[deliverable/linux.git] / net / bridge / br_input.c

/*
 *	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>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/netfilter_bridge.h>
#include <linux/neighbour.h>
#include <net/arp.h>
#include <linux/export.h>
#include <linux/rculist.h>
#include "br_private.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_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 pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats);
	struct net_port_vlans *pv;

	u64_stats_update_begin(&brstats->syncp);
	brstats->rx_packets++;
	brstats->rx_bytes += skb->len;
	u64_stats_update_end(&brstats->syncp);

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

	indev = skb->dev;
	skb->dev = brdev;
	skb = br_handle_vlan(br, pv, skb);
	if (!skb)
		return NET_RX_DROP;

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

static void br_do_proxy_arp(struct sk_buff *skb, struct net_bridge *br,
			    u16 vid)
{
	struct net_device *dev = br->dev;
	struct neighbour *n;
	struct arphdr *parp;
	u8 *arpptr, *sha;
	__be32 sip, tip;

	if (dev->flags & IFF_NOARP)
		return;

	if (!pskb_may_pull(skb, arp_hdr_len(dev))) {
		dev->stats.tx_dropped++;
		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_get(br, n->ha, vid);
		if (f)
			arp_send(ARPOP_REPLY, ETH_P_ARP, sip, skb->dev, tip,
				 sha, n->ha, sha);

		neigh_release(n);
	}
}

/* note: already called with rcu_read_lock */
int br_handle_frame_finish(struct sk_buff *skb)
{
	const unsigned char *dest = eth_hdr(skb)->h_dest;
	struct net_bridge_port *p = br_port_get_rcu(skb->dev);
	struct net_bridge *br;
	struct net_bridge_fdb_entry *dst;
	struct net_bridge_mdb_entry *mdst;
	struct sk_buff *skb2;
	bool unicast = true;
	u16 vid = 0;

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

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

	/* 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);

	if (!is_broadcast_ether_addr(dest) && is_multicast_ether_addr(dest) &&
	    br_multicast_rcv(br, p, skb, vid))
		goto drop;

	if (p->state == BR_STATE_LEARNING)
		goto drop;

	BR_INPUT_SKB_CB(skb)->brdev = br->dev;

	/* The packet skb2 goes to the local host (NULL to skip). */
	skb2 = NULL;

	if (br->dev->flags & IFF_PROMISC)
		skb2 = skb;

	dst = NULL;

	if (is_broadcast_ether_addr(dest)) {
		if (p->flags & BR_PROXYARP &&
		    skb->protocol == htons(ETH_P_ARP))
			br_do_proxy_arp(skb, br, vid);

		skb2 = skb;
		unicast = false;
	} else if (is_multicast_ether_addr(dest)) {
		mdst = br_mdb_get(br, skb, vid);
		if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) &&
		    br_multicast_querier_exists(br, eth_hdr(skb))) {
			if ((mdst && mdst->mglist) ||
			    br_multicast_is_router(br))
				skb2 = skb;
			br_multicast_forward(mdst, skb, skb2);
			skb = NULL;
			if (!skb2)
				goto out;
		} else
			skb2 = skb;

		unicast = false;
		br->dev->stats.multicast++;
	} else if ((dst = __br_fdb_get(br, dest, vid)) &&
			dst->is_local) {
		skb2 = skb;
		/* Do not forward the packet since it's local. */
		skb = NULL;
	}

	if (skb) {
		if (dst) {
			dst->used = jiffies;
			br_forward(dst->dst, skb, skb2);
		} else
			br_flood_forward(br, skb, skb2, unicast);
	}

	if (skb2)
		return br_pass_frame_up(skb2);

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

/* note: already called with rcu_read_lock */
static int 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 && br_should_learn(p, skb, &vid))
		br_fdb_update(p->br, p, eth_hdr(skb)->h_source, vid, false);
	return 0;	 /* process further */
}

/*
 * Return NULL if skb is handled
 * note: already called with rcu_read_lock
 */
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;
	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))
		goto drop;

	skb = skb_share_check(skb, GFP_ATOMIC);
	if (!skb)
		return RX_HANDLER_CONSUMED;

	p = br_port_get_rcu(skb->dev);

	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
		 */
		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;
			break;

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

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

		/* Deliver packet to local host only */
		if (NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, skb, skb->dev,
			    NULL, br_handle_local_finish)) {
			return RX_HANDLER_CONSUMED; /* consumed by filter */
		} else {
			*pskb = skb;
			return RX_HANDLER_PASS;	/* continue processing */
		}
	}

forward:
	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:
		if (ether_addr_equal(p->br->dev->dev_addr, dest))
			skb->pkt_type = PACKET_HOST;

