diff options
Diffstat (limited to 'net/bridge/br_multicast.c')
| -rw-r--r-- | net/bridge/br_multicast.c | 1076 |
1 files changed, 753 insertions, 323 deletions
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 326e599f83f..abfa0b65a11 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -11,6 +11,7 @@ */ #include <linux/err.h> +#include <linux/export.h> #include <linux/if_ether.h> #include <linux/igmp.h> #include <linux/jhash.h> @@ -23,37 +24,31 @@ #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/timer.h> +#include <linux/inetdevice.h> #include <net/ip.h> -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> #include <net/mld.h> -#include <net/addrconf.h> #include <net/ip6_checksum.h> +#include <net/addrconf.h> #endif #include "br_private.h" -#define mlock_dereference(X, br) \ - rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock)) - -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) -static inline int ipv6_is_local_multicast(const struct in6_addr *addr) -{ - if (ipv6_addr_is_multicast(addr) && - IPV6_ADDR_MC_SCOPE(addr) <= IPV6_ADDR_SCOPE_LINKLOCAL) - return 1; - return 0; -} -#endif +static void br_multicast_start_querier(struct net_bridge *br, + struct bridge_mcast_own_query *query); +unsigned int br_mdb_rehash_seq; static inline int br_ip_equal(const struct br_ip *a, const struct br_ip *b) { if (a->proto != b->proto) return 0; + if (a->vid != b->vid) + return 0; switch (a->proto) { case htons(ETH_P_IP): return a->u.ip4 == b->u.ip4; -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): return ipv6_addr_equal(&a->u.ip6, &b->u.ip6); #endif @@ -61,16 +56,19 @@ static inline int br_ip_equal(const struct br_ip *a, const struct br_ip *b) return 0; } -static inline int __br_ip4_hash(struct net_bridge_mdb_htable *mdb, __be32 ip) +static inline int __br_ip4_hash(struct net_bridge_mdb_htable *mdb, __be32 ip, + __u16 vid) { - return jhash_1word(mdb->secret, (__force u32)ip) & (mdb->max - 1); + return jhash_2words((__force u32)ip, vid, mdb->secret) & (mdb->max - 1); } -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) static inline int __br_ip6_hash(struct net_bridge_mdb_htable *mdb, - const struct in6_addr *ip) + const struct in6_addr *ip, + __u16 vid) { - return jhash2((__force u32 *)ip->s6_addr32, 4, mdb->secret) & (mdb->max - 1); + return jhash_2words(ipv6_addr_hash(ip), vid, + mdb->secret) & (mdb->max - 1); } #endif @@ -79,10 +77,10 @@ static inline int br_ip_hash(struct net_bridge_mdb_htable *mdb, { switch (ip->proto) { case htons(ETH_P_IP): - return __br_ip4_hash(mdb, ip->u.ip4); -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) + return __br_ip4_hash(mdb, ip->u.ip4, ip->vid); +#if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): - return __br_ip6_hash(mdb, &ip->u.ip6); + return __br_ip6_hash(mdb, &ip->u.ip6, ip->vid); #endif } return 0; @@ -92,9 +90,8 @@ 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]) { + hlist_for_each_entry_rcu(mp, &mdb->mhash[hash], hlist[mdb->ver]) { if (br_ip_equal(&mp->addr, dst)) return mp; } @@ -102,8 +99,8 @@ static struct net_bridge_mdb_entry *__br_mdb_ip_get( return NULL; } -static struct net_bridge_mdb_entry *br_mdb_ip_get( - struct net_bridge_mdb_htable *mdb, struct br_ip *dst) +struct net_bridge_mdb_entry *br_mdb_ip_get(struct net_bridge_mdb_htable *mdb, + struct br_ip *dst) { if (!mdb) return NULL; @@ -112,31 +109,34 @@ static struct net_bridge_mdb_entry *br_mdb_ip_get( } static struct net_bridge_mdb_entry *br_mdb_ip4_get( - struct net_bridge_mdb_htable *mdb, __be32 dst) + struct net_bridge_mdb_htable *mdb, __be32 dst, __u16 vid) { struct br_ip br_dst; br_dst.u.ip4 = dst; br_dst.proto = htons(ETH_P_IP); + br_dst.vid = vid; return br_mdb_ip_get(mdb, &br_dst); } -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#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 net_bridge_mdb_htable *mdb, const struct in6_addr *dst, + __u16 vid) { struct br_ip br_dst; - ipv6_addr_copy(&br_dst.u.ip6, dst); + br_dst.u.ip6 = *dst; br_dst.proto = htons(ETH_P_IPV6); + br_dst.vid = vid; 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 sk_buff *skb, u16 vid) { struct net_bridge_mdb_htable *mdb = rcu_dereference(br->mdb); struct br_ip ip; @@ -148,14 +148,15 @@ struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br, return NULL; ip.proto = skb->protocol; + ip.vid = vid; switch (skb->protocol) { case htons(ETH_P_IP): ip.u.ip4 = ip_hdr(skb)->daddr; break; -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): - ipv6_addr_copy(&ip.u.ip6, &ipv6_hdr(skb)->daddr); + ip.u.ip6 = ipv6_hdr(skb)->daddr; break; #endif default: @@ -181,13 +182,12 @@ static int br_mdb_copy(struct net_bridge_mdb_htable *new, 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_for_each_entry(mp, &old->mhash[i], hlist[old->ver]) hlist_add_head(&mp->hlist[new->ver], &new->mhash[br_ip_hash(new, &mp->addr)]); @@ -197,7 +197,7 @@ static int br_mdb_copy(struct net_bridge_mdb_htable *new, maxlen = 0; for (i = 0; i < new->max; i++) { len = 0; - hlist_for_each_entry(mp, p, &new->mhash[i], hlist[new->ver]) + hlist_for_each_entry(mp, &new->mhash[i], hlist[new->ver]) len++; if (len > maxlen) maxlen = len; @@ -206,7 +206,7 @@ static int br_mdb_copy(struct net_bridge_mdb_htable *new, return maxlen > elasticity ? -EINVAL : 0; } -static void br_multicast_free_pg(struct rcu_head *head) +void br_multicast_free_pg(struct rcu_head *head) { struct net_bridge_port_group *p = container_of(head, struct net_bridge_port_group, rcu); @@ -232,8 +232,7 @@ static void br_multicast_group_expired(unsigned long data) if (!netif_running(br->dev) || timer_pending(&mp->timer)) goto out; - if (!hlist_unhashed(&mp->mglist)) - hlist_del_init(&mp->mglist); + mp->mglist = false; if (mp->ports) goto out; @@ -243,7 +242,6 @@ static void br_multicast_group_expired(unsigned long