linux/net/bridge/br_multicast.c
Herbert Xu 996304bbea bridge: Do not send queries on multicast group leaves
As it stands the bridge IGMP snooping system will respond to
group leave messages with queries for remaining membership.
This is both unnecessary and undesirable.  First of all any
multicast routers present should be doing this rather than us.
What's more the queries that we send may end up upsetting other
multicast snooping swithces in the system that are buggy.

In fact, we can simply remove the code that send these queries
because the existing membership expiry mechanism doesn't rely
on them anyway.

So this patch simply removes all code associated with group
queries in response to group leave messages.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-04-11 09:43:13 -04:00

1781 lines
38 KiB
C

/*
* Bridge multicast support.
*
* Copyright (c) 2010 Herbert Xu <herbert@gondor.apana.org.au>
*
* 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/err.h>
#include <linux/if_ether.h>
#include <linux/igmp.h>
#include <linux/jhash.h>
#include <linux/kernel.h>
#include <linux/log2.h>
#include <linux/netdevice.h>
#include <linux/netfilter_bridge.h>
#include <linux/random.h>
#include <linux/rculist.h>
#include <linux/skbuff.h>
#include <linux/slab.h>
#include <linux/timer.h>
#include <net/ip.h>
#if IS_ENABLED(CONFIG_IPV6)
#include <net/ipv6.h>
#include <net/mld.h>
#include <net/addrconf.h>
#include <net/ip6_checksum.h>
#endif
#include "br_private.h"
#define mlock_dereference(X, br) \
rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock))
#if IS_ENABLED(CONFIG_IPV6)
static inline int ipv6_is_transient_multicast(const struct in6_addr *addr)
{
if (ipv6_addr_is_multicast(addr) && IPV6_ADDR_MC_FLAG_TRANSIENT(addr))
return 1;
return 0;
}
#endif
static inline int br_ip_equal(const struct br_ip *a, const struct br_ip *b)
{
if (a->proto != b->proto)
return 0;
switch (a->proto) {
case htons(ETH_P_IP):
return a->u.ip4 == b->u.ip4;
#if IS_ENABLED(CONFIG_IPV6)
case htons(ETH_P_IPV6):
return ipv6_addr_equal(&a->u.ip6, &b->u.ip6);
#endif
}
return 0;
}
static inline int __br_ip4_hash(struct net_bridge_mdb_htable *mdb, __be32 ip)
{
return jhash_1word(mdb->secret, (__force u32)ip) & (mdb->max - 1);
}
#if IS_ENABLED(CONFIG_IPV6)
static inline int __br_ip6_hash(struct net_bridge_mdb_htable *mdb,
const struct in6_addr *ip)
{
return jhash2((__force u32 *)ip->s6_addr32, 4, mdb->secret) & (mdb->max - 1);
}
#endif
static inline int br_ip_hash(struct net_bridge_mdb_htable *mdb,
struct br_ip *ip)
{
switch (ip->proto) {
case htons(ETH_P_IP):
return __br_ip4_hash(mdb, ip->u.ip4);
#if IS_ENABLED(CONFIG_IPV6)
case htons(ETH_P_IPV6):
return __br_ip6_hash(mdb, &ip->u.ip6);
#endif
}
return 0;
}
static struct net_bridge_mdb_entry *__br_mdb_ip_get(
struct net_bridge_mdb_htable *mdb, struct br_ip *dst, int hash)
{
struct net_bridge_mdb_entry *mp;
struct hlist_node *p;
hlist_for_each_entry_rcu(mp, p, &mdb->mhash[hash], hlist[mdb->ver]) {
if (br_ip_equal(&mp->addr, dst))
return mp;
}
return NULL;
}
static struct net_bridge_mdb_entry *br_mdb_ip_get(
struct net_bridge_mdb_htable *mdb, struct br_ip *dst)
{
if (!mdb)
return NULL;
return __br_mdb_ip_get(mdb, dst, br_ip_hash(mdb, dst));
}
static struct net_bridge_mdb_entry *br_mdb_ip4_get(
struct net_bridge_mdb_htable *mdb, __be32 dst)
{
struct br_ip br_dst;
br_dst.u.ip4 = dst;
br_dst.proto = htons(ETH_P_IP);
return br_mdb_ip_get(mdb, &br_dst);
}
#if IS_ENABLED(CONFIG_IPV6)
static struct net_bridge_mdb_entry *br_mdb_ip6_get(
struct net_bridge_mdb_htable *mdb, const struct in6_addr *dst)
{
struct br_ip br_dst;
br_dst.u.ip6 = *dst;
br_dst.proto = htons(ETH_P_IPV6);
return br_mdb_ip_get(mdb, &br_dst);
}
#endif
struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br,
struct sk_buff *skb)
{
struct net_bridge_mdb_htable *mdb = rcu_dereference(br->mdb);
struct br_ip ip;
if (br->multicast_disabled)
return NULL;
if (BR_INPUT_SKB_CB(skb)->igmp)
return NULL;
ip.proto = skb->protocol;
switch (skb->protocol) {
case htons(ETH_P_IP):
ip.u.ip4 = ip_hdr(skb)->daddr;
break;
#if IS_ENABLED(CONFIG_IPV6)
case htons(ETH_P_IPV6):
ip.u.ip6 = ipv6_hdr(skb)->daddr;
break;
#endif
default:
return NULL;
}
return br_mdb_ip_get(mdb, &ip);
}
static void br_mdb_free(struct rcu_head *head)
{
struct net_bridge_mdb_htable *mdb =
container_of(head, struct net_bridge_mdb_htable, rcu);
struct net_bridge_mdb_htable *old = mdb->old;
mdb->old = NULL;
kfree(old->mhash);
kfree(old);
}
static int br_mdb_copy(struct net_bridge_mdb_htable *new,
struct net_bridge_mdb_htable *old,
int elasticity)
{
struct net_bridge_mdb_entry *mp;
struct hlist_node *p;
int maxlen;
int len;
int i;
for (i = 0; i < old->max; i++)
