1 files changed, 241 insertions, 70 deletions

diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 5ea7e56119c1..777fa869c1a1 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *	Handle incoming frames
  *	Linux ethernet bridge
  *
  *	Authors:
  *	Lennert Buytenhek		<buytenh@gnu.org>
- *
- *	This program is free software; you can redistribute it and/or
- *	modify it under the terms of the GNU General Public License
- *	as published by the Free Software Foundation; either version
- *	2 of the License, or (at your option) any later version.
  */
 
 #include <linux/slab.h>
@@ -16,17 +12,17 @@
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/netfilter_bridge.h>
+#ifdef CONFIG_NETFILTER_FAMILY_BRIDGE
+#include <net/netfilter/nf_queue.h>
+#endif
 #include <linux/neighbour.h>
 #include <net/arp.h>
+#include <net/dsa.h>
 #include <linux/export.h>
 #include <linux/rculist.h>
 #include "br_private.h"
 #include "br_private_tunnel.h"
 
-/* Hook for brouter */
-br_should_route_hook_t __rcu *br_should_route_hook __read_mostly;
-EXPORT_SYMBOL(br_should_route_hook);
-
 static int
 br_netif_receive_skb(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
@@ -34,21 +30,24 @@ br_netif_receive_skb(struct net *net, struct sock *sk, struct sk_buff *skb)
 	return netif_receive_skb(skb);
 }
 
-static int br_pass_frame_up(struct sk_buff *skb)
+static int br_pass_frame_up(struct sk_buff *skb, bool promisc)
 {
 	struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev;
 	struct net_bridge *br = netdev_priv(brdev);
 	struct net_bridge_vlan_group *vg;
-	struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats);
 
-	u64_stats_update_begin(&brstats->syncp);
-	brstats->rx_packets++;
-	brstats->rx_bytes += skb->len;
-	u64_stats_update_end(&brstats->syncp);
+	dev_sw_netstats_rx_add(brdev, skb->len);
 
 	vg = br_vlan_group_rcu(br);
+
+	/* Reset the offload_fwd_mark because there could be a stacked
+	 * bridge above, and it should not think this bridge it doing
+	 * that bridge's work forwarding out its ports.
+	 */
+	br_switchdev_frame_unmark(skb);
+
 	/* Bridge is just like any other port.  Make sure the
-	 * packet is allowed except in promisc modue when someone
+	 * packet is allowed except in promisc mode when someone
 	 * may be running packet capture.
 	 */
 	if (!(brdev->flags & IFF_PROMISC) &&
@@ -66,6 +65,8 @@ static int br_pass_frame_up(struct sk_buff *skb)
 	br_multicast_count(br, NULL, skb, br_multicast_igmp_type(skb),
 			   BR_MCAST_DIR_TX);
 
+	BR_INPUT_SKB_CB(skb)->promisc = promisc;
+
 	return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN,
 		       dev_net(indev), NULL, skb, indev, NULL,
 		       br_netif_receive_skb);
@@ -74,44 +75,93 @@ static int br_pass_frame_up(struct sk_buff *skb)
 /* note: already called with rcu_read_lock */
 int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
+	enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED;
 	struct net_bridge_port *p = br_port_get_rcu(skb->dev);
 	enum br_pkt_type pkt_type = BR_PKT_UNICAST;
 	struct net_bridge_fdb_entry *dst = NULL;
+	struct net_bridge_mcast_port *pmctx;
 	struct net_bridge_mdb_entry *mdst;
 	bool local_rcv, mcast_hit = false;
-	const unsigned char *dest;
+	struct net_bridge_mcast *brmctx;
+	struct net_bridge_vlan *vlan;
 	struct net_bridge *br;
+	bool promisc;
 	u16 vid = 0;
+	u8 state;
 
-	if (!p || p->state == BR_STATE_DISABLED)
+	if (!p)
 		goto drop;
 
