+
+static bool br_is_local_ip(struct net_device *dev, __be32 ip)
+{
+	if (br_chk_addr_ip(dev, &ip))
+		return true;
+
+	/* check if ip is configured on upper dev */
+	if (netdev_walk_all_upper_dev_rcu(dev, br_chk_addr_ip, &ip))
+		return true;
+
+	return false;
+}
+
+void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br,
+			      u16 vid, struct net_bridge_port *p)
+{
+	struct net_device *dev = br->dev;
+	struct net_device *vlandev = dev;
+	struct neighbour *n;
+	struct arphdr *parp;
+	u8 *arpptr, *sha;
+	__be32 sip, tip;
+
+	BR_INPUT_SKB_CB(skb)->proxyarp_replied = false;
+
+	if ((dev->flags & IFF_NOARP) ||
+	    !pskb_may_pull(skb, arp_hdr_len(dev)))
+		return;
+
+	parp = arp_hdr(skb);
+
+	if (parp->ar_pro != htons(ETH_P_IP) ||
+	    parp->ar_hln != dev->addr_len ||
+	    parp->ar_pln != 4)
+		return;
+
+	arpptr = (u8 *)parp + sizeof(struct arphdr);
+	sha = arpptr;
+	arpptr += dev->addr_len;	/* sha */
+	memcpy(&sip, arpptr, sizeof(sip));
+	arpptr += sizeof(sip);
+	arpptr += dev->addr_len;	/* tha */
+	memcpy(&tip, arpptr, sizeof(tip));
+
+	if (ipv4_is_loopback(tip) ||
+	    ipv4_is_multicast(tip))
+		return;
+
+	if (br->neigh_suppress_enabled) {
+		if (p && (p->flags & BR_NEIGH_SUPPRESS))
+			return;
+		if (ipv4_is_zeronet(sip) || sip == tip) {
+			/* prevent flooding to neigh suppress ports */
+			BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+			return;
+		}
+	}
+
+	if (parp->ar_op != htons(ARPOP_REQUEST))
+		return;
+
+	if (vid != 0) {
+		vlandev = __vlan_find_dev_deep_rcu(br->dev, skb->vlan_proto,
+						   vid);
+		if (!vlandev)
+			return;
+	}
+
+	if (br->neigh_suppress_enabled && br_is_local_ip(vlandev, tip)) {
+		/* its our local ip, so don't proxy reply
+		 * and don't forward to neigh suppress ports
+		 */
+		BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+		return;
+	}
+
+	n = neigh_lookup(&arp_tbl, &tip, vlandev);
+	if (n) {
+		struct net_bridge_fdb_entry *f;
+
+		if (!(n->nud_state & NUD_VALID)) {
+			neigh_release(n);
+			return;
+		}
+
+		f = br_fdb_find_rcu(br, n->ha, vid);
+		if (f) {
+			bool replied = false;
+
+			if ((p && (p->flags & BR_PROXYARP)) ||
+			    (f->dst && (f->dst->flags & (BR_PROXYARP_WIFI |
+							 BR_NEIGH_SUPPRESS)))) {
+				if (!vid)
+					br_arp_send(br, p, skb->dev, sip, tip,
+						    sha, n->ha, sha, 0, 0);
+				else
+					br_arp_send(br, p, skb->dev, sip, tip,
+						    sha, n->ha, sha,
+						    skb->vlan_proto,
+						    skb_vlan_tag_get(skb));
+				replied = true;
+			}
+
+			/* If we have replied or as long as we know the
+			 * mac, indicate to arp replied
+			 */
+			if (replied || br->neigh_suppress_enabled)
+				BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+		}
+
+		neigh_release(n);
+	}
+}
+#endif

net/bridge/br_device.c

@@ -39,6 +39,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats);
 	const struct nf_br_ops *nf_ops;
 	const unsigned char *dest;
+	struct ethhdr *eth;
 	u16 vid = 0;
 
 	rcu_read_lock();
@@ -57,11 +58,19 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 	BR_INPUT_SKB_CB(skb)->brdev = dev;
 
 	skb_reset_mac_header(skb);
+	eth = eth_hdr(skb);
 	skb_pull(skb, ETH_HLEN);
 
 	if (!br_allowed_ingress(br, br_vlan_group_rcu(br), skb, &vid))
 		goto out;
 