hlist_for_each_entry(mp, p, &old->mhash[i], hlist[old->ver])
hlist_add_head(&mp->hlist[new->ver],
&new->mhash[br_ip_hash(new, &mp->addr)]);
if (!elasticity)
return 0;
maxlen = 0;
for (i = 0; i < new->max; i++) {
len = 0;
hlist_for_each_entry(mp, p, &new->mhash[i], hlist[new->ver])
len++;
if (len > maxlen)
maxlen = len;
}
return maxlen > elasticity ? -EINVAL : 0;
}
static void br_multicast_free_pg(struct rcu_head *head)
{
struct net_bridge_port_group *p =
container_of(head, struct net_bridge_port_group, rcu);
kfree(p);
}
static void br_multicast_free_group(struct rcu_head *head)
{
struct net_bridge_mdb_entry *mp =
container_of(head, struct net_bridge_mdb_entry, rcu);
kfree(mp);
}
static void br_multicast_group_expired(unsigned long data)
{
struct net_bridge_mdb_entry *mp = (void *)data;
struct net_bridge *br = mp->br;
struct net_bridge_mdb_htable *mdb;
spin_lock(&br->multicast_lock);
if (!netif_running(br->dev) || timer_pending(&mp->timer))
goto out;
mp->mglist = false;
if (mp->ports)
goto out;
mdb = mlock_dereference(br->mdb, br);
hlist_del_rcu(&mp->hlist[mdb->ver]);
mdb->size--;
call_rcu_bh(&mp->rcu, br_multicast_free_group);
out:
spin_unlock(&br->multicast_lock);
}
static void br_multicast_del_pg(struct net_bridge *br,
struct net_bridge_port_group *pg)
{
struct net_bridge_mdb_htable *mdb;
struct net_bridge_mdb_entry *mp;
struct net_bridge_port_group *p;
struct net_bridge_port_group __rcu **pp;
mdb = mlock_dereference(br->mdb, br);
mp = br_mdb_ip_get(mdb, &pg->addr);
if (WARN_ON(!mp))
return;
for (pp = &mp->ports;
(p = mlock_dereference(*pp, br)) != NULL;
pp = &p->next) {
if (p != pg)
continue;
rcu_assign_pointer(*pp, p->next);
hlist_del_init(&p->mglist);
del_timer(&p->timer);
call_rcu_bh(&p->rcu, br_multicast_free_pg);
if (!mp->ports && !mp->mglist &&
netif_running(br->dev))
mod_timer(&mp->timer, jiffies);
return;
}
WARN_ON(1);
}
static void br_multicast_port_group_expired(unsigned long data)
{
struct net_bridge_port_group *pg = (void *)data;
struct net_bridge *br = pg->port->br;
spin_lock(&br->multicast_lock);
if (!netif_running(br->dev) || timer_pending(&pg->timer) ||
hlist_unhashed(&pg->mglist))
goto out;
br_multicast_del_pg(br, pg);
out:
spin_unlock(&br->multicast_lock);
}
static int br_mdb_rehash(struct net_bridge_mdb_htable __rcu **mdbp, int max,
int elasticity)
{
struct net_bridge_mdb_htable *old = rcu_dereference_protected(*mdbp, 1);
struct net_bridge_mdb_htable *mdb;
int err;
mdb = kmalloc(sizeof(*mdb), GFP_ATOMIC);
if (!mdb)
return -ENOMEM;
mdb->max = max;
mdb->old = old;
mdb->mhash = kzalloc(max * sizeof(*mdb->mhash), GFP_ATOMIC);
if (!mdb->mhash) {
kfree(mdb);
return -ENOMEM;
}
mdb->size = old ? old->size : 0;
mdb->ver = old ? old->ver ^ 1 : 0;
if (!old || elasticity)
get_random_bytes(&mdb->secret, sizeof(mdb->secret));
else
mdb->secret = old->secret;
if (!old)
goto out;
err = br_mdb_copy(mdb, old, elasticity);
if (err) {
kfree(mdb->mhash);
kfree(mdb);
return err;
}
call_rcu_bh(&mdb->rcu, br_mdb_free);
out:
rcu_assign_pointer(*mdbp, mdb);
return 0;
}
static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br,
__be32 group)
{
struct sk_buff *skb;
struct igmphdr *ih;
struct ethhdr *eth;
struct iphdr *iph;
skb = netdev_alloc_skb_ip_align(br->dev, sizeof(*eth) + sizeof(*iph) +
sizeof(*ih) + 4);
if (!skb)
goto out;
skb->protocol = htons(ETH_P_IP);
skb_reset_mac_header(skb);
eth = eth_hdr(skb);
memcpy(eth->h_source, br->dev->dev_addr, 6);
eth->h_dest[0] = 1;
eth->h_dest[1] = 0;
eth->h_dest[2] = 0x5e;
eth->h_dest[3] = 0;
eth->h_dest[4] = 0;
eth->h_dest[5] = 1;
eth->h_proto = htons(ETH_P_IP);
skb_put(skb, sizeof(*eth));
skb_set_network_header(skb, skb->len);
iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = 6;
iph->tos = 0xc0;
iph->tot_len = htons(sizeof(*iph) + sizeof(*ih) + 4);
iph->id = 0;
iph->frag_off = htons(IP_DF);
iph->ttl = 1;
iph->protocol = IPPROTO_IGMP;
iph->saddr = 0;
iph->daddr = htonl(INADDR_ALLHOSTS_GROUP);
((u8 *)&iph[1])[0] = IPOPT_RA;
((u8 *)&iph[1])[1] = 4;
((u8 *)&iph[1])[2] = 0;
((u8 *)&iph[1])[3] = 0;
ip_send_check(iph);
skb_put(skb, 24);
skb_set_transport_header(skb, skb->len);
ih = igmp_hdr(skb);
ih->type = IGMP_HOST_MEMBERSHIP_QUERY;
ih->code = (group ? br->multicast_last_member_interval :
br->multicast_query_response_interval) /
(HZ / IGMP_TIMER_SCALE);
ih->group = group;
ih->csum = 0;
ih->csum = ip_compute_csum((void *)ih, sizeof(struct igmphdr));
skb_put(skb, sizeof(*ih));
__skb_pull(skb, sizeof(*eth));
out:
return skb;
}
#if IS_ENABLED(CONFIG_IPV6)
static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br,
const struct in6_addr *group)
{
struct sk_buff *skb;
struct ipv6hdr *ip6h;
struct mld_msg *mldq;
struct ethhdr *eth;
u8 *hopopt;
unsigned long interval;
