summaryrefslogtreecommitdiff
path: root/net/bridge/br_forward.c
blob: d7c35f55bd69fb5e7d3add82a4ce7c48c83b8332 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 *	Forwarding decision
 *	Linux ethernet bridge
 *
 *	Authors:
 *	Lennert Buytenhek		<buytenh@gnu.org>
 */

#include <linux/err.h>
#include <linux/slab.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/netpoll.h>
#include <linux/skbuff.h>
#include <linux/if_vlan.h>
#include <linux/netfilter_bridge.h>
#include "br_private.h"

/* Don't forward packets to originating port or forwarding disabled */
static inline int should_deliver(const struct net_bridge_port *p,
				 const struct sk_buff *skb)
{
	struct net_bridge_vlan_group *vg;

	vg = nbp_vlan_group_rcu(p);
	return ((p->flags & BR_HAIRPIN_MODE) || skb->dev != p->dev) &&
		p->state == BR_STATE_FORWARDING && br_allowed_egress(vg, skb) &&
		nbp_switchdev_allowed_egress(p, skb) &&
		!br_skb_isolated(p, skb);
}

int br_dev_queue_push_xmit(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	skb_push(skb, ETH_HLEN);
	if (!is_skb_forwardable(skb->dev, skb))
		goto drop;

	br_drop_fake_rtable(skb);

	if (skb->ip_summed == CHECKSUM_PARTIAL &&
	    eth_type_vlan(skb->protocol)) {
		int depth;

		if (!vlan_get_protocol_and_depth(skb, skb->protocol, &depth))
			goto drop;

		skb_set_network_header(skb, depth);
	}

	br_switchdev_frame_set_offload_fwd_mark(skb);

	dev_queue_xmit(skb);

	return 0;

drop:
	kfree_skb(skb);
	return 0;
}
EXPORT_SYMBOL_GPL(br_dev_queue_push_xmit);

int br_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	skb_clear_tstamp(skb);
	return NF_HOOK(NFPROTO_BRIDGE, NF_BR_POST_ROUTING,
		       net, sk, skb, NULL, skb->dev,
		       br_dev_queue_push_xmit);

}
EXPORT_SYMBOL_GPL(br_forward_finish);

static void __br_forward(const struct net_bridge_port *to,
			 struct sk_buff *skb, bool local_orig)
{
	struct net_bridge_vlan_group *vg;
	struct net_device *indev;
	struct net *net;
	int br_hook;

	/* Mark the skb for forwarding offload early so that br_handle_vlan()
	 * can know whether to pop the VLAN header on egress or keep it.
	 */
	nbp_switchdev_frame_mark_tx_fwd_offload(to, skb);

	vg = nbp_vlan_group_rcu(to);
	skb = br_handle_vlan(to->br, to, vg, skb);
	if (!skb)
		return;

	indev = skb->dev;
	skb->dev = to->dev;
	if (!local_orig) {
		if (skb_warn_if_lro(skb)) {
			kfree_skb(skb);
			return;
		}
		br_hook = NF_BR_FORWARD;
		skb_forward_csum(skb);
		net = dev_net(indev);
	} else {
		if (unlikely(netpoll_tx_running(to->br->dev))) {
			skb_push(skb, ETH_HLEN);
			if (!is_skb_forwardable(skb->dev, skb))
				kfree_skb(skb);
			else
				br_netpoll_send_skb(to, skb);
			return;
		}
		br_hook = NF_BR_LOCAL_OUT;
		net = dev_net(skb->dev);
		indev = NULL;
	}

	NF_HOOK(NFPROTO_BRIDGE, br_hook,
		net, NULL, skb, indev, skb->dev,
		br_forward_finish);
}

static int deliver_clone(const struct net_bridge_port *prev,
			 struct sk_buff *skb, bool local_orig)
{
	struct net_device *dev = BR_INPUT_SKB_CB(skb)->brdev;

	skb = skb_clone(skb, GFP_ATOMIC);
	if (!skb) {
		DEV_STATS_INC(dev, tx_dropped);
		return -ENOMEM;
	}

	__br_forward(prev, skb, local_orig);
	return 0;
}

/**
 * br_forward - forward a packet to a specific port
 * @to: destination port
 * @skb: packet being forwarded
 * @local_rcv: packet will be received locally after forwarding
 * @local_orig: packet is locally originated
 *
 * Should be called with rcu_read_lock.
 */
void br_forward(const struct net_bridge_port *to,
		struct sk_buff *skb, bool local_rcv, bool local_orig)
{
	if (unlikely(!to))
		goto out;

	/* redirect to backup link if the destination port is down */
	if (rcu_access_pointer(to->backup_port) && !netif_carrier_ok(to->dev)) {
		struct net_bridge_port *backup_port;

		backup_port = rcu_dereference(to->backup_port);
		if (unlikely(!backup_port))
			goto out;
		BR_INPUT_SKB_CB(skb)->backup_nhid = READ_ONCE(to->backup_nhid);
		to = backup_port;
	}

	if (should_deliver(to, skb)) {
		if (local_rcv)
			deliver_clone(to, skb, local_orig);
		else
			__br_forward(to, skb, local_orig);
		return;
	}

out:
	if (!local_rcv)
		kfree_skb(skb);
}
EXPORT_SYMBOL_GPL(br_forward);

