diff options
Diffstat (limited to 'net/bridge')
-rw-r--r-- | net/bridge/Makefile | 2 | ||||
-rw-r--r-- | net/bridge/br.c | 22 | ||||
-rw-r--r-- | net/bridge/br_fdb.c | 38 | ||||
-rw-r--r-- | net/bridge/br_forward.c | 28 | ||||
-rw-r--r-- | net/bridge/br_if.c | 4 | ||||
-rw-r--r-- | net/bridge/br_mdb.c | 18 | ||||
-rw-r--r-- | net/bridge/br_multicast.c | 353 | ||||
-rw-r--r-- | net/bridge/br_netfilter_hooks.c (renamed from net/bridge/br_netfilter.c) | 322 | ||||
-rw-r--r-- | net/bridge/br_netfilter_ipv6.c | 245 | ||||
-rw-r--r-- | net/bridge/br_netlink.c | 40 | ||||
-rw-r--r-- | net/bridge/br_private.h | 13 | ||||
-rw-r--r-- | net/bridge/br_stp.c | 18 | ||||
-rw-r--r-- | net/bridge/br_stp_if.c | 15 | ||||
-rw-r--r-- | net/bridge/br_stp_timer.c | 4 | ||||
-rw-r--r-- | net/bridge/br_sysfs_if.c | 2 | ||||
-rw-r--r-- | net/bridge/br_vlan.c | 60 | ||||
-rw-r--r-- | net/bridge/netfilter/ebt_stp.c | 6 | ||||
-rw-r--r-- | net/bridge/netfilter/ebtables.c | 4 |
18 files changed, 656 insertions, 538 deletions
diff --git a/net/bridge/Makefile b/net/bridge/Makefile index fd7ee03c5..a1cda5d47 100644 --- a/net/bridge/Makefile +++ b/net/bridge/Makefile @@ -12,6 +12,8 @@ bridge-$(CONFIG_SYSFS) += br_sysfs_if.o br_sysfs_br.o bridge-$(subst m,y,$(CONFIG_BRIDGE_NETFILTER)) += br_nf_core.o +br_netfilter-y := br_netfilter_hooks.o +br_netfilter-$(subst m,y,$(CONFIG_IPV6)) += br_netfilter_ipv6.o obj-$(CONFIG_BRIDGE_NETFILTER) += br_netfilter.o bridge-$(CONFIG_BRIDGE_IGMP_SNOOPING) += br_multicast.o br_mdb.o diff --git a/net/bridge/br.c b/net/bridge/br.c index 02c24cf63..a1abe4936 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -121,13 +121,13 @@ static struct notifier_block br_device_notifier = { .notifier_call = br_device_event }; -static int br_netdev_switch_event(struct notifier_block *unused, - unsigned long event, void *ptr) +static int br_switchdev_event(struct notifier_block *unused, + unsigned long event, void *ptr) { - struct net_device *dev = netdev_switch_notifier_info_to_dev(ptr); + struct net_device *dev = switchdev_notifier_info_to_dev(ptr); struct net_bridge_port *p; struct net_bridge *br; - struct netdev_switch_notifier_fdb_info *fdb_info; + struct switchdev_notifier_fdb_info *fdb_info; int err = NOTIFY_DONE; rtnl_lock(); @@ -138,14 +138,14 @@ static int br_netdev_switch_event(struct notifier_block *unused, br = p->br; switch (event) { - case NETDEV_SWITCH_FDB_ADD: + case SWITCHDEV_FDB_ADD: fdb_info = ptr; err = br_fdb_external_learn_add(br, p, fdb_info->addr, fdb_info->vid); if (err) err = notifier_from_errno(err); break; - case NETDEV_SWITCH_FDB_DEL: + case SWITCHDEV_FDB_DEL: fdb_info = ptr; err = br_fdb_external_learn_del(br, p, fdb_info->addr, fdb_info->vid); @@ -159,8 +159,8 @@ out: return err; } -static struct notifier_block br_netdev_switch_notifier = { - .notifier_call = br_netdev_switch_event, +static struct notifier_block br_switchdev_notifier = { + .notifier_call = br_switchdev_event, }; static void __net_exit br_net_exit(struct net *net) @@ -214,7 +214,7 @@ static int __init br_init(void) if (err) goto err_out3; - err = register_netdev_switch_notifier(&br_netdev_switch_notifier); + err = register_switchdev_notifier(&br_switchdev_notifier); if (err) goto err_out4; @@ -235,7 +235,7 @@ static int __init br_init(void) return 0; err_out5: - unregister_netdev_switch_notifier(&br_netdev_switch_notifier); + unregister_switchdev_notifier(&br_switchdev_notifier); err_out4: unregister_netdevice_notifier(&br_device_notifier); err_out3: @@ -253,7 +253,7 @@ static void __exit