skb = netdev_alloc_skb_ip_align(br->dev, sizeof(*eth) + sizeof(*ip6h) +
8 + sizeof(*mldq));
if (!skb)
goto out;
skb->protocol = htons(ETH_P_IPV6);
/* Ethernet header */
skb_reset_mac_header(skb);
eth = eth_hdr(skb);
memcpy(eth->h_source, br->dev->dev_addr, 6);
eth->h_proto = htons(ETH_P_IPV6);
skb_put(skb, sizeof(*eth));
/* IPv6 header + HbH option */
skb_set_network_header(skb, skb->len);
ip6h = ipv6_hdr(skb);
*(__force __be32 *)ip6h = htonl(0x60000000);
ip6h->payload_len = htons(8 + sizeof(*mldq));
ip6h->nexthdr = IPPROTO_HOPOPTS;
ip6h->hop_limit = 1;
ipv6_addr_set(&ip6h->daddr, htonl(0xff020000), 0, 0, htonl(1));
if (ipv6_dev_get_saddr(dev_net(br->dev), br->dev, &ip6h->daddr, 0,
&ip6h->saddr)) {
kfree_skb(skb);
return NULL;
}
ipv6_eth_mc_map(&ip6h->daddr, eth->h_dest);
hopopt = (u8 *)(ip6h + 1);
hopopt[0] = IPPROTO_ICMPV6; /* next hdr */
hopopt[1] = 0; /* length of HbH */
hopopt[2] = IPV6_TLV_ROUTERALERT; /* Router Alert */
hopopt[3] = 2; /* Length of RA Option */
hopopt[4] = 0; /* Type = 0x0000 (MLD) */
hopopt[5] = 0;
hopopt[6] = IPV6_TLV_PAD0; /* Pad0 */
hopopt[7] = IPV6_TLV_PAD0; /* Pad0 */
skb_put(skb, sizeof(*ip6h) + 8);
/* ICMPv6 */
skb_set_transport_header(skb, skb->len);
mldq = (struct mld_msg *) icmp6_hdr(skb);
interval = ipv6_addr_any(group) ? br->multicast_last_member_interval :
br->multicast_query_response_interval;
mldq->mld_type = ICMPV6_MGM_QUERY;
mldq->mld_code = 0;
mldq->mld_cksum = 0;
mldq->mld_maxdelay = htons((u16)jiffies_to_msecs(interval));
mldq->mld_reserved = 0;
mldq->mld_mca = *group;
/* checksum */
mldq->mld_cksum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
sizeof(*mldq), IPPROTO_ICMPV6,
csum_partial(mldq,
sizeof(*mldq), 0));
skb_put(skb, sizeof(*mldq));
__skb_pull(skb, sizeof(*eth));
out:
return skb;
}
#endif
static struct sk_buff *br_multicast_alloc_query(struct net_bridge *br,
struct br_ip *addr)
{
switch (addr->proto) {
case htons(ETH_P_IP):
return br_ip4_multicast_alloc_query(br, addr->u.ip4);
#if IS_ENABLED(CONFIG_IPV6)
case htons(ETH_P_IPV6):
return br_ip6_multicast_alloc_query(br, &addr->u.ip6);
#endif
}
return NULL;
}
static struct net_bridge_mdb_entry *br_multicast_get_group(
struct net_bridge *br, struct net_bridge_port *port,
struct br_ip *group, int hash)
{
struct net_bridge_mdb_htable *mdb;
struct net_bridge_mdb_entry *mp;
struct hlist_node *p;
unsigned count = 0;
unsigned max;
int elasticity;
int err;
mdb = rcu_dereference_protected(br->mdb, 1);
hlist_for_each_entry(mp, p, &mdb->mhash[hash], hlist[mdb->ver]) {
count++;
if (unlikely(br_ip_equal(group, &mp->addr)))
return mp;
}
elasticity = 0;
max = mdb->max;
if (unlikely(count > br->hash_elasticity && count)) {
if (net_ratelimit())
br_info(br, "Multicast hash table "
"chain limit reached: %s\n",
port ? port->dev->name : br->dev->name);
elasticity = br->hash_elasticity;
}
if (mdb->size >= max) {
max *= 2;
if (unlikely(max >= br->hash_max)) {
br_warn(br, "Multicast hash table maximum "
"reached, disabling snooping: %s, %d\n",
port ? port->dev->name : br->dev->name, max);
err = -E2BIG;
disable:
br->multicast_disabled = 1;
goto err;
}
}
if (max > mdb->max || elasticity) {
if (mdb->old) {
if (net_ratelimit())
br_info(br, "Multicast hash table "
"on fire: %s\n",
port ? port->dev->name : br->dev->name);
err = -EEXIST;
goto err;
}
err = br_mdb_rehash(&br->mdb, max, elasticity);
if (err) {
br_warn(br, "Cannot rehash multicast "
"hash table, disabling snooping: %s, %d, %d\n",
port ? port->dev->name : br->dev->name,
mdb->size, err);
goto disable;
}
err = -EAGAIN;
goto err;
}
return NULL;
err:
mp = ERR_PTR(err);
return mp;
}
static struct net_bridge_mdb_entry *br_multicast_new_group(
struct net_bridge *br, struct net_bridge_port *port,
struct br_ip *group)
{
struct net_bridge_mdb_htable *mdb;
struct net_bridge_mdb_entry *mp;
int hash;
int err;
mdb = rcu_dereference_protected(br->mdb, 1);
if (!mdb) {
err = br_mdb_rehash(&br->mdb, BR_HASH_SIZE, 0);
if (err)
return ERR_PTR(err);
goto rehash;
}
hash = br_ip_hash(mdb, group);
mp = br_multicast_get_group(br, port, group, hash);
switch (PTR_ERR(mp)) {
case 0:
break;
case -EAGAIN:
rehash:
mdb = rcu_dereference_protected(br->mdb, 1);
hash = br_ip_hash(mdb, group);
break;
default:
goto out;
}
mp = kzalloc(sizeof(*mp), GFP_ATOMIC);
if (unlikely(!mp))
return ERR_PTR(-ENOMEM);
mp->br = br;
mp->addr = *group;
setup_timer(&mp->timer, br_multicast_group_expired,
(unsigned long)mp);
hlist_add_head_rcu(&mp->hlist[mdb->ver], &mdb->mhash[hash]);
mdb->size++;
out:
return mp;
}
static int br_multicast_add_group(struct net_bridge *br,
struct net_bridge_port *port,
struct br_ip *group)
{
struct net_bridge_mdb_entry *mp;
struct net_bridge_port_group *p;