+	if (IS_ENABLED(CONFIG_INET) &&
+	    (eth->h_proto == htons(ETH_P_ARP) ||
+	     eth->h_proto == htons(ETH_P_RARP)) &&
+	    br->neigh_suppress_enabled) {
+		br_do_proxy_suppress_arp(skb, br, vid, NULL);
+	}
+
 	dest = eth_hdr(skb)->h_dest;
 	if (is_broadcast_ether_addr(dest)) {
 		br_flood(br, skb, BR_PKT_BROADCAST, false, true);

net/bridge/br_input.c

@@ -71,62 +71,6 @@ static int br_pass_frame_up(struct sk_buff *skb)
 		       br_netif_receive_skb);
 }
 
-static void br_do_proxy_arp(struct sk_buff *skb, struct net_bridge *br,
-			    u16 vid, struct net_bridge_port *p)
-{
-	struct net_device *dev = br->dev;
-	struct neighbour *n;
-	struct arphdr *parp;
-	u8 *arpptr, *sha;
-	__be32 sip, tip;
-
-	BR_INPUT_SKB_CB(skb)->proxyarp_replied = false;
-
-	if ((dev->flags & IFF_NOARP) ||
-	    !pskb_may_pull(skb, arp_hdr_len(dev)))
-		return;
-
-	parp = arp_hdr(skb);
-
-	if (parp->ar_pro != htons(ETH_P_IP) ||
-	    parp->ar_op != htons(ARPOP_REQUEST) ||
-	    parp->ar_hln != dev->addr_len ||
-	    parp->ar_pln != 4)
-		return;
-
-	arpptr = (u8 *)parp + sizeof(struct arphdr);
-	sha = arpptr;
-	arpptr += dev->addr_len;	/* sha */
-	memcpy(&sip, arpptr, sizeof(sip));
-	arpptr += sizeof(sip);
-	arpptr += dev->addr_len;	/* tha */
-	memcpy(&tip, arpptr, sizeof(tip));
-
-	if (ipv4_is_loopback(tip) ||
-	    ipv4_is_multicast(tip))
-		return;
-
-	n = neigh_lookup(&arp_tbl, &tip, dev);
-	if (n) {
-		struct net_bridge_fdb_entry *f;
-
-		if (!(n->nud_state & NUD_VALID)) {
-			neigh_release(n);
-			return;
-		}
-
-		f = br_fdb_find_rcu(br, n->ha, vid);
-		if (f && ((p->flags & BR_PROXYARP) ||
-			  (f->dst && (f->dst->flags & BR_PROXYARP_WIFI)))) {
-			arp_send(ARPOP_REPLY, ETH_P_ARP, sip, skb->dev, tip,
-				 sha, n->ha, sha);
-			BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
-		}
-
-		neigh_release(n);
-	}
-}
-
 /* note: already called with rcu_read_lock */
 int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
@@ -171,8 +115,11 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
 
 	BR_INPUT_SKB_CB(skb)->brdev = br->dev;
 
-	if (IS_ENABLED(CONFIG_INET) && skb->protocol == htons(ETH_P_ARP))
-		br_do_proxy_arp(skb, br, vid, p);
+	if (IS_ENABLED(CONFIG_INET) &&
+	    (skb->protocol == htons(ETH_P_ARP) ||
+	     skb->protocol == htons(ETH_P_RARP))) {
+		br_do_proxy_suppress_arp(skb, br, vid, p);
+	}
 
 	switch (pkt_type) {
 	case BR_PKT_MULTICAST:

net/bridge/br_private.h

@@ -1140,5 +1140,8 @@ static inline void br_switchdev_frame_unmark(struct sk_buff *skb)
 }
 #endif /* CONFIG_NET_SWITCHDEV */
 
+/* br_arp_nd_proxy.c */
 void br_recalculate_neigh_suppress_enabled(struct net_bridge *br);
+void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br,
+			      u16 vid, struct net_bridge_port *p);
 #endif