data) hlist_del_rcu(&mp->hlist[mdb->ver]); mdb->size--; - del_timer(&mp->query_timer); call_rcu_bh(&mp->rcu, br_multicast_free_group); out: @@ -273,10 +271,9 @@ static void br_multicast_del_pg(struct net_bridge *br, rcu_assign_pointer(*pp, p->next); hlist_del_init(&p->mglist); del_timer(&p->timer); - del_timer(&p->query_timer); call_rcu_bh(&p->rcu, br_multicast_free_pg); - if (!mp->ports && hlist_unhashed(&mp->mglist) && + if (!mp->ports && !mp->mglist && netif_running(br->dev)) mod_timer(&mp->timer, jiffies); @@ -293,7 +290,7 @@ static void br_multicast_port_group_expired(unsigned long data) spin_lock(&br->multicast_lock); if (!netif_running(br->dev) || timer_pending(&pg->timer) || - hlist_unhashed(&pg->mglist)) + hlist_unhashed(&pg->mglist) || pg->state & MDB_PERMANENT) goto out; br_multicast_del_pg(br, pg); @@ -340,6 +337,7 @@ static int br_mdb_rehash(struct net_bridge_mdb_htable __rcu **mdbp, int max, return err; } + br_mdb_rehash_seq++; call_rcu_bh(&mdb->rcu, br_mdb_free); out: @@ -366,7 +364,7 @@ static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br, skb_reset_mac_header(skb); eth = eth_hdr(skb); - memcpy(eth->h_source, br->dev->dev_addr, 6); + ether_addr_copy(eth->h_source, br->dev->dev_addr); eth->h_dest[0] = 1; eth->h_dest[1] = 0; eth->h_dest[2] = 0x5e; @@ -387,7 +385,8 @@ static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br, iph->frag_off = htons(IP_DF); iph->ttl = 1; iph->protocol = IPPROTO_IGMP; - iph->saddr = 0; + iph->saddr = br->multicast_query_use_ifaddr ? + inet_select_addr(br->dev, 0, RT_SCOPE_LINK) : 0; iph->daddr = htonl(INADDR_ALLHOSTS_GROUP); ((u8 *)&iph[1])[0] = IPOPT_RA; ((u8 *)&iph[1])[1] = 4; @@ -413,9 +412,9 @@ out: return skb; } -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, - struct in6_addr *group) + const struct in6_addr *group) { struct sk_buff *skb; struct ipv6hdr *ip6h; @@ -435,8 +434,7 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, skb_reset_mac_header(skb); eth = eth_hdr(skb); - memcpy(eth->h_source, br->dev->dev_addr, 6); - ipv6_eth_mc_map(group, eth->h_dest); + ether_addr_copy(eth->h_source, br->dev->dev_addr); eth->h_proto = htons(ETH_P_IPV6); skb_put(skb, sizeof(*eth)); @@ -445,11 +443,16 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, ip6h = ipv6_hdr(skb); *(__force __be32 *)ip6h = htonl(0x60000000); - ip6h->payload_len = 8 + sizeof(*mldq); + ip6h->payload_len = htons(8 + sizeof(*mldq)); ip6h->nexthdr = IPPROTO_HOPOPTS; ip6h->hop_limit = 1; - ipv6_addr_set(&ip6h->saddr, 0, 0, 0, 0); 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 */ @@ -458,8 +461,8 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, 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 */ + hopopt[6] = IPV6_TLV_PAD1; /* Pad1 */ + hopopt[7] = IPV6_TLV_PAD1; /* Pad1 */ skb_put(skb, sizeof(*ip6h) + 8); @@ -467,15 +470,16 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, 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; + interval = ipv6_addr_any(group) ? + br->multicast_query_response_interval : + br->multicast_last_member_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; - ipv6_addr_copy(&mldq->mld_mca, group); + mldq->mld_mca = *group; /* checksum */ mldq->mld_cksum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, @@ -497,7 +501,7 @@ static struct sk_buff *br_multicast_alloc_query(struct net_bridge *br, switch (addr->proto) { case htons(ETH_P_IP): return br_ip4_multicast_alloc_query(br, addr->u.ip4); -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): return br_ip6_multicast_alloc_query(br, &addr->u.ip6); #endif @@ -505,88 +509,19 @@ static struct sk_buff *br_multicast_alloc_query(struct net_bridge *br, return NULL; } -static void br_multicast_send_group_query(struct net_bridge_mdb_entry *mp) -{ - struct net_bridge *br = mp->br; - struct sk_buff *skb; - - skb = br_multicast_alloc_query(br, &mp->addr); - if (!skb) - goto timer; - - netif_rx(skb); - -timer: - if (++mp->queries_sent < br->multicast_last_member_count) - mod_timer(&mp->query_timer, - jiffies + br->multicast_last_member_interval); -} - -static void br_multicast_group_query_expired(unsigned long data) -{ - struct net_bridge_mdb_entry *mp = (void *)data; - struct net_bridge *br = mp->br; - - spin_lock(&br->multicast_lock); - if (!netif_running(br->dev) || hlist_unhashed(&mp->mglist) || - mp->queries_sent >= br->multicast_last_member_count) - goto out; - - br_multicast_send_group_query(mp); - -out: - spin_unlock(&br->multicast_lock); -} - -static void br_multicast_send_port_group_query(struct net_bridge_port_group *pg) -{ - struct net_bridge_port *port = pg->port; - struct net_bridge *br = port->br; - struct sk_buff *skb; - - skb = br_multicast_alloc_query(br, &pg->addr); - if (!skb) - goto timer; - - br_deliver(port, skb); - -timer: - if (++pg->queries_sent < br->multicast_last_member_count) - mod_timer(&pg->query_timer, - jiffies + br->multicast_last_member_interval); -} - -static void br_multicast_port_group_query_expired(unsigned long data) -{ - struct net_bridge_port_group *pg = (void *)data; - struct net_bridge_port *port = pg->port; - struct net_bridge *br = port->br; - - spin_lock(&br->multicast_lock); - if (!netif_running(br->dev) || hlist_unhashed(&pg->mglist) || - pg->queries_sent >= br->multicast_last_member_count) - goto out; - - br_multicast_send_port_group_query(pg); - -out: - spin_unlock(&br->multicast_lock); -} - 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; + unsigned int count = 0; + unsigned int max; int elasticity; int err; mdb = rcu_dereference_protected(br->mdb, 1); - hlist_for_each_entry(mp, p, &mdb->mhash[hash], hlist[mdb->ver]) { + hlist_for_each_entry(mp, &mdb->mhash[hash], hlist[mdb->ver]) { count++; if (unlikely(br_ip_equal(group, &mp->addr))) return mp; @@ -606,10 +541,11 @@ static struct net_bridge_mdb_entry *br_multicast_get_group( 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); + if (unlikely(max > br->hash_max)) { + br_warn(br, "Multicast hash table maximum of %d " + "reached, disabling snooping: %s\n", + br->hash_max, + port ? port->dev->name : br->dev->name); err = -E2BIG; disable: br->multicast_disabled = 1; @@ -647,18 +583,19 @@ 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_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) { - if (br_mdb_rehash(&br->mdb, BR_HASH_SIZE, 0)) - return NULL; + err = br_mdb_rehash(&br->mdb, BR_HASH_SIZE, 0); + if (err) + return ERR_PTR(err); goto rehash; } @@ -680,14 +617,12 @@ rehash: mp = kzalloc(sizeof(*mp), GFP_ATOMIC); if (unlikely(!mp)) - goto out; + return ERR_PTR(-ENOMEM); mp->br = br; mp->addr = *group; setup_timer(&mp->timer, br_multicast_group_expired, (unsigned long)mp); - setup_timer(&mp->query_timer, br_multicast_group_query_expired, - (unsigned long)mp); hlist_add_head_rcu(&mp->hlist[mdb->ver], &mdb->mhash[hash]); mdb->size++; @@ -696,6 +631,28 @@ out: return mp; } +struct net_bridge_port_group *br_multicast_new_port_group( + struct net_bridge_port *port, + struct br_ip *group, + struct net_bridge_port_group __rcu *next, + unsigned char state) +{ + struct net_bridge_port_group *p; + + p = kzalloc(sizeof(*p), GFP_ATOMIC); + if (unlikely(!p)) + return NULL; + + p->addr = *group; + p->port = port; + p->state = state; + rcu_assign_pointer(p->next, next); + hlist_add_head(&p->mglist, &port->mglist); + setup_timer(&p->timer, br_multicast_port_group_expired, + (unsigned long)p); + return p; +} + static int br_multicast_add_group(struct net_bridge *br, struct net_bridge_port *port, struct br_ip *group) @@ -713,11 +670,11 @@ static int br_multicast_add_group(struct net_bridge *br, mp = br_multicast_new_group(br, port, group); err = PTR_ERR(mp); - if (unlikely(IS_ERR(mp) || !mp)) + if (IS_ERR(mp)) goto err; if (!port) { - hlist_add_head(&mp->mglist, &br->mglist); + mp->mglist = true; mod_timer(&mp->timer, now + br->multicast_membership_interval); goto out; } @@ -731,21 +688,11 @@ static int br_multicast_add_group(struct net_bridge *br, break; } - p = kzalloc(sizeof(*p), GFP_ATOMIC); - err = -ENOMEM; + p = br_multicast_new_port_group(port, group, *pp, MDB_TEMPORARY); 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); - setup_timer(&p->query_timer, br_multicast_port_group_query_expired, - (unsigned long)p); - rcu_assign_pointer(*pp, p); + br_mdb_notify(br->dev, port, group, RTM_NEWMDB); found: mod_timer(&p->timer, now + br->multicast_membership_interval); @@ -759,7 +706,8 @@ err: static int br_ip4_multicast_add_group(struct net_bridge *br, struct net_bridge_port *port, - __be32 group) + __be32 group, + __u16 vid) { struct br_ip br_group; @@ -768,22 +716,25 @@ static int br_ip4_multicast_add_group(struct net_bridge *br, br_group.u.ip4 = group; br_group.proto = htons(ETH_P_IP); + br_group.vid = vid; return br_multicast_add_group(br, port, &br_group); } -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#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) + const struct in6_addr *group, + __u16 vid) { struct br_ip br_group; - if (ipv6_is_local_multicast(group)) + if (ipv6_addr_is_ll_all_nodes(group)) return 0; - ipv6_addr_copy(&br_group.u.ip6, group); - br_group.proto = htons(ETH_P_IP); + br_group.u.ip6 = *group; + br_group.proto = htons(ETH_P_IPV6); + br_group.vid = vid; return br_multicast_add_group(br, port, &br_group); } @@ -810,6 +761,47 @@ static void br_multicast_local_router_expired(unsigned long data) { } +static void br_multicast_querier_expired(struct net_bridge *br, + struct bridge_mcast_own_query *query) +{ + spin_lock(&br->multicast_lock); + if (!netif_running(br->dev) || br->multicast_disabled) + goto out; + + br_multicast_start_querier(br, query); + +out: + spin_unlock(&br->multicast_lock); +} + +static void br_ip4_multicast_querier_expired(unsigned long data) +{ + struct net_bridge *br = (void *)data; + + br_multicast_querier_expired(br, &br->ip4_own_query); +} + +#if IS_ENABLED(CONFIG_IPV6) +static void br_ip6_multicast_querier_expired(unsigned long data) +{ + struct net_bridge *br = (void *)data; + + br_multicast_querier_expired(br, &br->ip6_own_query); +} +#endif + +static void br_multicast_select_own_querier(struct net_bridge *br, + struct br_ip *ip, + struct sk_buff *skb) +{ + if (ip->proto == htons(ETH_P_IP)) + br->ip4_querier.addr.u.ip4 = ip_hdr(skb)->saddr; +#if IS_ENABLED(CONFIG_IPV6) + else + br->ip6_querier.addr.u.ip6 = ipv6_hdr(skb)->saddr; +#endif +} + static void __br_multicast_send_query(struct net_bridge *br, struct net_bridge_port *port, struct br_ip *ip) @@ -825,41 +817,53 @@ static void __br_multicast_send_query(struct net_bridge *br, skb->dev = port->dev; NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, skb, NULL, skb->dev, dev_queue_xmit); - } else + } else { + br_multicast_select_own_querier(br, ip, skb); netif_rx(skb); + } } static void br_multicast_send_query(struct net_bridge *br, - struct net_bridge_port *port, u32 sent) + struct net_bridge_port *port, + struct bridge_mcast_own_query *own_query) { unsigned long time; struct br_ip br_group; + struct bridge_mcast_other_query *other_query = NULL; if (!netif_running(br->dev) || br->multicast_disabled || - timer_pending(&br->multicast_querier_timer)) + !br->multicast_querier) 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 (port ? (own_query == &port->ip4_own_query) : + (own_query == &br->ip4_own_query)) { + other_query = &br->ip4_other_query; + br_group.proto = htons(ETH_P_IP); +#if IS_ENABLED(CONFIG_IPV6) + } else { + other_query = &br->ip6_other_query; + br_group.proto = htons(ETH_P_IPV6); +#endif + } + + if (!other_query || timer_pending(&other_query->timer)) + return; -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) - 