struct net_bridge_port_group __rcu **pp;
unsigned long now = jiffies;
int err;
spin_lock(&br->multicast_lock);
if (!netif_running(br->dev) ||
(port && port->state == BR_STATE_DISABLED))
goto out;
mp = br_multicast_new_group(br, port, group);
err = PTR_ERR(mp);
if (IS_ERR(mp))
goto err;
if (!port) {
mp->mglist = true;
mod_timer(&mp->timer, now + br->multicast_membership_interval);
goto out;
}
for (pp = &mp->ports;
(p = mlock_dereference(*pp, br)) != NULL;
pp = &p->next) {
if (p->port == port)
goto found;
if ((unsigned long)p->port < (unsigned long)port)
break;
}
p = kzalloc(sizeof(*p), GFP_ATOMIC);
err = -ENOMEM;
if (unlikely(!p))
goto err;
p->addr = *group;
p->port = port;
p->next = *pp;
hlist_add_head(&p->mglist, &port->mglist);
setup_timer(&p->timer, br_multicast_port_group_expired,
(unsigned long)p);
rcu_assign_pointer(*pp, p);
found:
mod_timer(&p->timer, now + br->multicast_membership_interval);
out:
err = 0;
err:
spin_unlock(&br->multicast_lock);
return err;
}
static int br_ip4_multicast_add_group(struct net_bridge *br,
struct net_bridge_port *port,
__be32 group)
{
struct br_ip br_group;
if (ipv4_is_local_multicast(group))
return 0;
br_group.u.ip4 = group;
br_group.proto = htons(ETH_P_IP);
return br_multicast_add_group(br, port, &br_group);
}
#if IS_ENABLED(CONFIG_IPV6)
static int br_ip6_multicast_add_group(struct net_bridge *br,
struct net_bridge_port *port,
const struct in6_addr *group)
{
struct br_ip br_group;
if (!ipv6_is_transient_multicast(group))
return 0;
br_group.u.ip6 = *group;
br_group.proto = htons(ETH_P_IPV6);
return br_multicast_add_group(br, port, &br_group);
}
#endif
static void br_multicast_router_expired(unsigned long data)
{
struct net_bridge_port *port = (void *)data;
struct net_bridge *br = port->br;
spin_lock(&br->multicast_lock);
if (port->multicast_router != 1 ||
timer_pending(&port->multicast_router_timer) ||
hlist_unhashed(&port->rlist))
goto out;
hlist_del_init_rcu(&port->rlist);
out:
spin_unlock(&br->multicast_lock);
}
static void br_multicast_local_router_expired(unsigned long data)
{
}
static void __br_multicast_send_query(struct net_bridge *br,
struct net_bridge_port *port,
struct br_ip *ip)
{
struct sk_buff *skb;
skb = br_multicast_alloc_query(br, ip);
if (!skb)
return;
if (port) {
__skb_push(skb, sizeof(struct ethhdr));
skb->dev = port->dev;
NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, skb, NULL, skb->dev,
dev_queue_xmit);
} else
netif_rx(skb);
}
static void br_multicast_send_query(struct net_bridge *br,
struct net_bridge_port *port, u32 sent)
{
unsigned long time;
struct br_ip br_group;
if (!netif_running(br->dev) || br->multicast_disabled ||
timer_pending(&br->multicast_querier_timer))
return;
memset(&br_group.u, 0, sizeof(br_group.u));
br_group.proto = htons(ETH_P_IP);
__br_multicast_send_query(br, port, &br_group);
#if IS_ENABLED(CONFIG_IPV6)
br_group.proto = htons(ETH_P_IPV6);
__br_multicast_send_query(br, port, &br_group);
#endif
time = jiffies;
time += sent < br->multicast_startup_query_count ?
br->multicast_startup_query_interval :
br->multicast_query_interval;
mod_timer(port ? &port->multicast_query_timer :
&br->multicast_query_timer, time);
}
static void br_multicast_port_query_expired(unsigned long data)
{
struct net_bridge_port *port = (void *)data;
struct net_bridge *br = port->br;
spin_lock(&br->multicast_lock);
if (port->state == BR_STATE_DISABLED ||
port->state == BR_STATE_BLOCKING)
goto out;
if (port->multicast_startup_queries_sent <
br->multicast_startup_query_count)
port->multicast_startup_queries_sent++;
br_multicast_send_query(port->br, port,
port->multicast_startup_queries_sent);
out:
spin_unlock(&br->multicast_lock);
}
void br_multicast_add_port(struct net_bridge_port *port)
{
port->multicast_router = 1;
setup_timer(&port->multicast_router_timer, br_multicast_router_expired,
(unsigned long)port);
setup_timer(&port->multicast_query_timer,
br_multicast_port_query_expired, (unsigned long)port);
}
void br_multicast_del_port(struct net_bridge_port *port)
{
del_timer_sync(&port->multicast_router_timer);
}
static void __br_multicast_enable_port(struct net_bridge_port *port)
{
port->multicast_startup_queries_sent = 0;
if (try_to_del_timer_sync(&port->multicast_query_timer) >= 0 ||
del_timer(&port->multicast_query_timer))
mod_timer(&port->multicast_query_timer, jiffies);
}
void br_multicast_enable_port(struct net_bridge_port *port)
{
struct net_bridge *br = port->br;
spin_lock(&br->multicast_lock);
if (br->multicast_disabled || !netif_running(br->dev))
goto out;
__br_multicast_enable_port(port);
out:
spin_unlock(&br->multicast_lock);
}
void br_multicast_disable_port(struct net_bridge_port *port)
{
struct net_bridge *br = port->br;