-	if (!br_allowed_ingress(p->br, nbp_vlan_group_rcu(p), skb, &vid))
+	br = p->br;
+
+	if (br_mst_is_enabled(p)) {
+		state = BR_STATE_FORWARDING;
+	} else {
+		if (p->state == BR_STATE_DISABLED) {
+			reason = SKB_DROP_REASON_BRIDGE_INGRESS_STP_STATE;
+			goto drop;
+		}
+
+		state = p->state;
+	}
+
+	brmctx = &p->br->multicast_ctx;
+	pmctx = &p->multicast_ctx;
+	if (!br_allowed_ingress(p->br, nbp_vlan_group_rcu(p), skb, &vid,
+				&state, &vlan))
 		goto out;
 
+	if (p->flags & BR_PORT_LOCKED) {
+		struct net_bridge_fdb_entry *fdb_src =
+			br_fdb_find_rcu(br, eth_hdr(skb)->h_source, vid);
+
+		if (!fdb_src) {
+			/* FDB miss. Create locked FDB entry if MAB is enabled
+			 * and drop the packet.
+			 */
+			if (p->flags & BR_PORT_MAB)
+				br_fdb_update(br, p, eth_hdr(skb)->h_source,
+					      vid, BIT(BR_FDB_LOCKED));
+			goto drop;
+		} else if (READ_ONCE(fdb_src->dst) != p ||
+			   test_bit(BR_FDB_LOCAL, &fdb_src->flags)) {
+			/* FDB mismatch. Drop the packet without roaming. */
+			goto drop;
+		} else if (test_bit(BR_FDB_LOCKED, &fdb_src->flags)) {
+			/* FDB match, but entry is locked. Refresh it and drop
+			 * the packet.
+			 */
+			br_fdb_update(br, p, eth_hdr(skb)->h_source, vid,
+				      BIT(BR_FDB_LOCKED));
+			goto drop;
+		}
+	}
+
 	nbp_switchdev_frame_mark(p, skb);
 
 	/* insert into forwarding database after filtering to avoid spoofing */
-	br = p->br;
 	if (p->flags & BR_LEARNING)
-		br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, false);
+		br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, 0);
+
+	promisc = !!(br->dev->flags & IFF_PROMISC);
+	local_rcv = promisc;
 
-	local_rcv = !!(br->dev->flags & IFF_PROMISC);
-	dest = eth_hdr(skb)->h_dest;
-	if (is_multicast_ether_addr(dest)) {
+	if (is_multicast_ether_addr(eth_hdr(skb)->h_dest)) {
 		/* by definition the broadcast is also a multicast address */
-		if (is_broadcast_ether_addr(dest)) {
+		if (is_broadcast_ether_addr(eth_hdr(skb)->h_dest)) {
 			pkt_type = BR_PKT_BROADCAST;
 			local_rcv = true;
 		} else {
 			pkt_type = BR_PKT_MULTICAST;
-			if (br_multicast_rcv(br, p, skb, vid))
+			if (br_multicast_rcv(&brmctx, &pmctx, vlan, skb, vid))
 				goto drop;
 		}
 	}
 
-	if (p->state == BR_STATE_LEARNING)
+	if (state == BR_STATE_LEARNING) {
+		reason = SKB_DROP_REASON_BRIDGE_INGRESS_STP_STATE;
 		goto drop;
+	}
 