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 ? + time += own_query->startup_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); + mod_timer(&own_query->timer, time); } -static void br_multicast_port_query_expired(unsigned long data) +static void +br_multicast_port_query_expired(struct net_bridge_port *port, + struct bridge_mcast_own_query *query) { - struct net_bridge_port *port = (void *)data; struct net_bridge *br = port->br; spin_lock(&br->multicast_lock); @@ -867,25 +871,43 @@ static void br_multicast_port_query_expired(unsigned long data) port->state == BR_STATE_BLOCKING) goto out; - if (port->multicast_startup_queries_sent < - br->multicast_startup_query_count) - port->multicast_startup_queries_sent++; + if (query->startup_sent < br->multicast_startup_query_count) + query->startup_sent++; - br_multicast_send_query(port->br, port, - port->multicast_startup_queries_sent); + br_multicast_send_query(port->br, port, query); out: spin_unlock(&br->multicast_lock); } +static void br_ip4_multicast_port_query_expired(unsigned long data) +{ + struct net_bridge_port *port = (void *)data; + + br_multicast_port_query_expired(port, &port->ip4_own_query); +} + +#if IS_ENABLED(CONFIG_IPV6) +static void br_ip6_multicast_port_query_expired(unsigned long data) +{ + struct net_bridge_port *port = (void *)data; + + br_multicast_port_query_expired(port, &port->ip6_own_query); +} +#endif + 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); + setup_timer(&port->ip4_own_query.timer, + br_ip4_multicast_port_query_expired, (unsigned long)port); +#if IS_ENABLED(CONFIG_IPV6) + setup_timer(&port->ip6_own_query.timer, + br_ip6_multicast_port_query_expired, (unsigned long)port); +#endif } void br_multicast_del_port(struct net_bridge_port *port) @@ -893,13 +915,13 @@ 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) +static void br_multicast_enable(struct bridge_mcast_own_query *query) { - port->multicast_startup_queries_sent = 0; + query->startup_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); + if (try_to_del_timer_sync(&query->timer) >= 0 || + del_timer(&query->timer)) + mod_timer(&query->timer, jiffies); } void br_multicast_enable_port(struct net_bridge_port *port) @@ -910,7 +932,10 @@ void br_multicast_enable_port(struct net_bridge_port *port) if (br->multicast_disabled || !netif_running(br->dev)) goto out; - __br_multicast_enable_port(port); + br_multicast_enable(&port->ip4_own_query); +#if IS_ENABLED(CONFIG_IPV6) + br_multicast_enable(&port->ip6_own_query); +#endif out: spin_unlock(&br->multicast_lock); @@ -920,22 +945,26 @@ 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; + struct hlist_node *n; spin_lock(&br->multicast_lock); - hlist_for_each_entry_safe(pg, p, n, &port->mglist, mglist) + hlist_for_each_entry_safe(pg, 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); + del_timer(&port->ip4_own_query.timer); +#if IS_ENABLED(CONFIG_IPV6) + del_timer(&port->ip6_own_query.timer); +#endif 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 sk_buff *skb, + u16 vid) { struct igmpv3_report *ih; struct igmpv3_grec *grec; @@ -980,7 +1009,7 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br, continue; } - err = br_ip4_multicast_add_group(br, port, group); + err = br_ip4_multicast_add_group(br, port, group, vid); if (err) break; } @@ -988,10 +1017,11 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br, return err; } -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#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 sk_buff *skb, + u16 vid) { struct icmp6hdr *icmp6h; struct mld2_grec *grec; @@ -1012,18 +1042,19 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, nsrcs = skb_header_pointer(skb, len + offsetof(struct mld2_grec, - grec_mca), + grec_nsrcs), sizeof(_nsrcs), &_nsrcs); if (!nsrcs) return -EINVAL; if (!pskb_may_pull(skb, len + sizeof(*grec) + - sizeof(struct in6_addr) * (*nsrcs))) + sizeof(struct in6_addr) * ntohs(*nsrcs))) return -EINVAL; grec = (struct mld2_grec *)(skb->data + len); - len += sizeof(*grec) + sizeof(struct in6_addr) * (*nsrcs); + len += sizeof(*grec) + + sizeof(struct in6_addr) * ntohs(*nsrcs); /* We treat these as MLDv1 reports for now. */ switch (grec->grec_type) { @@ -1039,7 +1070,8 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, continue; } - err = br_ip6_multicast_add_group(br, port, &grec->grec_mca); + err = br_ip6_multicast_add_group(br, port, &grec->grec_mca, + vid); if (!err) break; } @@ -1048,8 +1080,84 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, } #endif +static bool br_ip4_multicast_select_querier(struct net_bridge *br, + struct net_bridge_port *port, + __be32 saddr) +{ + if (!timer_pending(&br->ip4_own_query.timer) && + !timer_pending(&br->ip4_other_query.timer)) + goto update; + + if (!br->ip4_querier.addr.u.ip4) + goto update; + + if (ntohl(saddr) <= ntohl(br->ip4_querier.addr.u.ip4)) + goto update; + + return false; + +update: + br->ip4_querier.addr.u.ip4 = saddr; + + /* update protected by general multicast_lock by caller */ + rcu_assign_pointer(br->ip4_querier.port, port); + + return true; +} + +#if IS_ENABLED(CONFIG_IPV6) +static bool br_ip6_multicast_select_querier(struct net_bridge *br, + struct net_bridge_port *port, + struct in6_addr *saddr) +{ + if (!timer_pending(&br->ip6_own_query.timer) && + !timer_pending(&br->ip6_other_query.timer)) + goto update; + + if (ipv6_addr_cmp(saddr, &br->ip6_querier.addr.u.ip6) <= 0) + goto update; + + return false; + +update: + br->ip6_querier.addr.u.ip6 = *saddr; + + /* update protected by general multicast_lock by caller */ + rcu_assign_pointer(br->ip6_querier.port, port); + + return true; +} +#endif + +static bool br_multicast_select_querier(struct net_bridge *br, + struct net_bridge_port *port, + struct br_ip *saddr) +{ + switch (saddr->proto) { + case