struct net_bridge_port_group *pg;
struct hlist_node *p, *n;
spin_lock(&br->multicast_lock);
hlist_for_each_entry_safe(pg, p, n, &port->mglist, mglist)
br_multicast_del_pg(br, pg);
if (!hlist_unhashed(&port->rlist))
hlist_del_init_rcu(&port->rlist);
del_timer(&port->multicast_router_timer);
del_timer(&port->multicast_query_timer);
spin_unlock(&br->multicast_lock);
}
static int br_ip4_multicast_igmp3_report(struct net_bridge *br,
struct net_bridge_port *port,
struct sk_buff *skb)
{
struct igmpv3_report *ih;
struct igmpv3_grec *grec;
int i;
int len;
int num;
int type;
int err = 0;
__be32 group;
if (!pskb_may_pull(skb, sizeof(*ih)))
return -EINVAL;
ih = igmpv3_report_hdr(skb);
num = ntohs(ih->ngrec);
len = sizeof(*ih);
for (i = 0; i < num; i++) {
len += sizeof(*grec);
if (!pskb_may_pull(skb, len))
return -EINVAL;
grec = (void *)(skb->data + len - sizeof(*grec));
group = grec->grec_mca;
type = grec->grec_type;
len += ntohs(grec->grec_nsrcs) * 4;
if (!pskb_may_pull(skb, len))
return -EINVAL;
/* We treat this as an IGMPv2 report for now. */
switch (type) {
case IGMPV3_MODE_IS_INCLUDE:
case IGMPV3_MODE_IS_EXCLUDE:
case IGMPV3_CHANGE_TO_INCLUDE:
case IGMPV3_CHANGE_TO_EXCLUDE:
case IGMPV3_ALLOW_NEW_SOURCES:
case IGMPV3_BLOCK_OLD_SOURCES:
break;
default:
continue;
}
err = br_ip4_multicast_add_group(br, port, group);
if (err)
break;
}
return err;
}
#if IS_ENABLED(CONFIG_IPV6)
static int br_ip6_multicast_mld2_report(struct net_bridge *br,
struct net_bridge_port *port,
struct sk_buff *skb)
{
struct icmp6hdr *icmp6h;
struct mld2_grec *grec;
int i;
int len;
int num;
int err = 0;
if (!pskb_may_pull(skb, sizeof(*icmp6h)))
return -EINVAL;
icmp6h = icmp6_hdr(skb);
num = ntohs(icmp6h->icmp6_dataun.un_data16[1]);
len = sizeof(*icmp6h);
for (i = 0; i < num; i++) {
__be16 *nsrcs, _nsrcs;
nsrcs = skb_header_pointer(skb,
len + offsetof(struct mld2_grec,
grec_nsrcs),
sizeof(_nsrcs), &_nsrcs);
if (!nsrcs)
return -EINVAL;
if (!pskb_may_pull(skb,
len + sizeof(*grec) +
sizeof(struct in6_addr) * ntohs(*nsrcs)))
return -EINVAL;
grec = (struct mld2_grec *)(skb->data + len);
len += sizeof(*grec) +
sizeof(struct in6_addr) * ntohs(*nsrcs);
/* We treat these as MLDv1 reports for now. */
switch (grec->grec_type) {
case MLD2_MODE_IS_INCLUDE:
case MLD2_MODE_IS_EXCLUDE:
case MLD2_CHANGE_TO_INCLUDE:
case MLD2_CHANGE_TO_EXCLUDE:
case MLD2_ALLOW_NEW_SOURCES:
case MLD2_BLOCK_OLD_SOURCES:
break;
default:
continue;
}
err = br_ip6_multicast_add_group(br, port, &grec->grec_mca);
if (!err)
break;
}
return err;
}
#endif
/*
* Add port to rotuer_list
* list is maintained ordered by pointer value
* and locked by br->multicast_lock and RCU
*/
static void br_multicast_add_router(struct net_bridge *br,
struct net_bridge_port *port)
{
struct net_bridge_port *p;
struct hlist_node *n, *slot = NULL;
hlist_for_each_entry(p, n, &br->router_list, rlist) {
if ((unsigned long) port >= (unsigned long) p)
break;
slot = n;
}
if (slot)
hlist_add_after_rcu(slot, &port->rlist);
else
hlist_add_head_rcu(&port->rlist, &br->router_list);
}
static void br_multicast_mark_router(struct net_bridge *br,
struct net_bridge_port *port)
{
unsigned long now = jiffies;
if (!port) {
if (br->multicast_router == 1)
mod_timer(&br->multicast_router_timer,
now + br->multicast_querier_interval);
return;
}
if (port->multicast_router != 1)
return;
if (!hlist_unhashed(&port->rlist))
goto timer;
br_multicast_add_router(br, port);
timer:
mod_timer(&port->multicast_router_timer,
now + br->multicast_querier_interval);
}
static void br_multicast_query_received(struct net_bridge *br,
struct net_bridge_port *port,
int saddr)
{
if (saddr)
mod_timer(&br->multicast_querier_timer,
jiffies + br->multicast_querier_interval);
else if (timer_pending(&br->multicast_querier_timer))
return;
br_multicast_mark_router(br, port);
}
static int br_ip4_multicast_query(struct net_bridge *br,
struct net_bridge_port *port,
struct sk_buff *skb)
{
const struct iphdr *iph = ip_hdr(skb);
struct igmphdr *ih = igmp_hdr(skb);
struct net_bridge_mdb_entry *mp;
struct igmpv3_query *ih3;
struct net_bridge_port_group *p;
struct net_bridge_port_group __rcu **pp;
unsigned long max_delay;
unsigned long now = jiffies;
__be32 group;
int err = 0;
spin_lock(&br->multicast_lock);
if (!netif_running(br->dev) ||
(port && port->state == BR_STATE_DISABLED))
goto out;
br_multicast_query_received(br, port, !!iph->saddr);
group = ih->group;
if (skb->len == sizeof(*ih)) {
max_delay = ih->code * (HZ / IGMP_TIMER_SCALE);
if (!max_delay) {
max_delay = 10 * HZ;
group = 0;
}
} else {
if (!pskb_may_pull(skb, sizeof(struct igmpv3_query))) {
err = -EINVAL;
goto out;
}
ih3 = igmpv3_query_hdr(skb);
if (ih3->nsrcs)
goto out;
max_delay = ih3->code ?