 	BR_INPUT_SKB_CB(skb)->brdev = br->dev;
 	BR_INPUT_SKB_CB(skb)->src_port_isolated = !!(p->flags & BR_ISOLATED);
@@ -135,22 +185,32 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
 
 	switch (pkt_type) {
 	case BR_PKT_MULTICAST:
-		mdst = br_mdb_get(br, skb, vid);
+		mdst = br_mdb_entry_skb_get(brmctx, skb, vid);
 		if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) &&
-		    br_multicast_querier_exists(br, eth_hdr(skb))) {
+		    br_multicast_querier_exists(brmctx, eth_hdr(skb), mdst)) {
 			if ((mdst && mdst->host_joined) ||
-			    br_multicast_is_router(br)) {
+			    br_multicast_is_router(brmctx, skb) ||
+			    br->dev->flags & IFF_ALLMULTI) {
 				local_rcv = true;
-				br->dev->stats.multicast++;
+				DEV_STATS_INC(br->dev, multicast);
 			}
 			mcast_hit = true;
 		} else {
 			local_rcv = true;
-			br->dev->stats.multicast++;
+			DEV_STATS_INC(br->dev, multicast);
 		}
 		break;
 	case BR_PKT_UNICAST:
-		dst = br_fdb_find_rcu(br, dest, vid);
+		dst = br_fdb_find_rcu(br, eth_hdr(skb)->h_dest, vid);
+		if (unlikely(!dst && vid &&
+			     br_opt_get(br, BROPT_FDB_LOCAL_VLAN_0))) {
+			dst = br_fdb_find_rcu(br, eth_hdr(skb)->h_dest, 0);
+			if (dst &&
+			    (!test_bit(BR_FDB_LOCAL, &dst->flags) ||
+			     test_bit(BR_FDB_ADDED_BY_USER, &dst->flags)))
+				dst = NULL;
+		}
+		break;
 	default:
 		break;
 	}
@@ -158,26 +218,26 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
 	if (dst) {
 		unsigned long now = jiffies;
 
-		if (dst->is_local)
-			return br_pass_frame_up(skb);
+		if (test_bit(BR_FDB_LOCAL, &dst->flags))
+			return br_pass_frame_up(skb, false);
 
 		if (now != dst->used)
 			dst->used = now;
 		br_forward(dst->dst, skb, local_rcv, false);
 	} else {
 		if (!mcast_hit)
-			br_flood(br, skb, pkt_type, local_rcv, false);
+			br_flood(br, skb, pkt_type, local_rcv, false, vid);
 		else
-			br_multicast_flood(mdst, skb, local_rcv, false);
+			br_multicast_flood(mdst, skb, brmctx, local_rcv, false);
 	}
 
 	if (local_rcv)
-		return br_pass_frame_up(skb);
+		return br_pass_frame_up(skb, promisc);
 
 out:
 	return 0;
 drop:
-	kfree_skb(skb);
+	kfree_skb_reason(skb, reason);
 	goto out;
 }
 EXPORT_SYMBOL_GPL(br_handle_frame_finish);
@@ -189,20 +249,86 @@ static void __br_handle_local_finish(struct sk_buff *skb)
 
 	/* check if vlan is allowed, to avoid spoofing */
 	if ((p->flags & BR_LEARNING) &&
+	    nbp_state_should_learn(p) &&
 	    !br_opt_get(p->br, BROPT_NO_LL_LEARN) &&
 	    br_should_learn(p, skb, &vid))
-		br_fdb_update(p->br, p, eth_hdr(skb)->h_source, vid, false);
+		br_fdb_update(p->br, p, eth_hdr(skb)->h_source, vid, 0);
 }
 
 /* note: already called with rcu_read_lock */
 static int br_handle_local_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
-	struct net_bridge_port *p = br_port_get_rcu(skb->dev);
-
 	__br_handle_local_finish(skb);
 