htons(ETH_P_IP): + return br_ip4_multicast_select_querier(br, port, saddr->u.ip4); +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): + return br_ip6_multicast_select_querier(br, port, &saddr->u.ip6); +#endif + } + + return false; +} + +static void +br_multicast_update_query_timer(struct net_bridge *br, + struct bridge_mcast_other_query *query, + unsigned long max_delay) +{ + if (!timer_pending(&query->timer)) + query->delay_time = jiffies + max_delay; + + mod_timer(&query->timer, jiffies + br->multicast_querier_interval); +} + /* - * Add port to rotuer_list + * Add port to router_list * list is maintained ordered by pointer value * and locked by br->multicast_lock and RCU */ @@ -1057,12 +1165,12 @@ 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; + struct hlist_node *slot = NULL; - hlist_for_each_entry(p, n, &br->router_list, rlist) { + hlist_for_each_entry(p, &br->router_list, rlist) { if ((unsigned long) port >= (unsigned long) p) break; - slot = n; + slot = &p->rlist; } if (slot) @@ -1098,27 +1206,29 @@ timer: static void br_multicast_query_received(struct net_bridge *br, struct net_bridge_port *port, - int saddr) + struct bridge_mcast_other_query *query, + struct br_ip *saddr, + unsigned long max_delay) { - if (saddr) - mod_timer(&br->multicast_querier_timer, - jiffies + br->multicast_querier_interval); - else if (timer_pending(&br->multicast_querier_timer)) + if (!br_multicast_select_querier(br, port, saddr)) return; + br_multicast_update_query_timer(br, query, max_delay); 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) + struct sk_buff *skb, + u16 vid) { - struct iphdr *iph = ip_hdr(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; + struct br_ip saddr; unsigned long max_delay; unsigned long now = jiffies; __be32 group; @@ -1129,8 +1239,6 @@ static int br_ip4_multicast_query(struct net_bridge *br, (port && port->state == BR_STATE_DISABLED)) goto out; - br_multicast_query_received(br, port, !!iph->saddr); - group = ih->group; if (skb->len == sizeof(*ih)) { @@ -1154,16 +1262,30 @@ static int br_ip4_multicast_query(struct net_bridge *br, IGMPV3_MRC(ih3->code) * (HZ / IGMP_TIMER_SCALE) : 1; } - if (!group) + /* RFC2236+RFC3376 (IGMPv2+IGMPv3) require the multicast link layer + * all-systems destination addresses (224.0.0.1) for general queries + */ + if (!group && iph->daddr != htonl(INADDR_ALLHOSTS_GROUP)) { + err = -EINVAL; goto out; + } + + if (!group) { + saddr.proto = htons(ETH_P_IP); + saddr.u.ip4 = iph->saddr; - mp = br_mdb_ip4_get(mlock_dereference(br->mdb, br), group); + br_multicast_query_received(br, port, &br->ip4_other_query, + &saddr, max_delay); + goto out; + } + + mp = br_mdb_ip4_get(mlock_dereference(br->mdb, br), group, vid); if (!mp) goto out; max_delay *= br->multicast_last_member_count; - if (!hlist_unhashed(&mp->mglist) && + if (mp->mglist && (timer_pending(&mp->timer) ? time_after(mp->timer.expires, now + max_delay) : try_to_del_timer_sync(&mp->timer) >= 0)) @@ -1175,7 +1297,7 @@ static int br_ip4_multicast_query(struct net_bridge *br, if (timer_pending(&p->timer) ? time_after(p->timer.expires, now + max_delay) : try_to_del_timer_sync(&p->timer) >= 0) - mod_timer(&mp->timer, now + max_delay); + mod_timer(&p->timer, now + max_delay); } out: @@ -1183,20 +1305,23 @@ out: return err; } -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) static int br_ip6_multicast_query(struct net_bridge *br, struct net_bridge_port *port, - struct sk_buff *skb) + struct sk_buff *skb, + u16 vid) { - struct ipv6hdr *ip6h = ipv6_hdr(skb); - struct mld_msg *mld = (struct mld_msg *) icmp6_hdr(skb); + const struct ipv6hdr *ip6h = ipv6_hdr(skb); + struct mld_msg *mld; struct net_bridge_mdb_entry *mp; struct mld2_query *mld2q; struct net_bridge_port_group *p; struct net_bridge_port_group __rcu **pp; + struct br_ip saddr; unsigned long max_delay; unsigned long now = jiffies; - struct in6_addr *group = NULL; + const struct in6_addr *group = NULL; + bool is_general_query; int err = 0; spin_lock(&br->multicast_lock); @@ -1204,7 +1329,11 @@ static int br_ip6_multicast_query(struct net_bridge *br, (port && port->state == BR_STATE_DISABLED)) goto out; - br_multicast_query_received(br, port, !ipv6_addr_any(&ip6h->saddr)); + /* RFC2710+RFC3810 (MLDv1+MLDv2) require link-local source addresses */ + if (!(ipv6_addr_type(&ip6h->saddr) & IPV6_ADDR_LINKLOCAL)) { + err = -EINVAL; + goto out; + } if (skb->len == sizeof(*mld)) { if (!pskb_may_pull(skb, sizeof(*mld))) { @@ -1212,10 +1341,10 @@ static int br_ip6_multicast_query(struct net_bridge *br, goto out; } mld = (struct mld_msg *) icmp6_hdr(skb); - max_delay = msecs_to_jiffies(htons(mld->mld_maxdelay)); + max_delay = msecs_to_jiffies(ntohs(mld->mld_maxdelay)); if (max_delay) group = &mld->mld_mca; - } else if (skb->len >= sizeof(*mld2q)) { + } else { if (!pskb_may_pull(skb, sizeof(*mld2q))) { err = -EINVAL; goto out; @@ -1223,18 +1352,37 @@ static int br_ip6_multicast_query(struct net_bridge *br, 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; + + max_delay = max(msecs_to_jiffies(mldv2_mrc(mld2q)), 1UL); + } + + is_general_query = group && ipv6_addr_any(group); + + /* RFC2710+RFC3810 (MLDv1+MLDv2) require the multicast link layer + * all-nodes destination address (ff02::1) for general queries + */ + if (is_general_query && !ipv6_addr_is_ll_all_nodes(&ip6h->daddr)) { + err = -EINVAL; + goto out; } - if (!group) + if (is_general_query) { + saddr.proto = htons(ETH_P_IPV6); + saddr.u.ip6 = ip6h->saddr; + + br_multicast_query_received(br, port, &br->ip6_other_query, + &saddr, max_delay); + goto out; + } else if (!group) { goto out; + } - mp = br_mdb_ip6_get(mlock_dereference(br->mdb, br), group); + mp = br_mdb_ip6_get(mlock_dereference(br->mdb, br), group, vid); if (!mp) goto out; max_delay *= br->multicast_last_member_count; - if (!hlist_unhashed(&mp->mglist) && + if (mp->mglist && (timer_pending(&mp->timer) ? time_after(mp->timer.expires, now + max_delay) : try_to_del_timer_sync(&mp->timer) >= 0)) @@ -1246,7 +1394,7 @@ static int br_ip6_multicast_query(struct net_bridge *br, if (timer_pending(&p->timer) ? time_after(p->timer.expires, now + max_delay) : try_to_del_timer_sync(&p->timer) >= 0) - mod_timer(&mp->timer, now + max_delay); + mod_timer(&p->timer, now + max_delay); } out: @@ -1255,9 +1403,12 @@ out: } #endif -static void br_multicast_leave_group(struct net_bridge *br, - struct net_bridge_port *port, - struct br_ip *group) +static void +br_multicast_leave_group(struct net_bridge *br, + struct net_bridge_port *port, + struct br_ip *group, + struct bridge_mcast_other_query *other_query, + struct bridge_mcast_own_query *own_query) { struct net_bridge_mdb_htable *mdb; struct net_bridge_mdb_entry *mp; @@ -1268,7 +1419,7 @@ static void br_multicast_leave_group(struct net_bridge *br, spin_lock(&br->multicast_lock); if (!netif_running(br->dev) || (port && port->state == BR_STATE_DISABLED) || - timer_pending(&br->multicast_querier_timer)) + timer_pending(&other_query->timer)) goto out; mdb = mlock_dereference(br->mdb, br); @@ -1276,19 +1427,63 @@ static void br_multicast_leave_group(struct net_bridge *br, if (!mp) goto out; + if (br->multicast_querier) { + __br_multicast_send_query(br, port, &mp->addr); + + time = jiffies + br->multicast_last_member_count * + br->multicast_last_member_interval; + + mod_timer(&own_query->timer, time); + + 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; + } + } + + if (port && (port->flags & BR_MULTICAST_FAST_LEAVE)) { + struct net_bridge_port_group __rcu **pp; + + for (pp = &mp->ports; + (p = mlock_dereference(*pp, br)) != NULL; + pp = &p->next) { + if (p->port != port) + 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); + br_mdb_notify(br->dev, port, group, RTM_DELMDB); + + if (!mp->ports && !mp->mglist && + netif_running(br->dev)) + mod_timer(&mp->timer, jiffies); + } + goto out; + } + now = jiffies; time = now + br->multicast_last_member_count * br->multicast_last_member_interval; if (!port) { - if (!hlist_unhashed(&mp->mglist) && + 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); - - mp->queries_sent = 0; - mod_timer(&mp->query_timer, now); } goto out; @@ -1305,59 +1500,68 @@ static void br_multicast_leave_group(struct net_bridge *br, time_after(p->timer.expires, time) : try_to_del_timer_sync(&p->timer) >= 0)) { mod_timer(&p->timer, time); - - p->queries_sent = 0; - mod_timer(&p->query_timer, now); } 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) + __be32 group, + __u16 vid) { struct br_ip br_group; + struct bridge_mcast_own_query *own_query; if (ipv4_is_local_multicast(group)) return; + own_query = port ? &port->ip4_own_query : &br->ip4_own_query; + br_group.u.ip4 = group; br_group.proto = htons(ETH_P_IP); + br_group.vid = vid; - br_multicast_leave_group(br, port, &br_group); + br_multicast_leave_group(br, port, &br_group, &br->ip4_other_query, + own_query); } -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#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) + const struct in6_addr *group, + __u16 vid) { struct br_ip br_group; + struct bridge_mcast_own_query *own_query; - if (ipv6_is_local_multicast(group)) + if (ipv6_addr_is_ll_all_nodes(group)) return; - ipv6_addr_copy(&br_group.u.ip6, group); + own_query = port ? &port->ip6_own_query : &br->ip6_own_query; + + br_group.u.ip6 = *group; br_group.proto = htons(ETH_P_IPV6); + br_group.vid = vid; - br_multicast_leave_group(br, port, &br_group); + br_multicast_leave_group(br, port, &br_group, &br->ip6_other_query, + own_query); } #endif static int br_multicast_ipv4_rcv(struct net_bridge *br, struct net_bridge_port *port, - struct sk_buff *skb) + struct sk_buff *skb, + u16 vid) { struct sk_buff *skb2 = skb; - struct iphdr *iph; + const struct iphdr *iph; struct igmphdr *ih; - unsigned len; - unsigned offset; + unsigned int len; + unsigned int offset; int err; /* We treat OOM as packet loss for now. */ @@ -1377,8 +1581,11 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl))) return -EINVAL; - if (iph->protocol != IPPROTO_IGMP) + if (iph->protocol != IPPROTO_IGMP) { + if (!ipv4_is_local_multicast(iph->daddr)) + BR_INPUT_SKB_CB(skb)->mrouters_only = 1; return 0; + } len = ntohs(iph->tot_len); if (skb->len < len || len < ip_hdrlen(skb)) @@ -1422,17 +1629,17 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, switch (ih->type) { case IGMP_HOST_MEMBERSHIP_REPORT: case IGMPV2_HOST_MEMBERSHIP_REPORT: - BR_INPUT_SKB_CB(skb2)->mrouters_only = 1; - err = br_ip4_multicast_add_group(br, port, ih->group); + BR_INPUT_SKB_CB(skb)->mrouters_only = 1; + err = br_ip4_multicast_add_group(br, port, ih->group, vid); break; case IGMPV3_HOST_MEMBERSHIP_REPORT: - err = br_ip4_multicast_igmp3_report(br, port, skb2); + err = br_ip4_multicast_igmp3_report(br, port, skb2, vid); break; case IGMP_HOST_MEMBERSHIP_QUERY: - err = br_ip4_multicast_query(br, port, skb2); + err = br_ip4_multicast_query(br, port, skb2, vid); break; case IGMP_HOST_LEAVE_MESSAGE: - br_ip4_multicast_leave_group(br, port, ih->group); + br_ip4_multicast_leave_group(br, port, ih->group, vid); break; } @@ -1444,16 +1651,18 @@ err_out: return err; } -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#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 *skb, + u16 vid) { - struct sk_buff *skb2 = skb; - struct ipv6hdr *ip6h; - struct icmp6hdr *icmp6h; + struct sk_buff *skb2; + const struct ipv6hdr *ip6h; + u8 icmp6_type; u8 nexthdr; - unsigned len; + __be16 frag_off; + unsigned int len; int offset; int err; @@ -1468,17 +1677,23 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, * - MLD has always Router Alert hop-by-hop option * - But we do not support jumbrograms. */ - if (ip6h->version != 6 || - ip6h->nexthdr != IPPROTO_HOPOPTS || + if (ip6h->version != 6) + return 0; + + /* Prevent flooding this packet if there is no listener present */ + if (!ipv6_addr_is_ll_all_nodes(&ip6h->daddr)) + BR_INPUT_SKB_CB(skb)->mrouters_only = 1; + + if (ip6h->nexthdr != IPPROTO_HOPOPTS || ip6h->payload_len == 0) return 0; - len = ntohs(ip6h->payload_len); + len = ntohs(ip6h->payload_len) + sizeof(*ip6h); if (skb->len < len) return -EINVAL; nexthdr = ip6h->nexthdr; - offset = ipv6_skip_exthdr(skb, sizeof(*ip6h), &nexthdr); + offset = ipv6_skip_exthdr(skb, sizeof(*ip6h), &nexthdr, &frag_off); if (offset < 0 || nexthdr != IPPROTO_ICMPV6) return 0; @@ -1488,18 +1703,20 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, 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)); - err = -EINVAL; - if (!pskb_may_pull(skb2, sizeof(*icmp6h))) - goto out; - - icmp6h = icmp6_hdr(skb2); + icmp6_type = icmp6_hdr(skb2)->icmp6_type; - switch (icmp6h->icmp6_type) { + switch (icmp6_type) { case ICMPV6_MGM_QUERY: case ICMPV6_MGM_REPORT: case ICMPV6_MGM_REDUCTION: @@ -1515,16 +1732,23 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, 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_fold(skb2->csum)) + if (!csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, skb2->len, + IPPROTO_ICMPV6, skb2->csum)) break; /*FALLTHROUGH*/ case CHECKSUM_NONE: - skb2->csum = 0; - if (skb_checksum_complete(skb2)) + skb2->csum = ~csum_unfold(csum_ipv6_magic(&ip6h->saddr, + &ip6h->daddr, + skb2->len, + IPPROTO_ICMPV6, 0)); + if (__skb_checksum_complete(skb2)) goto out; } @@ -1532,37 +1756,45 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, BR_INPUT_SKB_CB(skb)->igmp = 1; - switch (icmp6h->icmp6_type) { + switch (icmp6_type) { case ICMPV6_MGM_REPORT: { - struct mld_msg *mld = (struct mld_msg *)icmp6h; - BR_INPUT_SKB_CB(skb2)->mrouters_only = 1; - err = br_ip6_multicast_add_group(br, port, &mld->mld_mca); + 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, vid); break; } case ICMPV6_MLD2_REPORT: - err = br_ip6_multicast_mld2_report(br, port, skb2); + err = br_ip6_multicast_mld2_report(br, port, skb2, vid); break; case ICMPV6_MGM_QUERY: - err = br_ip6_multicast_query(br, port, skb2); + err = br_ip6_multicast_query(br, port, skb2, vid); break; case ICMPV6_MGM_REDUCTION: { - struct mld_msg *mld = (struct mld_msg *)icmp6h; - br_ip6_multicast_leave_group(br, port, &mld->mld_mca); + 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, vid); } } out: - __skb_push(skb2, offset); - if (skb2 != skb) - kfree_skb(skb2); + kfree_skb(skb2); return err; } #endif int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port, - struct sk_buff *skb) + struct sk_buff *skb, u16 vid) { BR_INPUT_SKB_CB(skb)->igmp = 0; BR_INPUT_SKB_CB(skb)->mrouters_only = 0; @@ -1572,29 +1804,44 @@ int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port, switch (skb->protocol) { case htons(ETH_P_IP): - return br_multicast_ipv4_rcv(br, port, skb); -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) + return br_multicast_ipv4_rcv(br, port, skb, vid); +#if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): - return br_multicast_ipv6_rcv(br, port, skb); + return br_multicast_ipv6_rcv(br, port, skb, vid); #endif } return 0; } -static void br_multicast_query_expired(unsigned long data) +static void br_multicast_query_expired(struct net_bridge *br, + struct bridge_mcast_own_query *query, + struct bridge_mcast_querier *querier) +{ + spin_lock(&br->multicast_lock); + if (query->startup_sent < br->multicast_startup_query_count) + query->startup_sent++; + + rcu_assign_pointer(querier, NULL); + br_multicast_send_query(br, NULL, query); + spin_unlock(&br->multicast_lock); +} + +static void br_ip4_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_query_expired(br, &br->ip4_own_query, &br->ip4_querier); +} - br_multicast_send_query(br, NULL, br->multicast_startup_queries_sent); +#if IS_ENABLED(CONFIG_IPV6) +static void br_ip6_multicast_query_expired(unsigned long data) +{ + struct net_bridge *br = (void *)data; - spin_unlock(&br->multicast_lock); + br_multicast_query_expired(br, &br->ip6_own_query, &br->ip6_querier); } +#endif void br_multicast_init(struct net_bridge *br) { @@ -1602,6 +1849,8 @@ void br_multicast_init(struct net_bridge *br) br->hash_max = 512; br->multicast_router = 1; + br->multicast_querier = 0; + br->multicast_query_use_ifaddr = 0; br->multicast_last_member_count = 2; br->multicast_startup_query_count = 2; @@ -1612,36 +1861,62 @@ void br_multicast_init(struct net_bridge *br) br->multicast_querier_interval = 255 * HZ; br->multicast_membership_interval = 260 * HZ; + br->ip4_other_query.delay_time = 0; + br->ip4_querier.port = NULL; +#if IS_ENABLED(CONFIG_IPV6) + br->ip6_other_query.delay_time = 0; + br->ip6_querier.port = NULL; +#endif + 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, + setup_timer(&br->ip4_other_query.timer, + br_ip4_multicast_querier_expired, (unsigned long)br); + setup_timer(&br->ip4_own_query.timer, br_ip4_multicast_query_expired, (unsigned long)br); +#if IS_ENABLED(CONFIG_IPV6) + setup_timer(&br->ip6_other_query.timer, + br_ip6_multicast_querier_expired, (unsigned long)br); + setup_timer(&br->ip6_own_query.timer, br_ip6_multicast_query_expired, + (unsigned long)br); +#endif } -void br_multicast_open(struct net_bridge *br) +static void __br_multicast_open(struct net_bridge *br, + struct bridge_mcast_own_query *query) { - br->multicast_startup_queries_sent = 0; + query->startup_sent = 0; if (br->multicast_disabled) return; - mod_timer(&br->multicast_query_timer, jiffies); + mod_timer(&query->timer, jiffies); +} + +void br_multicast_open(struct net_bridge *br) +{ + __br_multicast_open(br, &br->ip4_own_query); +#if