		NF_HOOK(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL,
			br_handle_frame_finish);
		break;
	default:
drop:
		kfree_skb(skb);
	}
	return RX_HANDLER_CONSUMED;
}
Commit	Line	Data
1da177e4 LT	1	/*
	2	* Handle incoming frames
	3	* Linux ethernet bridge
	4	*
	5	* Authors:
	6	* Lennert Buytenhek <buytenh@gnu.org>
	7	*
1da177e4 LT	8	* This program is free software; you can redistribute it and/or
	9	* modify it under the terms of the GNU General Public License
	10	* as published by the Free Software Foundation; either version
	11	* 2 of the License, or (at your option) any later version.
	12	*/
	13
5a0e3ad6	14	#include <linux/slab.h>
1da177e4 LT	15	#include <linux/kernel.h>
	16	#include <linux/netdevice.h>
	17	#include <linux/etherdevice.h>
	18	#include <linux/netfilter_bridge.h>
95850116 KP	19	#include <linux/neighbour.h>
95850116 KP	20	#include <net/arp.h>
bc3b2d7f	21	#include <linux/export.h>
a37b85c9	22	#include <linux/rculist.h>
1da177e4 LT	23	#include "br_private.h"
1da177e4 LT	24
a386f990 ED	25	/* Hook for brouter */
	26	br_should_route_hook_t __rcu *br_should_route_hook __read_mostly;
	27	EXPORT_SYMBOL(br_should_route_hook);
	28
68b7c895	29	static int br_pass_frame_up(struct sk_buff *skb)
1da177e4	30	{
68b7c895	31	struct net_device indev, brdev = BR_INPUT_SKB_CB(skb)->brdev;
14bb4789	32	struct net_bridge *br = netdev_priv(brdev);
8f84985f	33	struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats);
fc92f745	34	struct net_port_vlans *pv;
1da177e4	35
406818ff	36	u64_stats_update_begin(&brstats->syncp);
14bb4789	37	brstats->rx_packets++;
14bb4789	38	brstats->rx_bytes += skb->len;
406818ff	39	u64_stats_update_end(&brstats->syncp);
1da177e4	40
85f46c6b VY	41	/* Bridge is just like any other port. Make sure the
	42	* packet is allowed except in promisc modue when someone
	43	* may be running packet capture.
	44	*/
fc92f745	45	pv = br_get_vlan_info(br);
85f46c6b	46	if (!(brdev->flags & IFF_PROMISC) &&
fc92f745	47	!br_allowed_egress(br, pv, skb)) {
85f46c6b VY	48	kfree_skb(skb);
	49	return NET_RX_DROP;
	50	}
	51
1da177e4	52	indev = skb->dev;
a339f1c8	53	skb->dev = brdev;
fc92f745 VY	54	skb = br_handle_vlan(br, pv, skb);
	55	if (!skb)
	56	return NET_RX_DROP;
1da177e4	57
713aefa3	58	return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, skb, indev, NULL,
68b7c895	59	netif_receive_skb);
1da177e4 LT	60	}
1da177e4 LT	61
95850116 KP	62	static void br_do_proxy_arp(struct sk_buff skb, struct net_bridge br,
	63	u16 vid)
	64	{
	65	struct net_device *dev = br->dev;
	66	struct neighbour *n;
	67	struct arphdr *parp;
	68	u8 arpptr, sha;
	69	__be32 sip, tip;
	70
	71	if (dev->flags & IFF_NOARP)
	72	return;
	73
	74	if (!pskb_may_pull(skb, arp_hdr_len(dev))) {
	75	dev->stats.tx_dropped++;
	76	return;
	77	}
	78	parp = arp_hdr(skb);
	79
	80	if (parp->ar_pro != htons(ETH_P_IP) \|\|
	81	parp->ar_op != htons(ARPOP_REQUEST) \|\|
	82	parp->ar_hln != dev->addr_len \|\|
	83	parp->ar_pln != 4)
	84	return;
	85
	86	arpptr = (u8 *)parp + sizeof(struct arphdr);
	87	sha = arpptr;
	88	arpptr += dev->addr_len; /* sha */
	89	memcpy(&sip, arpptr, sizeof(sip));
	90	arpptr += sizeof(sip);
	91	arpptr += dev->addr_len; /* tha */
	92	memcpy(&tip, arpptr, sizeof(tip));
	93
	94	if (ipv4_is_loopback(tip) \|\|
	95	ipv4_is_multicast(tip))
	96	return;
	97
	98	n = neigh_lookup(&arp_tbl, &tip, dev);
	99	if (n) {
	100	struct net_bridge_fdb_entry *f;
	101
	102	if (!(n->nud_state & NUD_VALID)) {
	103	neigh_release(n);