static struct net_bridge_port *maybe_deliver(
	struct net_bridge_port *prev, struct net_bridge_port *p,
	struct sk_buff *skb, bool local_orig)
{
	u8 igmp_type = br_multicast_igmp_type(skb);
	int err;

	if (!should_deliver(p, skb))
		return prev;

	nbp_switchdev_frame_mark_tx_fwd_to_hwdom(p, skb);

	if (!prev)
		goto out;

	err = deliver_clone(prev, skb, local_orig);
	if (err)
		return ERR_PTR(err);
out:
	br_multicast_count(p->br, p, skb, igmp_type, BR_MCAST_DIR_TX);

	return p;
}

/* called under rcu_read_lock */
void br_flood(struct net_bridge *br, struct sk_buff *skb,
	      enum br_pkt_type pkt_type, bool local_rcv, bool local_orig,
	      u16 vid)
{
	struct net_bridge_port *prev = NULL;
	struct net_bridge_port *p;

	br_tc_skb_miss_set(skb, pkt_type != BR_PKT_BROADCAST);

	list_for_each_entry_rcu(p, &br->port_list, list) {
		/* Do not flood unicast traffic to ports that turn it off, nor
		 * other traffic if flood off, except for traffic we originate
		 */
		switch (pkt_type) {
		case BR_PKT_UNICAST:
			if (!(p->flags & BR_FLOOD))
				continue;
			break;
		case BR_PKT_MULTICAST:
			if (!(p->flags & BR_MCAST_FLOOD) && skb->dev != br->dev)
				continue;
			break;
		case BR_PKT_BROADCAST:
			if (!(p->flags & BR_BCAST_FLOOD) && skb->dev != br->dev)
				continue;
			break;
		}

		/* Do not flood to ports that enable proxy ARP */
		if (p->flags & BR_PROXYARP)
			continue;
		if (BR_INPUT_SKB_CB(skb)->proxyarp_replied &&
		    ((p->flags & BR_PROXYARP_WIFI) ||
		     br_is_neigh_suppress_enabled(p, vid)))
			continue;

		prev = maybe_deliver(prev, p, skb, local_orig);
		if (IS_ERR(prev))
			goto out;
	}

	if (!prev)
		goto out;

	if (local_rcv)
		deliver_clone(prev, skb, local_orig);
	else
		__br_forward(prev, skb, local_orig);
	return;

out:
	if (!local_rcv)
		kfree_skb(skb);
}

#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
static void maybe_deliver_addr(struct net_bridge_port *p, struct sk_buff *skb,
			       const unsigned char *addr, bool local_orig)
{
	struct net_device *dev = BR_INPUT_SKB_CB(skb)->brdev;
	const unsigned char *src = eth_hdr(skb)->h_source;

	if (!should_deliver(p, skb))
		return;

	/* Even with hairpin, no soliloquies - prevent breaking IPv6 DAD */
	if (skb->dev == p->dev && ether_addr_equal(src, addr))
		return;

	skb = pskb_copy(skb, GFP_ATOMIC);
	if (!skb) {
		DEV_STATS_INC(dev, tx_dropped);
		return;
	}

	if (!is_broadcast_ether_addr(addr))
		memcpy(eth_hdr(skb)->h_dest, addr, ETH_ALEN);

	__br_forward(p, skb, local_orig);
}

/* called with rcu_read_lock */
void br_multicast_flood(struct net_bridge_mdb_entry *mdst,
			struct sk_buff *skb,
			struct net_bridge_mcast *brmctx,
			bool local_rcv, bool local_orig)
{
	struct net_bridge_port *prev = NULL;
	struct net_bridge_port_group *p;
	bool allow_mode_include = true;
	struct hlist_node *rp;

	rp = br_multicast_get_first_rport_node(brmctx, skb);

	if (mdst) {
		p = rcu_dereference(mdst->ports);
		if (br_multicast_should_handle_mode(brmctx, mdst->addr.proto) &&
		    br_multicast_is_star_g(&mdst->addr))
			allow_mode_include = false;
	} else {
		p = NULL;
		br_tc_skb_miss_set(skb, true);
	}

	while (p || rp) {
		struct net_bridge_port *port, *lport, *rport;

		lport = p ? p->key.port : NULL;
		rport = br_multicast_rport_from_node_skb(rp, skb);

		if ((unsigned long)lport > (unsigned long)rport) {
			port = lport;

			if (port->flags & BR_MULTICAST_TO_UNICAST) {
				maybe_deliver_addr(lport, skb, p->eth_addr,
						   local_orig);
				goto delivered;
			}
			if ((!allow_mode_include &&
			     p->filter_mode == MCAST_INCLUDE) ||
			    (p->flags & MDB_PG_FLAGS_BLOCKED))
				goto delivered;
		} else {
			port = rport;
		}

		prev = maybe_deliver(prev, port, skb, local_orig);
		if (IS_ERR(prev))
			goto out;
delivered:
		if ((unsigned long)lport >= (unsigned long)port)
			p = rcu_dereference(p->next);
		if ((unsigned long)rport >= (unsigned long)port)
			rp = rcu_dereference(hlist_next_rcu(rp));
	}

	if (!prev)
		goto out;

	if (local_rcv)
		deliver_clone(prev, skb, local_orig);
	else
		__br_forward(prev, skb, local_orig);
	return;

out:
	if (!local_rcv)
		kfree_skb(skb);
}
#endif