IS_ENABLED(CONFIG_IPV6) + __br_multicast_open(br, &br->ip6_own_query); +#endif } 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; + struct hlist_node *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); + del_timer_sync(&br->ip4_other_query.timer); + del_timer_sync(&br->ip4_own_query.timer); +#if IS_ENABLED(CONFIG_IPV6) + del_timer_sync(&br->ip6_other_query.timer); + del_timer_sync(&br->ip6_own_query.timer); +#endif spin_lock_bh(&br->multicast_lock); mdb = mlock_dereference(br->mdb, br); @@ -1652,10 +1927,9 @@ void br_multicast_stop(struct net_bridge *br) ver = mdb->ver; for (i = 0; i < mdb->max; i++) { - hlist_for_each_entry_safe(mp, p, n, &mdb->mhash[i], + hlist_for_each_entry_safe(mp, n, &mdb->mhash[i], hlist[ver]) { del_timer(&mp->timer); - del_timer(&mp->query_timer); call_rcu_bh(&mp->rcu, br_multicast_free_group); } } @@ -1744,13 +2018,33 @@ unlock: return err; } -int br_multicast_toggle(struct net_bridge *br, unsigned long val) +static void br_multicast_start_querier(struct net_bridge *br, + struct bridge_mcast_own_query *query) { struct net_bridge_port *port; + + __br_multicast_open(br, query); + + list_for_each_entry(port, &br->port_list, list) { + if (port->state == BR_STATE_DISABLED || + port->state == BR_STATE_BLOCKING) + continue; + + if (query == &br->ip4_own_query) + br_multicast_enable(&port->ip4_own_query); +#if IS_ENABLED(CONFIG_IPV6) + else + br_multicast_enable(&port->ip6_own_query); +#endif + } +} + +int br_multicast_toggle(struct net_bridge *br, unsigned long val) +{ int err = 0; struct net_bridge_mdb_htable *mdb; - spin_lock(&br->multicast_lock); + spin_lock_bh(&br->multicast_lock); if (br->multicast_disabled == !val) goto unlock; @@ -1776,28 +2070,58 @@ rollback: 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); - } + br_multicast_start_querier(br, &br->ip4_own_query); +#if IS_ENABLED(CONFIG_IPV6) + br_multicast_start_querier(br, &br->ip6_own_query); +#endif unlock: - spin_unlock(&br->multicast_lock); + spin_unlock_bh(&br->multicast_lock); return err; } +int br_multicast_set_querier(struct net_bridge *br, unsigned long val) +{ + unsigned long max_delay; + + val = !!val; + + spin_lock_bh(&br->multicast_lock); + if (br->multicast_querier == val) + goto unlock; + + br->multicast_querier = val; + if (!val) + goto unlock; + + max_delay = br->multicast_query_response_interval; + + if (!timer_pending(&br->ip4_other_query.timer)) + br->ip4_other_query.delay_time = jiffies + max_delay; + + br_multicast_start_querier(br, &br->ip4_own_query); + +#if IS_ENABLED(CONFIG_IPV6) + if (!timer_pending(&br->ip6_other_query.timer)) + br->ip6_other_query.delay_time = jiffies + max_delay; + + br_multicast_start_querier(br, &br->ip6_own_query); +#endif + +unlock: + spin_unlock_bh(&br->multicast_lock); + + return 0; +} + 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); + spin_lock_bh(&br->multicast_lock); if (!netif_running(br->dev)) goto unlock; @@ -1829,7 +2153,113 @@ rollback: } unlock: - spin_unlock(&br->multicast_lock); + spin_unlock_bh(&br->multicast_lock); return err; } + +/** + * br_multicast_list_adjacent - Returns snooped multicast addresses + * @dev: The bridge port adjacent to which to retrieve addresses + * @br_ip_list: The list to store found, snooped multicast IP addresses in + * + * Creates a list of IP addresses (struct br_ip_list) sensed by the multicast + * snooping feature on all bridge ports of dev's bridge device, excluding + * the addresses from dev itself. + * + * Returns the number of items added to br_ip_list. + * + * Notes: + * - br_ip_list needs to be initialized by caller + * - br_ip_list might contain duplicates in the end + * (needs to be taken care of by caller) + * - br_ip_list needs to be freed by caller + */ +int br_multicast_list_adjacent(struct net_device *dev, + struct list_head *br_ip_list) +{ + struct net_bridge *br; + struct net_bridge_port *port; + struct net_bridge_port_group *group; + struct br_ip_list *entry; + int count = 0; + + rcu_read_lock(); + if (!br_ip_list || !br_port_exists(dev)) + goto unlock; + + port = br_port_get_rcu(dev); + if (!port || !port->br) + goto unlock; + + br = port->br; + + list_for_each_entry_rcu(port, &br->port_list, list) { + if (!port->dev || port->dev == dev) + continue; + + hlist_for_each_entry_rcu(group, &port->mglist, mglist) { + entry = kmalloc(sizeof(*entry), GFP_ATOMIC); + if (!entry) + goto unlock; + + entry->addr = group->addr; + list_add(&entry->list, br_ip_list); + count++; + } + } + +unlock: + rcu_read_unlock(); + return count; +} +EXPORT_SYMBOL_GPL(br_multicast_list_adjacent); + +/** + * br_multicast_has_querier_adjacent - Checks for a querier behind a bridge port + * @dev: The bridge port adjacent to which to check for a querier + * @proto: The protocol family to check for: IGMP -> ETH_P_IP, MLD -> ETH_P_IPV6 + * + * Checks whether the given interface has a bridge on top and if so returns + * true if a selected querier is behind one of the other ports of this + * bridge. Otherwise returns false. + */ +bool br_multicast_has_querier_adjacent(struct net_device *dev, int proto) +{ + struct net_bridge *br; + struct net_bridge_port *port; + bool ret = false; + + rcu_read_lock(); + if (!br_port_exists(dev)) + goto unlock; + + port = br_port_get_rcu(dev); + if (!port || !port->br) + goto unlock; + + br = port->br; + + switch (proto) { + case ETH_P_IP: + if (!timer_pending(&br->ip4_other_query.timer) || + rcu_dereference(br->ip4_querier.port) == port) + goto unlock; + break; +#if IS_ENABLED(CONFIG_IPV6) + case ETH_P_IPV6: + if (!timer_pending(&br->ip6_other_query.timer) || + rcu_dereference(br->ip6_querier.port) == port) + goto unlock; + break; +#endif + default: + goto unlock; + } + + ret = true; +unlock: + rcu_read_unlock(); + return ret; +} +EXPORT_SYMBOL_GPL(br_multicast_has_querier_adjacent); |