	104	return;
	105	}
	106
	107	f = __br_fdb_get(br, n->ha, vid);
	108	if (f)
	109	arp_send(ARPOP_REPLY, ETH_P_ARP, sip, skb->dev, tip,
	110	sha, n->ha, sha);
	111
	112	neigh_release(n);
	113	}
	114	}
	115
eeaf61d8	116	/* note: already called with rcu_read_lock */
1da177e4 LT	117	int br_handle_frame_finish(struct sk_buff *skb)
	118	{
	119	const unsigned char *dest = eth_hdr(skb)->h_dest;
f350a0a8	120	struct net_bridge_port *p = br_port_get_rcu(skb->dev);
b3f1be4b	121	struct net_bridge *br;
1da177e4	122	struct net_bridge_fdb_entry *dst;
c4fcb78c	123	struct net_bridge_mdb_entry *mdst;
e081e1e3	124	struct sk_buff *skb2;
867a5943	125	bool unicast = true;
78851988	126	u16 vid = 0;
1da177e4	127
b3f1be4b SH	128	if (!p \|\| p->state == BR_STATE_DISABLED)
	129	goto drop;
	130
78851988	131	if (!br_allowed_ingress(p->br, nbp_get_vlan_info(p), skb, &vid))
eb707618	132	goto out;
a37b85c9	133
85967bb4	134	/* insert into forwarding database after filtering to avoid spoofing */
b3f1be4b	135	br = p->br;
9ba18891	136	if (p->flags & BR_LEARNING)
a5642ab4	137	br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, false);
85967bb4	138
44661462	139	if (!is_broadcast_ether_addr(dest) && is_multicast_ether_addr(dest) &&
06499098	140	br_multicast_rcv(br, p, skb, vid))
c4fcb78c HX	141	goto drop;
c4fcb78c HX	142
b3f1be4b SH	143	if (p->state == BR_STATE_LEARNING)
b3f1be4b SH	144	goto drop;
0e5eabac	145
68b7c895 HX	146	BR_INPUT_SKB_CB(skb)->brdev = br->dev;
68b7c895 HX	147
e081e1e3 HX	148	/* The packet skb2 goes to the local host (NULL to skip). */
e081e1e3 HX	149	skb2 = NULL;
1da177e4	150
e081e1e3 HX	151	if (br->dev->flags & IFF_PROMISC)
	152	skb2 = skb;
	153
	154	dst = NULL;
1da177e4	155
867a5943	156	if (is_broadcast_ether_addr(dest)) {
95850116 KP	157	if (p->flags & BR_PROXYARP &&
	158	skb->protocol == htons(ETH_P_ARP))
	159	br_do_proxy_arp(skb, br, vid);
	160
44661462	161	skb2 = skb;
867a5943 VY	162	unicast = false;
867a5943 VY	163	} else if (is_multicast_ether_addr(dest)) {
fbca58a2	164	mdst = br_mdb_get(br, skb, vid);
b00589af	165	if ((mdst \|\| BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) &&
cc0fdd80	166	br_multicast_querier_exists(br, eth_hdr(skb))) {
8a870178	167	if ((mdst && mdst->mglist) \|\|
c4fcb78c HX	168	br_multicast_is_router(br))
	169	skb2 = skb;
	170	br_multicast_forward(mdst, skb, skb2);
	171	skb = NULL;
	172	if (!skb2)
	173	goto out;
	174	} else
	175	skb2 = skb;
	176
867a5943	177	unicast = false;
a339f1c8	178	br->dev->stats.multicast++;
2ba071ec VY	179	} else if ((dst = __br_fdb_get(br, dest, vid)) &&
2ba071ec VY	180	dst->is_local) {
e081e1e3 HX	181	skb2 = skb;
	182	/* Do not forward the packet since it's local. */
	183	skb = NULL;
1da177e4 LT	184	}
1da177e4 LT	185
e081e1e3	186	if (skb) {
7cd8861a	187	if (dst) {
7cd8861a	188	dst->used = jiffies;
7f7708f0	189	br_forward(dst->dst, skb, skb2);
7cd8861a	190	} else
867a5943	191	br_flood_forward(br, skb, skb2, unicast);
e081e1e3	192	}
1da177e4	193
87557c18	194	if (skb2)
68b7c895	195	return br_pass_frame_up(skb2);
87557c18	196
1da177e4 LT	197	out:
1da177e4 LT	198	return 0;
b3f1be4b SH	199	drop:
	200	kfree_skb(skb);
	201	goto out;
1da177e4	202	}
34666d46	203	EXPORT_SYMBOL_GPL(br_handle_frame_finish);
1da177e4	204
eeaf61d8	205	/* note: already called with rcu_read_lock */
cf0f02d0 SH	206	static int br_handle_local_finish(struct sk_buff *skb)
cf0f02d0 SH	207	{
f350a0a8	208	struct net_bridge_port *p = br_port_get_rcu(skb->dev);