br_deinit(void) { stp_proto_unregister(&br_stp_proto); br_netlink_fini(); - unregister_netdev_switch_notifier(&br_netdev_switch_notifier); + unregister_switchdev_notifier(&br_switchdev_notifier); unregister_netdevice_notifier(&br_device_notifier); brioctl_set(NULL); unregister_pernet_subsys(&br_net_ops); diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 659fb9667..9e9875da0 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -24,6 +24,7 @@ #include <linux/atomic.h> #include <asm/unaligned.h> #include <linux/if_vlan.h> +#include <net/switchdev.h> #include "br_private.h" static struct kmem_cache *br_fdb_cache __read_mostly; @@ -130,11 +131,27 @@ static void fdb_del_hw_addr(struct net_bridge *br, const unsigned char *addr) } } +static void fdb_del_external_learn(struct net_bridge_fdb_entry *f) +{ + struct switchdev_obj obj = { + .id = SWITCHDEV_OBJ_PORT_FDB, + .u.fdb = { + .addr = f->addr.addr, + .vid = f->vlan_id, + }, + }; + + switchdev_port_obj_del(f->dst->dev, &obj); +} + static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f) { if (f->is_static) fdb_del_hw_addr(br, f->addr.addr); + if (f->added_by_external_learn) + fdb_del_external_learn(f); + hlist_del_rcu(&f->hlist); fdb_notify(br, f, RTM_DELNEIGH); call_rcu(&f->rcu, fdb_rcu_free); @@ -313,9 +330,11 @@ void br_fdb_flush(struct net_bridge *br) /* Flush all entries referring to a specific port. * if do_all is set also flush static entries + * if vid is set delete all entries that match the vlan_id */ void br_fdb_delete_by_port(struct net_bridge *br, const struct net_bridge_port *p, + u16 vid, int do_all) { int i; @@ -330,8 +349,9 @@ void br_fdb_delete_by_port(struct net_bridge *br, if (f->dst != p) continue; - if (f->is_static && !do_all) - continue; + if (!do_all) + if (f->is_static || (vid && f->vlan_id != vid)) + continue; if (f->is_local) fdb_delete_local(br, p, f); @@ -736,6 +756,12 @@ static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr, struct net_bridge_fdb_entry *fdb; bool modified = false; + /* If the port cannot learn allow only local and static entries */ + if (!(state & NUD_PERMANENT) && !(state & NUD_NOARP) && + !(source->state == BR_STATE_LEARNING || + source->state == BR_STATE_FORWARDING)) + return -EPERM; + fdb = fdb_find(head, addr, vid); if (fdb == NULL) { if (!(flags & NLM_F_CREATE)) @@ -867,13 +893,15 @@ out: return err; } -static int fdb_delete_by_addr(struct net_bridge *br, const u8 *addr, u16 vlan) +static int fdb_delete_by_addr_and_port(struct net_bridge_port *p, + const u8 *addr, u16 vlan) { + struct net_bridge *br = p->br; struct hlist_head *head = &br->hash[br_mac_hash(addr, vlan)]; struct net_bridge_fdb_entry *fdb; fdb = fdb_find(head, addr, vlan); - if (!fdb) + if (!fdb || fdb->dst != p) return -ENOENT; fdb_delete(br, fdb); @@ -886,7 +914,7 @@ static int __br_fdb_delete(struct net_bridge_port *p, int err; spin_lock_bh(&p->br->hash_lock); - err = fdb_delete_by_addr(p->br, addr, vid); + err = fdb_delete_by_addr_and_port(p, addr, vid); spin_unlock_bh(&p->br->hash_lock); return err; diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index e97572b5d..fa7bfced8 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -37,14 +37,30 @@ static inline int should_deliver(const struct net_bridge_port *p, int br_dev_queue_push_xmit(struct sock *sk, struct sk_buff *skb) { - if (!is_skb_forwardable(skb->dev, skb)) { - kfree_skb(skb); - } else { - skb_push(skb, ETH_HLEN); - br_drop_fake_rtable(skb); - dev_queue_xmit(skb); + if (!is_skb_forwardable(skb->dev, skb)) + goto drop; + + skb_push(skb, ETH_HLEN); + br_drop_fake_rtable(skb); + skb_sender_cpu_clear(skb); + + if (skb->ip_summed == CHECKSUM_PARTIAL && + (skb->protocol == htons(ETH_P_8021Q) || + skb->protocol == htons(ETH_P_8021AD))) { + int depth; + + if (!