IGMPV3_MRC(ih3->code) * (HZ / IGMP_TIMER_SCALE) : 1;
}
if (!group)
goto out;
mp = br_mdb_ip4_get(mlock_dereference(br->mdb, br), group);
if (!mp)
goto out;
max_delay *= br->multicast_last_member_count;
if (mp->mglist &&
(timer_pending(&mp->timer) ?
time_after(mp->timer.expires, now + max_delay) :
try_to_del_timer_sync(&mp->timer) >= 0))
mod_timer(&mp->timer, now + max_delay);
for (pp = &mp->ports;
(p = mlock_dereference(*pp, br)) != NULL;
pp = &p->next) {
if (timer_pending(&p->timer) ?
time_after(p->timer.expires, now + max_delay) :
try_to_del_timer_sync(&p->timer) >= 0)
mod_timer(&p->timer, now + max_delay);
}
out:
spin_unlock(&br->multicast_lock);
return err;
}
#if IS_ENABLED(CONFIG_IPV6)
static int br_ip6_multicast_query(struct net_bridge *br,
struct net_bridge_port *port,
struct sk_buff *skb)
{
const struct ipv6hdr *ip6h = ipv6_hdr(skb);
struct mld_msg *mld = (struct mld_msg *) icmp6_hdr(skb);
struct net_bridge_mdb_entry *mp;
struct mld2_query *mld2q;
struct net_bridge_port_group *p;
struct net_bridge_port_group __rcu **pp;
unsigned long max_delay;
unsigned long now = jiffies;
const struct in6_addr *group = NULL;
int err = 0;
spin_lock(&br->multicast_lock);
if (!netif_running(br->dev) ||
(port && port->state == BR_STATE_DISABLED))
goto out;
br_multicast_query_received(br, port, !ipv6_addr_any(&ip6h->saddr));
if (skb->len == sizeof(*mld)) {
if (!pskb_may_pull(skb, sizeof(*mld))) {
err = -EINVAL;
goto out;
}
mld = (struct mld_msg *) icmp6_hdr(skb);
max_delay = msecs_to_jiffies(htons(mld->mld_maxdelay));
if (max_delay)
group = &mld->mld_mca;
} else if (skb->len >= sizeof(*mld2q)) {
if (!pskb_may_pull(skb, sizeof(*mld2q))) {
err = -EINVAL;
goto out;
}
mld2q = (struct mld2_query *)icmp6_hdr(skb);
if (!mld2q->mld2q_nsrcs)
group = &mld2q->mld2q_mca;
max_delay = mld2q->mld2q_mrc ? MLDV2_MRC(mld2q->mld2q_mrc) : 1;
}
if (!group)
goto out;
mp = br_mdb_ip6_get(mlock_dereference(br->mdb, br), group);
if (!mp)
goto out;
max_delay *= br->multicast_last_member_count;
if (mp->mglist &&
(timer_pending(&mp->timer) ?
time_after(mp->timer.expires, now + max_delay) :
try_to_del_timer_sync(&mp->timer) >= 0))
mod_timer(&mp->timer, now + max_delay);
for (pp = &mp->ports;
(p = mlock_dereference(*pp, br)) != NULL;
pp = &p->next) {
if (timer_pending(&p->timer) ?
time_after(p->timer.expires, now + max_delay) :
try_to_del_timer_sync(&p->timer) >= 0)
mod_timer(&p->timer, now + max_delay);
}
out:
spin_unlock(&br->multicast_lock);
return err;
}
#endif
static void br_multicast_leave_group(struct net_bridge *br,
struct net_bridge_port *port,
struct br_ip *group)
{
struct net_bridge_mdb_htable *mdb;
struct net_bridge_mdb_entry *mp;
struct net_bridge_port_group *p;
unsigned long now;
unsigned long time;
spin_lock(&br->multicast_lock);
if (!netif_running(br->dev) ||
(port && port->state == BR_STATE_DISABLED) ||
timer_pending(&br->multicast_querier_timer))
goto out;
mdb = mlock_dereference(br->mdb, br);
mp = br_mdb_ip_get(mdb, group);
if (!mp)
goto out;
now = jiffies;
time = now + br->multicast_last_member_count *
br->multicast_last_member_interval;
if (!port) {
if (mp->mglist &&
(timer_pending(&mp->timer) ?
time_after(mp->timer.expires, time) :
try_to_del_timer_sync(&mp->timer) >= 0)) {
mod_timer(&mp->timer, time);
}
goto out;
}
for (p = mlock_dereference(mp->ports, br);
p != NULL;
p = mlock_dereference(p->next, br)) {
if (p->port != port)
continue;
if (!hlist_unhashed(&p->mglist) &&
(timer_pending(&p->timer) ?
