This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
323 lines
7.8 KiB
C
323 lines
7.8 KiB
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_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)
|
|
{
|
|
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);
|
|
|
|
vg = br_vlan_group(br);
|
|
/* Bridge is just like any other port. Make sure the
|
|
* packet is allowed except in promisc modue 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, vg, skb);
|
|
if (!skb)
|
|
return NET_RX_DROP;
|
|
|
|
return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN,
|
|
dev_net(indev), NULL, skb, indev, NULL,
|
|
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)
|
|
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 && ((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)
|
|
{
|
|
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 (!nbp_allowed_ingress(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_ENABLED(CONFIG_INET) && skb->protocol == htons(ETH_P_ARP))
|
|
br_do_proxy_arp(skb, br, vid, p);
|
|
|
|
if (is_broadcast_ether_addr(dest)) {
|
|
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 net *net, struct sock *sk, 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,
|
|
dev_net(skb->dev), NULL, 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,
|
|
dev_net(skb->dev), NULL, skb, skb->dev, NULL,
|
|
br_handle_frame_finish);
|
|
break;
|
|
default:
|
|
drop:
|
|
kfree_skb(skb);
|
|
}
|
|
return RX_HANDLER_CONSUMED;
|
|
}
|