-	BR_INPUT_SKB_CB(skb)->brdev = p->br->dev;
-	br_pass_frame_up(skb);
+	/* return 1 to signal the okfn() was called so it's ok to use the skb */
+	return 1;
+}
+
+static int nf_hook_bridge_pre(struct sk_buff *skb, struct sk_buff **pskb)
+{
+#ifdef CONFIG_NETFILTER_FAMILY_BRIDGE
+	struct nf_hook_entries *e = NULL;
+	struct nf_hook_state state;
+	unsigned int verdict, i;
+	struct net *net;
+	int ret;
+
+	net = dev_net(skb->dev);
+#ifdef HAVE_JUMP_LABEL
+	if (!static_key_false(&nf_hooks_needed[NFPROTO_BRIDGE][NF_BR_PRE_ROUTING]))
+		goto frame_finish;
+#endif
+
+	e = rcu_dereference(net->nf.hooks_bridge[NF_BR_PRE_ROUTING]);
+	if (!e)
+		goto frame_finish;
+
+	nf_hook_state_init(&state, NF_BR_PRE_ROUTING,
+			   NFPROTO_BRIDGE, skb->dev, NULL, NULL,
+			   net, br_handle_frame_finish);
+
+	for (i = 0; i < e->num_hook_entries; i++) {
+		verdict = nf_hook_entry_hookfn(&e->hooks[i], skb, &state);
+		switch (verdict & NF_VERDICT_MASK) {
+		case NF_ACCEPT:
+			if (BR_INPUT_SKB_CB(skb)->br_netfilter_broute) {
+				*pskb = skb;
+				return RX_HANDLER_PASS;
+			}
+			break;
+		case NF_DROP:
+			kfree_skb(skb);
+			return RX_HANDLER_CONSUMED;
+		case NF_QUEUE:
+			ret = nf_queue(skb, &state, i, verdict);
+			if (ret == 1)
+				continue;
+			return RX_HANDLER_CONSUMED;
+		default: /* STOLEN */
+			return RX_HANDLER_CONSUMED;
+		}
+	}
+frame_finish:
+	net = dev_net(skb->dev);
+	br_handle_frame_finish(net, NULL, skb);
+#else
+	br_handle_frame_finish(dev_net(skb->dev), NULL, skb);
+#endif
+	return RX_HANDLER_CONSUMED;
+}
+
+/* Return 0 if the frame was not processed otherwise 1
+ * note: already called with rcu_read_lock
+ */
+static int br_process_frame_type(struct net_bridge_port *p,
+				 struct sk_buff *skb)
+{
+	struct br_frame_type *tmp;
+
+	hlist_for_each_entry_rcu(tmp, &p->br->frame_type_list, list)
+		if (unlikely(tmp->type == skb->protocol))
+			return tmp->frame_handler(p, skb);
+
 	return 0;
 }
 
@@ -210,29 +336,31 @@ static int br_handle_local_finish(struct net *net, struct sock *sk, struct sk_bu
  * Return NULL if skb is handled
  * note: already called with rcu_read_lock
  */
-rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
+static rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
 {
+	enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED;
 	struct net_bridge_port *p;
 	struct sk_buff *skb = *pskb;
 	const unsigned char *dest = eth_hdr(skb)->h_dest;
-	br_should_route_hook_t *rhook;
 
 	if (unlikely(skb->pkt_type == PACKET_LOOPBACK))
 		return RX_HANDLER_PASS;
 
-	if (!is_valid_ether_addr(eth_hdr(skb)->h_source))
+	if (!is_valid_ether_addr(eth_hdr(skb)->h_source)) {
+		reason = SKB_DROP_REASON_MAC_INVALID_SOURCE;
 		goto drop;
+	}
 
 	skb = skb_share_check(skb, GFP_ATOMIC);
 	if (!skb)
 		return RX_HANDLER_CONSUMED;
 
+	memset(skb->cb, 0, sizeof(struct br_input_skb_cb));
+	br_tc_skb_miss_set(skb, false);
+
 	p = br_port_get_rcu(skb->dev);
-	if (p->flags & BR_VLAN_TUNNEL) {
-		if (br_handle_ingress_vlan_tunnel(skb, p,
-						  nbp_vlan_group_rcu(p)))
-			goto drop;
-	}
+	if (p->flags & BR_VLAN_TUNNEL)
+		br_handle_ingress_vlan_tunnel(skb, p, nbp_vlan_group_rcu(p));
 
 	if (unlikely(is_link_local_ether_addr(dest))) {
 		u16 fwd_mask = p->br->group_fwd_mask_required;
@@ -263,6 +391,7 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
 			return RX_HANDLER_PASS;
 
 		case 0x01:	/* IEEE MAC (Pause) */
+			reason = SKB_DROP_REASON_MAC_IEEE_MAC_CONTROL;
 			goto drop;
 
 		case 0x0E:	/* 802.1AB LLDP */
@@ -280,35 +409,77 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
 				goto forward;
 		}
 