time_after(p->timer.expires, time) :
try_to_del_timer_sync(&p->timer) >= 0)) {
mod_timer(&p->timer, time);
}
break;
}
out:
spin_unlock(&br->multicast_lock);
}
static void br_ip4_multicast_leave_group(struct net_bridge *br,
struct net_bridge_port *port,
__be32 group)
{
struct br_ip br_group;
if (ipv4_is_local_multicast(group))
return;
br_group.u.ip4 = group;
br_group.proto = htons(ETH_P_IP);
br_multicast_leave_group(br, port, &br_group);
}
#if IS_ENABLED(CONFIG_IPV6)
static void br_ip6_multicast_leave_group(struct net_bridge *br,
struct net_bridge_port *port,
const struct in6_addr *group)
{
struct br_ip br_group;
if (!ipv6_is_transient_multicast(group))
return;
br_group.u.ip6 = *group;
br_group.proto = htons(ETH_P_IPV6);
br_multicast_leave_group(br, port, &br_group);
}
#endif
static int br_multicast_ipv4_rcv(struct net_bridge *br,
struct net_bridge_port *port,
struct sk_buff *skb)
{
struct sk_buff *skb2 = skb;
const struct iphdr *iph;
struct igmphdr *ih;
unsigned len;
unsigned offset;
int err;
/* We treat OOM as packet loss for now. */
if (!pskb_may_pull(skb, sizeof(*iph)))
return -EINVAL;
iph = ip_hdr(skb);
if (iph->ihl < 5 || iph->version != 4)
return -EINVAL;
if (!pskb_may_pull(skb, ip_hdrlen(skb)))
return -EINVAL;
iph = ip_hdr(skb);
if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl)))
return -EINVAL;
if (iph->protocol != IPPROTO_IGMP) {
if ((iph->daddr & IGMP_LOCAL_GROUP_MASK) != IGMP_LOCAL_GROUP)
BR_INPUT_SKB_CB(skb)->mrouters_only = 1;
return 0;
}
len = ntohs(iph->tot_len);
if (skb->len < len || len < ip_hdrlen(skb))
return -EINVAL;
if (skb->len > len) {
skb2 = skb_clone(skb, GFP_ATOMIC);
if (!skb2)
return -ENOMEM;
err = pskb_trim_rcsum(skb2, len);
if (err)
goto err_out;
}
len -= ip_hdrlen(skb2);
offset = skb_network_offset(skb2) + ip_hdrlen(skb2);
__skb_pull(skb2, offset);
skb_reset_transport_header(skb2);
err = -EINVAL;
if (!pskb_may_pull(skb2, sizeof(*ih)))
goto out;
switch (skb2->ip_summed) {
case CHECKSUM_COMPLETE:
if (!csum_fold(skb2->csum))
break;
/* fall through */
case CHECKSUM_NONE:
skb2->csum = 0;
if (skb_checksum_complete(skb2))
goto out;
}
err = 0;
BR_INPUT_SKB_CB(skb)->igmp = 1;
ih = igmp_hdr(skb2);
switch (ih->type) {
case IGMP_HOST_MEMBERSHIP_REPORT:
case IGMPV2_HOST_MEMBERSHIP_REPORT:
BR_INPUT_SKB_CB(skb)->mrouters_only = 1;
err = br_ip4_multicast_add_group(br, port, ih->group);
break;
case IGMPV3_HOST_MEMBERSHIP_REPORT:
err = br_ip4_multicast_igmp3_report(br, port, skb2);
break;
case IGMP_HOST_MEMBERSHIP_QUERY:
err = br_ip4_multicast_query(br, port, skb2);
break;
case IGMP_HOST_LEAVE_MESSAGE:
br_ip4_multicast_leave_group(br, port, ih->group);
break;
}
out:
__skb_push(skb2, offset);
err_out:
if (skb2 != skb)
kfree_skb(skb2);
return err;
}
#if IS_ENABLED(CONFIG_IPV6)
static int br_multicast_ipv6_rcv(struct net_bridge *br,
struct net_bridge_port *port,
struct sk_buff *skb)
{
struct sk_buff *skb2;
const struct ipv6hdr *ip6h;
u8 icmp6_type;
u8 nexthdr;
__be16 frag_off;
unsigned len;
int offset;
int err;
if (!pskb_may_pull(skb, sizeof(*ip6h)))
return -EINVAL;
ip6h = ipv6_hdr(skb);
/*
* We're interested in MLD messages only.
* - Version is 6
* - MLD has always Router Alert hop-by-hop option
* - But we do not support jumbrograms.
*/
if (ip6h->version != 6 ||
ip6h->nexthdr != IPPROTO_HOPOPTS ||
ip6h->payload_len == 0)
return 0;
len = ntohs(ip6h->payload_len) + sizeof(*ip6h);
if (skb->len < len)
return -EINVAL;
nexthdr = ip6h->nexthdr;
offset = ipv6_skip_exthdr(skb, sizeof(*ip6h), &nexthdr, &frag_off);
if (offset < 0 || nexthdr != IPPROTO_ICMPV6)
return 0;
/* Okay, we found ICMPv6 header */
skb2 = skb_clone(skb, GFP_ATOMIC);
if (!skb2)
return -ENOMEM;
err = -EINVAL;
if (!pskb_may_pull(skb2, offset + sizeof(struct icmp6hdr)))
goto out;
len -= offset - skb_network_offset(skb2);
__skb_pull(skb2, offset);
skb_reset_transport_header(skb2);
skb_postpull_rcsum(skb2, skb_network_header(skb2),
skb_network_header_len(skb2));
icmp6_type = icmp6_hdr(skb2)->icmp6_type;
switch (icmp6_type) {
case ICMPV6_MGM_QUERY:
case ICMPV6_MGM_REPORT:
case ICMPV6_MGM_REDUCTION:
case ICMPV6_MLD2_REPORT:
break;
default:
err = 0;
goto out;
}
/* Okay, we found MLD message. Check further. */
if (skb2->len > len) {
err = pskb_trim_rcsum(skb2, len);
if (err)
goto out;
err = -EINVAL;
}
ip6h = ipv6_hdr(skb2);
switch (skb2->ip_summed) {
case CHECKSUM_COMPLETE:
if (!csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, skb2->len,
IPPROTO_ICMPV6, skb2->csum))
break;
/*FALLTHROUGH*/
case CHECKSUM_NONE:
skb2->csum = ~csum_unfold(csum_ipv6_magic(&ip6h->saddr,
&ip6h->daddr,
skb2->len,
IPPROTO_ICMPV6, 0));
if (__skb_checksum_complete(skb2))
goto out;
}
err = 0;
BR_INPUT_SKB_CB(skb)->igmp = 1;
switch (icmp6_type) {
case ICMPV6_MGM_REPORT:
{
struct mld_msg *mld;
if (!pskb_may_pull(skb2, sizeof(*mld))) {
err = -EINVAL;
goto out;
}
mld = (struct mld_msg *)skb_transport_header(skb2);
BR_INPUT_SKB_CB(skb)->mrouters_only = 1;
err = br_ip6_multicast_add_group(br, port, &mld->mld_mca);
break;
}
case ICMPV6_MLD2_REPORT:
err = br_ip6_multicast_mld2_report(br, port, skb2);
break;
case ICMPV6_MGM_QUERY:
err = br_ip6_multicast_query(br, port, skb2);
break;
case ICMPV6_MGM_REDUCTION:
{
struct mld_msg *mld;