2ba071ec	209	u16 vid = 0;
cf0f02d0	210
e0d7968a TM	211	/* check if vlan is allowed, to avoid spoofing */
e0d7968a TM	212	if (p->flags & BR_LEARNING && br_should_learn(p, skb, &vid))
a5642ab4	213	br_fdb_update(p->br, p, eth_hdr(skb)->h_source, vid, false);
cf0f02d0 SH	214	return 0; /* process further */
	215	}
	216
1da177e4	217	/*
6229e362	218	* Return NULL if skb is handled
eeaf61d8	219	* note: already called with rcu_read_lock
1da177e4	220	*/
8a4eb573	221	rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
1da177e4	222	{
ab95bfe0	223	struct net_bridge_port *p;
8a4eb573	224	struct sk_buff skb = pskb;
1da177e4	225	const unsigned char *dest = eth_hdr(skb)->h_dest;
a386f990	226	br_should_route_hook_t *rhook;
1da177e4	227
c2368e79	228	if (unlikely(skb->pkt_type == PACKET_LOOPBACK))
8a4eb573	229	return RX_HANDLER_PASS;
ab95bfe0	230
1da177e4	231	if (!is_valid_ether_addr(eth_hdr(skb)->h_source))
467aea0d	232	goto drop;
1da177e4	233
7b995651 HX	234	skb = skb_share_check(skb, GFP_ATOMIC);
7b995651 HX	235	if (!skb)
8a4eb573	236	return RX_HANDLER_CONSUMED;
7b995651	237
f350a0a8	238	p = br_port_get_rcu(skb->dev);
ab95bfe0	239
46acc460	240	if (unlikely(is_link_local_ether_addr(dest))) {
f2808d22 TM	241	u16 fwd_mask = p->br->group_fwd_mask_required;
f2808d22 TM	242
515853cc	243	/*
	244	* See IEEE 802.1D Table 7-10 Reserved addresses
	245	*
	246	* Assignment Value
	247	* Bridge Group Address 01-80-C2-00-00-00
	248	* (MAC Control) 802.3 01-80-C2-00-00-01
	249	* (Link Aggregation) 802.3 01-80-C2-00-00-02
	250	* 802.1X PAE address 01-80-C2-00-00-03
	251	*
	252	* 802.1AB LLDP 01-80-C2-00-00-0E
	253	*
	254	* Others reserved for future standardization
	255	*/
	256	switch (dest[5]) {
	257	case 0x00: /* Bridge Group Address */
	258	/* If STP is turned off,
	259	then must forward to keep loop detection */
f2808d22 TM	260	if (p->br->stp_enabled == BR_NO_STP \|\|
f2808d22 TM	261	fwd_mask & (1u << dest[5]))
515853cc	262	goto forward;
	263	break;
	264
	265	case 0x01: /* IEEE MAC (Pause) */
2111f8b9 SH	266	goto drop;
2111f8b9 SH	267
515853cc	268	default:
515853cc	269	/* Allow selective forwarding for most other protocols */
f2808d22 TM	270	fwd_mask \|= p->br->group_fwd_mask;
f2808d22 TM	271	if (fwd_mask & (1u << dest[5]))
515853cc	272	goto forward;
515853cc	273	}
a598f6ae	274
515853cc	275	/* Deliver packet to local host only */
713aefa3	276	if (NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, skb, skb->dev,
8a4eb573 JP	277	NULL, br_handle_local_finish)) {
	278	return RX_HANDLER_CONSUMED; /* consumed by filter */
	279	} else {
	280	*pskb = skb;
	281	return RX_HANDLER_PASS; /* continue processing */
	282	}
2111f8b9	283	}
1da177e4	284
a598f6ae	285	forward:
467aea0d SH	286	switch (p->state) {
467aea0d SH	287	case BR_STATE_FORWARDING:
82de382c	288	rhook = rcu_dereference(br_should_route_hook);
a386f990	289	if (rhook) {
8a4eb573 JP	290	if ((*rhook)(skb)) {
	291	*pskb = skb;
	292	return RX_HANDLER_PASS;
	293	}
1da177e4 LT	294	dest = eth_hdr(skb)->h_dest;
1da177e4 LT	295	}
467aea0d SH	296	/* fall through */
467aea0d SH	297	case BR_STATE_LEARNING:
9a7b6ef9	298	if (ether_addr_equal(p->br->dev->dev_addr, dest))
1da177e4 LT	299	skb->pkt_type = PACKET_HOST;
1da177e4 LT	300
713aefa3	301	NF_HOOK(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL,
1da177e4	302	br_handle_frame_finish);
467aea0d SH	303	break;
	304	default:
	305	drop:
	306	kfree_skb(skb);
1da177e4	307	}
8a4eb573	308	return RX_HANDLER_CONSUMED;
1da177e4	309	}