-		/* Deliver packet to local host only */
-		NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, dev_net(skb->dev),
-			NULL, skb, skb->dev, NULL, br_handle_local_finish);
-		return RX_HANDLER_CONSUMED;
+		BR_INPUT_SKB_CB(skb)->promisc = false;
+
+		/* The else clause should be hit when nf_hook():
+		 *   - returns < 0 (drop/error)
+		 *   - returns = 0 (stolen/nf_queue)
+		 * Thus return 1 from the okfn() to signal the skb is ok to pass
+		 */
+		if (NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN,
+			    dev_net(skb->dev), NULL, skb, skb->dev, NULL,
+			    br_handle_local_finish) == 1) {
+			return RX_HANDLER_PASS;
+		} else {
+			return RX_HANDLER_CONSUMED;
+		}
 	}
 
+	if (unlikely(br_process_frame_type(p, skb)))
+		return RX_HANDLER_PASS;
+
 forward:
+	if (br_mst_is_enabled(p))
+		goto defer_stp_filtering;
+
 	switch (p->state) {
 	case BR_STATE_FORWARDING:
-		rhook = rcu_dereference(br_should_route_hook);
-		if (rhook) {
-			if ((*rhook)(skb)) {
-				*pskb = skb;
-				return RX_HANDLER_PASS;
-			}
-			dest = eth_hdr(skb)->h_dest;
-		}
-		/* fall through */
 	case BR_STATE_LEARNING:
+defer_stp_filtering:
 		if (ether_addr_equal(p->br->dev->dev_addr, dest))
 			skb->pkt_type = PACKET_HOST;
 
-		NF_HOOK(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING,
-			dev_net(skb->dev), NULL, skb, skb->dev, NULL,
-			br_handle_frame_finish);
-		break;
+		return nf_hook_bridge_pre(skb, pskb);
 	default:
+		reason = SKB_DROP_REASON_BRIDGE_INGRESS_STP_STATE;
 drop:
-		kfree_skb(skb);
+		kfree_skb_reason(skb, reason);
 	}
 	return RX_HANDLER_CONSUMED;
 }
+
+/* This function has no purpose other than to appease the br_port_get_rcu/rtnl
+ * helpers which identify bridged ports according to the rx_handler installed
+ * on them (so there _needs_ to be a bridge rx_handler even if we don't need it
+ * to do anything useful). This bridge won't support traffic to/from the stack,
+ * but only hardware bridging. So return RX_HANDLER_PASS so we don't steal
+ * frames from the ETH_P_XDSA packet_type handler.
+ */
+static rx_handler_result_t br_handle_frame_dummy(struct sk_buff **pskb)
+{
+	return RX_HANDLER_PASS;
+}
+
+rx_handler_func_t *br_get_rx_handler(const struct net_device *dev)
+{
+	if (netdev_uses_dsa(dev))
+		return br_handle_frame_dummy;
+
+	return br_handle_frame;
+}
+
+void br_add_frame(struct net_bridge *br, struct br_frame_type *ft)
+{
+	hlist_add_head_rcu(&ft->list, &br->frame_type_list);
+}
+
+void br_del_frame(struct net_bridge *br, struct br_frame_type *ft)
+{
+	struct br_frame_type *tmp;
+
+	hlist_for_each_entry(tmp, &br->frame_type_list, list)
+		if (ft == tmp) {
+			hlist_del_rcu(&ft->list);
+			return;
+		}
+}