if (!pskb_may_pull(skb2, sizeof(*mld))) {
err = -EINVAL;
goto out;
}
mld = (struct mld_msg *)skb_transport_header(skb2);
br_ip6_multicast_leave_group(br, port, &mld->mld_mca);
}
}
out:
kfree_skb(skb2);
return err;
}
#endif
int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port,
struct sk_buff *skb)
{
BR_INPUT_SKB_CB(skb)->igmp = 0;
BR_INPUT_SKB_CB(skb)->mrouters_only = 0;
if (br->multicast_disabled)
return 0;
switch (skb->protocol) {
case htons(ETH_P_IP):
return br_multicast_ipv4_rcv(br, port, skb);
#if IS_ENABLED(CONFIG_IPV6)
case htons(ETH_P_IPV6):
return br_multicast_ipv6_rcv(br, port, skb);
#endif
}
return 0;
}
static void br_multicast_query_expired(unsigned long data)
{
struct net_bridge *br = (void *)data;
spin_lock(&br->multicast_lock);
if (br->multicast_startup_queries_sent <
br->multicast_startup_query_count)
br->multicast_startup_queries_sent++;
br_multicast_send_query(br, NULL, br->multicast_startup_queries_sent);
spin_unlock(&br->multicast_lock);
}
void br_multicast_init(struct net_bridge *br)
{
br->hash_elasticity = 4;
br->hash_max = 512;
br->multicast_router = 1;
br->multicast_last_member_count = 2;
br->multicast_startup_query_count = 2;
br->multicast_last_member_interval = HZ;
br->multicast_query_response_interval = 10 * HZ;
br->multicast_startup_query_interval = 125 * HZ / 4;
br->multicast_query_interval = 125 * HZ;
br->multicast_querier_interval = 255 * HZ;
br->multicast_membership_interval = 260 * HZ;
spin_lock_init(&br->multicast_lock);
setup_timer(&br->multicast_router_timer,
br_multicast_local_router_expired, 0);
setup_timer(&br->multicast_querier_timer,
br_multicast_local_router_expired, 0);
setup_timer(&br->multicast_query_timer, br_multicast_query_expired,
(unsigned long)br);
}
void br_multicast_open(struct net_bridge *br)
{
br->multicast_startup_queries_sent = 0;
if (br->multicast_disabled)
return;
mod_timer(&br->multicast_query_timer, jiffies);
}
void br_multicast_stop(struct net_bridge *br)
{
struct net_bridge_mdb_htable *mdb;
struct net_bridge_mdb_entry *mp;
struct hlist_node *p, *n;
u32 ver;
int i;
del_timer_sync(&br->multicast_router_timer);
del_timer_sync(&br->multicast_querier_timer);
del_timer_sync(&br->multicast_query_timer);
spin_lock_bh(&br->multicast_lock);
mdb = mlock_dereference(br->mdb, br);
if (!mdb)
goto out;
br->mdb = NULL;
ver = mdb->ver;
for (i = 0; i < mdb->max; i++) {
hlist_for_each_entry_safe(mp, p, n, &mdb->mhash[i],
hlist[ver]) {
del_timer(&mp->timer);
call_rcu_bh(&mp->rcu, br_multicast_free_group);
}
}
if (mdb->old) {
spin_unlock_bh(&br->multicast_lock);
rcu_barrier_bh();
spin_lock_bh(&br->multicast_lock);
WARN_ON(mdb->old);
}
mdb->old = mdb;
call_rcu_bh(&mdb->rcu, br_mdb_free);
out:
spin_unlock_bh(&br->multicast_lock);
}
int br_multicast_set_router(struct net_bridge *br, unsigned long val)
{
int err = -ENOENT;
spin_lock_bh(&br->multicast_lock);
if (!netif_running(br->dev))
goto unlock;
switch (val) {
case 0:
case 2:
del_timer(&br->multicast_router_timer);
/* fall through */
case 1:
br->multicast_router = val;
err = 0;
break;
default:
err = -EINVAL;
break;
}
unlock:
spin_unlock_bh(&br->multicast_lock);
return err;
}
int br_multicast_set_port_router(struct net_bridge_port *p, unsigned long val)
{
struct net_bridge *br = p->br;
int err = -ENOENT;
spin_lock(&br->multicast_lock);
if (!netif_running(br->dev) || p->state == BR_STATE_DISABLED)
goto unlock;
switch (val) {
case 0:
case 1:
case 2:
p->multicast_router = val;
err = 0;
if (val < 2 && !hlist_unhashed(&p->rlist))
hlist_del_init_rcu(&p->rlist);
if (val == 1)
break;
del_timer(&p->multicast_router_timer);
if (val == 0)
break;
br_multicast_add_router(br, p);
break;
default:
err = -EINVAL;
break;
}
unlock:
spin_unlock(&br->multicast_lock);
return err;
}
int br_multicast_toggle(struct net_bridge *br, unsigned long val)
{
struct net_bridge_port *port;
int err = 0;
struct net_bridge_mdb_htable *mdb;
spin_lock_bh(&br->multicast_lock);
if (br->multicast_disabled == !val)
goto unlock;
br->multicast_disabled = !val;
if (br->multicast_disabled)
goto unlock;
if (!netif_running(br->dev))
goto unlock;
mdb = mlock_dereference(br->mdb, br);
if (mdb) {
if (mdb->old) {
err = -EEXIST;
rollback:
br->multicast_disabled = !!val;
goto unlock;
}
err = br_mdb_rehash(&br->mdb, mdb->max,
br->hash_elasticity);
if (err)
goto rollback;
}
br_multicast_open(br);
list_for_each_entry(port, &br->port_list, list) {
if (port->state == BR_STATE_DISABLED ||
port->state == BR_STATE_BLOCKING)
continue;
__br_multicast_enable_port(port);
}
unlock:
spin_unlock_bh(&br->multicast_lock);
return err;
}
int br_multicast_set_hash_max(struct net_bridge *br, unsigned long val)
{
int err = -ENOENT;
u32 old;
struct net_bridge_mdb_htable *mdb;
spin_lock(&br->multicast_lock);
if (!netif_running(br->dev))
goto unlock;
err = -EINVAL;
if (!is_power_of_2(val))
goto unlock;
mdb = mlock_dereference(br->mdb, br);
if (mdb && val < mdb->size)
goto unlock;
err = 0;
old = br->hash_max;
br->hash_max = val;
if (mdb) {
if (mdb->old) {
err = -EEXIST;
rollback:
br->hash_max = old;
goto unlock;
}
err = br_mdb_rehash(&br->mdb, br->hash_max,
br->hash_elasticity);
if (err)
goto rollback;
}
unlock:
spin_unlock(&br->multicast_lock);
return err;
}