summaryrefslogtreecommitdiff
path: root/net/bridge/br_input.c
blob: 222285d9dae29b6e0dfbefb4b287112187f006a4 (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
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 *	Handle incoming frames
 *	Linux ethernet bridge
 *
 *	Authors:
 *	Lennert Buytenhek		<buytenh@gnu.org>
 */

#include <linux/slab.h>
#include <linux/kernel.h>
#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"

static int
br_netif_receive_skb(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	br_drop_fake_rtable(skb);
	return netif_receive_skb(skb);
}

static int br_pass_frame_up(struct sk_buff *skb)
{
	struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev;
	struct net_bridge *br = netdev_priv(brdev);
	struct net_bridge_vlan_group *vg;

	dev_sw_netstats_rx_add(brdev, skb->len);

	vg = br_vlan_group_rcu(br);
	/* Bridge is just like any other port.  Make sure the
	 * packet is allowed except in promisc mode when someone
	 * may be running packet capture.
	 */
	if (!(brdev->flags & IFF_PROMISC) &&
	    !br_allowed_egress(vg, skb)) {
		kfree_skb(skb);
		return NET_RX_DROP;
	}

	indev = skb->dev;
	skb->dev = brdev;
	skb = br_handle_vlan(br, NULL, vg, skb);
	if (!skb)
		return NET_RX_DROP;
	/* update the multicast stats if the packet is IGMP/MLD */
	br_multicast_count(br, NULL, skb, br_multicast_igmp_type(skb),
			   BR_MCAST_DIR_TX);

	return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN,
		       dev_net(indev), NULL, skb, indev, NULL,
		       br_netif_receive_skb);
}

/* note: already called with rcu_read_lock */
int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	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_mdb_entry *mdst;
	bool local_rcv, mcast_hit = false;
	struct net_bridge *br;
	u16 vid = 0;
	u8 state;

	if (!p || p->state == BR_STATE_DISABLED)
		goto drop;

	state = p->state;
	if (!br_allowed_ingress(p->br, nbp_vlan_group_rcu(p), skb, &vid,
				&state))
		goto out;

	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, 0);

	local_rcv = !!(br->dev->flags & IFF_PROMISC);
	if (is_multicast_ether_addr(eth_hdr(skb)->h_dest)) {
		/* by definition the broadcast is also a multicast address */
		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))
				goto drop;
		}
	}

	if (state == BR_STATE_LEARNING)
		goto drop;

	BR_INPUT_SKB_CB(skb)->brdev = br->dev;
	BR_INPUT_SKB_CB(skb)->src_port_isolated = !!(p->flags & BR_ISOLATED);

	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);
	} else if (IS_ENABLED(CONFIG_IPV6) &&
		   skb->protocol == htons(ETH_P_IPV6) &&
		   br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED) &&
		   pskb_may_pull(skb, sizeof(struct ipv6hdr) +
				 sizeof(struct nd_msg)) &&
		   ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) {
			struct nd_msg *msg, _msg;

			msg = br_is_nd_neigh_msg(skb, &_msg);
			if (msg)
				br_do_suppress_nd(skb, br, vid, p, msg);
	}

	switch (pkt_type) {
	case BR_PKT_MULTICAST:
		mdst = br_mdb_get(br, skb, vid);
		if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) &&
		    br_multicast_querier_exists(br, eth_hdr(skb), mdst)) {
			if ((mdst && mdst->host_joined) ||
			    br_multicast_is_router(br)) {
				local_rcv = true;
				br->dev->stats.multicast++;
			}
			mcast_hit = true;
		} else {
			local_rcv = true;
			br->dev->stats.multicast++;
		}
		break;
	case BR_PKT_UNICAST:
		dst = br_fdb_find_rcu(br, eth_hdr(skb)->h_dest, vid);
	default:
		break;
	}

	if (dst) {
		unsigned long now = jiffies;

		if (test_bit(BR_FDB_LOCAL, &dst->flags))
			return br_pass_frame_up(skb);

		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);
		else
			br_multicast_flood(mdst, skb, local_rcv, false);
	}

	if (local_rcv)
		return br_pass_frame_up(skb);

out:
	return 0;
drop:
	kfree_skb(skb);
	goto out;
}
EXPORT_SYMBOL_GPL(br_handle_frame_finish);

static void __br_handle_local_finish(struct sk_buff *skb)
{
	struct net_bridge_port *p = br_port_get_rcu(skb->dev);
	u16 vid = 0;

	/* 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, 0);
}

/* note: already called with rcu_read_lock */
static int br_handle_local_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	__br_handle_local_finish(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;
}

/*
 * Return NULL if skb is handled
 * note: already called with rcu_read_lock
 */
static rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
{
	struct net_bridge_port *p;
	struct sk_buff *skb = *pskb;
	const unsigned char *dest = eth_hdr(skb)->h_dest;

	if (unlikely(skb->pkt_type == PACKET_LOOPBACK))
		return RX_HANDLER_PASS;

	if (!is_valid_ether_addr(eth_hdr(skb)->h_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));

	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 (unlikely(is_link_local_ether_addr(dest))) {
		u16 fwd_mask = p->br->group_fwd_mask_required;

		/*
		 * See IEEE 802.1D Table 7-10 Reserved addresses
		 *
		 * Assignment		 		Value
		 * Bridge Group Address		01-80-C2-00-00-00
		 * (MAC Control) 802.3		01-80-C2-00-00-01
		 * (Link Aggregation) 802.3	01-80-C2-00-00-02
		 * 802.1X PAE address		01-80-C2-00-00-03
		 *
		 * 802.1AB LLDP 		01-80-C2-00-00-0E
		 *
		 * Others reserved for future standardization
		 */
		fwd_mask |= p->group_fwd_mask;
		switch (dest[5]) {
		case 0x00:	/* Bridge Group Address */
			/* If STP is turned off,
			   then must forward to keep loop detection */
			if (p->br->stp_enabled == BR_NO_STP ||
			    fwd_mask & (1u << dest[5]))
				goto forward;
			*pskb = skb;
			__br_handle_local_finish(skb);
			return RX_HANDLER_PASS;

		case 0x01:	/* IEEE MAC (Pause) */
			goto drop;

		case 0x0E:	/* 802.1AB LLDP */
			fwd_mask |= p->br->group_fwd_mask;
			if (fwd_mask & (1u << dest[5]))
				goto forward;
			*pskb = skb;
			__br_handle_local_finish(skb);
			return RX_HANDLER_PASS;

		default:
			/* Allow selective forwarding for most other protocols */
			fwd_mask |= p->br->group_fwd_mask;
			if (fwd_mask & (1u << dest[5]))
				goto forward;
		}

		/* 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:
	switch (p->state) {
	case BR_STATE_FORWARDING:
	case BR_STATE_LEARNING:
		if (ether_addr_equal(p->br->dev->dev_addr, dest))
			skb->pkt_type = PACKET_HOST;

		return nf_hook_bridge_pre(skb, pskb);
	default:
drop:
		kfree_skb(skb);
	}
	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;
		}
}