__vlan_get_protocol(skb, skb->protocol, &depth)) + goto drop; + + skb_set_network_header(skb, depth); } + dev_queue_xmit(skb); + + return 0; + +drop: + kfree_skb(skb); return 0; } EXPORT_SYMBOL_GPL(br_dev_queue_push_xmit); diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 1849d96b3..a538cb119 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -249,7 +249,7 @@ static void del_nbp(struct net_bridge_port *p) list_del_rcu(&p->list); nbp_vlan_flush(p); - br_fdb_delete_by_port(br, p, 1); + br_fdb_delete_by_port(br, p, 0, 1); nbp_update_port_count(br); netdev_upper_dev_unlink(dev, br->dev); @@ -278,7 +278,7 @@ void br_dev_delete(struct net_device *dev, struct list_head *head) del_nbp(p); } - br_fdb_delete_by_port(br, NULL, 1); + br_fdb_delete_by_port(br, NULL, 0, 1); br_vlan_flush(br); del_timer_sync(&br->gc_timer); diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index e29ad70b3..c94321955 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -323,6 +323,7 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, struct net_bridge_port_group *p; struct net_bridge_port_group __rcu **pp; struct net_bridge_mdb_htable *mdb; + unsigned long now = jiffies; int err; mdb = mlock_dereference(br->mdb, br); @@ -347,8 +348,9 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, if (unlikely(!p)) return -ENOMEM; rcu_assign_pointer(*pp, p); + if (state == MDB_TEMPORARY) + mod_timer(&p->timer, now + br->multicast_membership_interval); - br_mdb_notify(br->dev, port, group, RTM_NEWMDB); return 0; } @@ -371,6 +373,7 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br, if (!p || p->br != br || p->state == BR_STATE_DISABLED) return -EINVAL; + memset(&ip, 0, sizeof(ip)); ip.proto = entry->addr.proto; if (ip.proto == htons(ETH_P_IP)) ip.u.ip4 = entry->addr.u.ip4; @@ -417,20 +420,14 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry) if (!netif_running(br->dev) || br->multicast_disabled) return -EINVAL; + memset(&ip, 0, sizeof(ip)); ip.proto = entry->addr.proto; - if (ip.proto == htons(ETH_P_IP)) { - if (timer_pending(&br->ip4_other_query.timer)) - return -EBUSY; - + if (ip.proto == htons(ETH_P_IP)) ip.u.ip4 = entry->addr.u.ip4; #if IS_ENABLED(CONFIG_IPV6) - } else { - if (timer_pending(&br->ip6_other_query.timer)) - return -EBUSY; - + else ip.u.ip6 = entry->addr.u.ip6; #endif - } spin_lock_bh(&br->multicast_lock); mdb = mlock_dereference(br->mdb, br); @@ -448,6 +445,7 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry) if (p->port->state == BR_STATE_DISABLED) goto unlock; + entry->state = p->state; rcu_assign_pointer(*pp, p->next); hlist_del_init(&p->mglist); del_timer(&p->timer); diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index ff667e18b..1285eaf5d 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -37,6 +37,18 @@ static void br_multicast_start_querier(struct net_bridge *br, struct bridge_mcast_own_query *query); +static void br_multicast_add_router(struct net_bridge *br, + struct net_bridge_port *port); +static void br_ip4_multicast_leave_group(struct net_bridge *br, + struct net_bridge_port *port, + __be32 group, + __u16 vid); +#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, + __u16 vid); +#endif unsigned int br_mdb_rehash_seq; static inline int br_ip_equal(const struct br_ip *a, const struct br_ip *b) @@ -936,6 +948,8 @@ void br_multicast_enable_port(struct net_bridge_port *port) #if IS_ENABLED(CONFIG_IPV6) br_multicast_enable(&port->ip6_own_query); #endif + if (port->multicast_router == 2 && hlist_unhashed(&port->rlist)) + br_multicast_add_router(br, port); out: spin_unlock(&br->multicast_lock); @@ -975,9 +989,6 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br, 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); @@ -1009,9 +1020,15 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br, continue; } - err = br_ip4_multicast_add_group(br, port, group, vid); - if (err) - break; + if ((type == IGMPV3_CHANGE_TO_INCLUDE || + type == IGMPV3_MODE_IS_INCLUDE) && + ntohs(grec->grec_nsrcs) == 0) { + br_ip4_multicast_leave_group(br, port, group, vid); + } else { + err = br_ip4_multicast_add_group(br, port, group, vid); + if (err) + break; + } } return err; @@ -1070,10 +1087,17 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, continue; } - err = br_ip6_multicast_add_group(br, port, &grec->grec_mca, - vid); - if (err) - break; + if ((grec->grec_type == MLD2_CHANGE_TO_INCLUDE || + grec->grec_type == MLD2_MODE_IS_INCLUDE) && + ntohs(*nsrcs) == 0) { + br_ip6_multicast_leave_group(br, port, &grec->grec_mca, + vid); + } else { + err = br_ip6_multicast_add_group(br, port, + &grec->grec_mca, vid); + if (!err) + break; + } } return err; @@ -1247,25 +1271,14 @@ static int br_ip4_multicast_query(struct net_bridge *br, max_delay = 10 * HZ; group = 0; } - } else { - if (!pskb_may_pull(skb, sizeof(struct igmpv3_query))) { - err = -EINVAL; - goto out; - } - + } else if (skb->len >= sizeof(*ih3)) { ih3 = igmpv3_query_hdr(skb); if (ih3->nsrcs) goto out; max_delay = ih3->code ? IGMPV3_MRC(ih3->code) * (HZ / IGMP_TIMER_SCALE) : 1; - } - - /* 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; + } else { goto out; } @@ -1328,12 +1341,6 @@ static int br_ip6_multicast_query(struct net_bridge *br, (port && port->state == BR_STATE_DISABLED)) goto out; - /* 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))) { err = -EINVAL; @@ -1357,14 +1364,6 @@ static int br_ip6_multicast_query(struct net_bridge *br, 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 (is_general_query) { saddr.proto = htons(ETH_P_IPV6); saddr.u.ip6 = ip6h->saddr; @@ -1417,8 +1416,7 @@ 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(&other_query->timer)) + (port && port->state == BR_STATE_DISABLED)) goto out; mdb = mlock_dereference(br->mdb, br); @@ -1426,6 +1424,31 @@ br_multicast_leave_group(struct net_bridge *br, if (!mp) goto out; + 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; + } + + if (timer_pending(&other_query->timer)) + goto out; + if (br->multicast_querier) { __br_multicast_send_query(br, port, &mp->addr); @@ -1451,28 +1474,6 @@ br_multicast_leave_group(struct net_bridge *br, } } - 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; @@ -1556,74 +1557,22 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, struct sk_buff *skb, u16 vid) { - struct sk_buff *skb2 = skb; - const struct iphdr *iph; + struct sk_buff *skb_trimmed = NULL; struct igmphdr *ih; - unsigned int len; - unsigned int 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; + err = ip_mc_check_igmp(skb, &skb_trimmed); - if (iph->protocol != IPPROTO_IGMP) { - if (!ipv4_is_local_multicast(iph->daddr)) + if (err == -ENOMSG) { + if (!ipv4_is_local_multicast(ip_hdr(skb)->daddr)) BR_INPUT_SKB_CB(skb)->mrouters_only = 1; return 0; + } else if (err < 0) { + return err; } - 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); + ih = igmp_hdr(skb); switch (ih->type) { case IGMP_HOST_MEMBERSHIP_REPORT: @@ -1632,21 +1581,19 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, 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, vid); + err = br_ip4_multicast_igmp3_report(br, port, skb_trimmed, vid); break; case IGMP_HOST_MEMBERSHIP_QUERY: - err = br_ip4_multicast_query(br, port, skb2, vid); + err = br_ip4_multicast_query(br, port, skb_trimmed, vid); break; case IGMP_HOST_LEAVE_MESSAGE: br_ip4_multicast_leave_group(br, port, ih->group, vid); break; } -out: - __skb_push(skb2, offset); -err_out: - if (skb2 != skb) - kfree_skb(skb2); + if (skb_trimmed && skb_trimmed != skb) + kfree_skb(skb_trimmed); + return err; } @@ -1656,138 +1603,42 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, struct sk_buff *skb, u16 vid) { - struct sk_buff *skb2; - const struct ipv6hdr *ip6h; - u8 icmp6_type; - u8 nexthdr; - __be16 frag_off; - unsigned int len; - int offset; + struct sk_buff *skb_trimmed = NULL; + struct mld_msg *mld; 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) - 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) + sizeof(*ip6h); - if (skb->len < len) - return -EINVAL; - - nexthdr = ip6h->nexthdr; - offset = ipv6_skip_exthdr(skb, sizeof(*ip6h), &nexthdr, &frag_off); + err = ipv6_mc_check_mld(skb, &skb_trimmed); - if (offset < 0 || nexthdr != IPPROTO_ICMPV6) + if (err == -ENOMSG) { + if (!ipv6_addr_is_ll_all_nodes(&ipv6_hdr(skb)->daddr)) + BR_INPUT_SKB_CB(skb)->mrouters_only = 1; 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; + } else if (err < 0) { + return err; } - err = 0; - BR_INPUT_SKB_CB(skb)->igmp = 1; + mld = (struct mld_msg *)skb_transport_header(skb); - switch (icmp6_type) { + switch (mld->mld_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, vid); break; - } case ICMPV6_MLD2_REPORT: - err = br_ip6_multicast_mld2_report(br, port, skb2, vid); + err = br_ip6_multicast_mld2_report(br, port, skb_trimmed, vid); break; case ICMPV6_MGM_QUERY: - err = br_ip6_multicast_query(br, port, skb2, vid); + err = br_ip6_multicast_query(br, port, skb_trimmed, vid); 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, vid); - } + break; } -out: - kfree_skb(skb2); + if (skb_trimmed && skb_trimmed != skb) + kfree_skb(skb_trimmed); + return err; } #endif @@ -1949,11 +1800,9 @@ out: int br_multicast_set_router(struct net_bridge *br, unsigned long val) { - int err = -ENOENT; + int err = -EINVAL; spin_lock_bh(&br->multicast_lock); - if (!netif_running(br->dev)) - goto unlock; switch (val) { case 0: @@ -1964,13 +1813,8 @@ int br_multicast_set_router(struct net_bridge *br, unsigned long val) br->multicast_router = val; err = 0; break; - - default: - err = -EINVAL; - break; } -unlock: spin_unlock_bh(&br->multicast_lock); return err; @@ -1979,11 +1823,9 @@ unlock: int br_multicast_set_port_router(struct net_bridge_port *p, unsigned long val) { struct net_bridge *br = p->br; - int err = -ENOENT; + int err = -EINVAL; spin_lock(&br->multicast_lock); - if (!netif_running(br->dev) || p->state == BR_STATE_DISABLED) - goto unlock; switch (val) { case 0: @@ -2005,13 +1847,8 @@ int br_multicast_set_port_router(struct net_bridge_port *p, unsigned long val) br_multicast_add_router(br, p); break; - - default: - err = -EINVAL; - break; } -unlock: spin_unlock(&br->multicast_lock); return err; @@ -2116,15 +1953,11 @@ unlock: int br_multicast_set_hash_max(struct net_bridge *br, unsigned long val) { - int err = -ENOENT; + int err = -EINVAL; u32 old; struct net_bridge_mdb_htable *mdb; spin_lock_bh(&br->multicast_lock); - if (!netif_running(br->dev)) - goto unlock; - - err = -EINVAL; if (!is_power_of_2(val)) goto unlock; diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter_hooks.c index 60ddfbeb4..c8b9bcfe9 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter_hooks.c @@ -34,6 +34,7 @@ #include <net/ip.h> #include <net/ipv6.h> +#include <net/addrconf.h> #include <net/route.h> #include <net/netfilter/br_netfilter.h> @@ -110,27 +111,24 @@ static inline __be16 pppoe_proto(const struct sk_buff *skb) /* largest possible L2 header, see br_nf_dev_queue_xmit() */ #define NF_BRIDGE_MAX_MAC_HEADER_LENGTH (PPPOE_SES_HLEN + ETH_HLEN) -#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) +#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) || IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) struct brnf_frag_data { char mac[NF_BRIDGE_MAX_MAC_HEADER_LENGTH]; u8 encap_size; u8 size; + u16 vlan_tci; + __be16 vlan_proto; }; static DEFINE_PER_CPU(struct brnf_frag_data, brnf_frag_data_storage); #endif -static struct nf_bridge_info *nf_bridge_info_get(const struct sk_buff *skb) +static void nf_bridge_info_free(struct sk_buff *skb) { - return skb->nf_bridge; -} - -static inline struct rtable *bridge_parent_rtable(const struct net_device *dev) -{ - struct net_bridge_port *port; - - port = br_port_get_rcu(dev); - return port ? &port->br->fake_rtable : NULL; + if (skb->nf_bridge) { + nf_bridge_put(skb->nf_bridge); + skb->nf_bridge = NULL; + } } static inline struct net_device *bridge_parent(const struct net_device *dev) @@ -141,15 +139,6 @@ static inline struct net_device *bridge_parent(const struct net_device *dev) return port ? port->br->dev : NULL; } -static inline struct nf_bridge_info *nf_bridge_alloc(struct sk_buff *skb) -{ - skb->nf_bridge = kzalloc(sizeof(struct nf_bridge_info), GFP_ATOMIC); - if (likely(skb->nf_bridge)) - atomic_set(&(skb->nf_bridge->use), 1); - - return skb->nf_bridge; -} - static inline struct nf_bridge_info *nf_bridge_unshare(struct sk_buff *skb) { struct nf_bridge_info *nf_bridge = skb->nf_bridge; @@ -167,7 +156,7 @@ static inline struct nf_bridge_info *nf_bridge_unshare(struct sk_buff *skb) return nf_bridge; } -static unsigned int nf_bridge_encap_header_len(const struct sk_buff *skb) +unsigned int nf_bridge_encap_header_len(const struct sk_buff *skb) { switch (skb->protocol) { case __cpu_to_be16(ETH_P_8021Q): @@ -179,14 +168,6 @@ static unsigned int nf_bridge_encap_header_len(const struct sk_buff *skb) } } -static inline void nf_bridge_push_encap_header(struct sk_buff *skb) -{ - unsigned int len = nf_bridge_encap_header_len(skb); - - skb_push(skb, len); - skb->network_header -= len; -} - static inline void nf_bridge_pull_encap_header(struct sk_buff *skb) { unsigned int len = nf_bridge_encap_header_len(skb); @@ -208,7 +189,7 @@ static inline void nf_bridge_pull_encap_header_rcsum(struct sk_buff *skb) * expected format */ -static int br_parse_ip_options(struct sk_buff *skb) +static int br_validate_ipv4(struct sk_buff *skb) { const struct iphdr *iph; struct net_device *dev = skb->dev; @@ -256,7 +237,7 @@ drop: return -1; } -static void nf_bridge_update_protocol(struct sk_buff *skb) +void nf_bridge_update_protocol(struct sk_buff *skb) { switch (skb->nf_bridge->orig_proto) { case BRNF_PROTO_8021Q: @@ -270,43 +251,12 @@ static void nf_bridge_update_protocol(struct sk_buff *skb) } } -/* PF_BRIDGE/PRE_ROUTING *********************************************/ -/* Undo the changes made for ip6tables PREROUTING and continue the - * bridge PRE_ROUTING hook. */ -static int br_nf_pre_routing_finish_ipv6(struct sock *sk, struct sk_buff *skb) -{ - struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); - struct rtable *rt; - - if (nf_bridge->pkt_otherhost) { - skb->pkt_type = PACKET_OTHERHOST; - nf_bridge->pkt_otherhost = false; - } - nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING; - - rt = bridge_parent_rtable(nf_bridge->physindev); - if (!rt) { - kfree_skb(skb); - return 0; - } - skb_dst_set_noref(skb, &rt->dst); - - skb->dev = nf_bridge->physindev; - nf_bridge_update_protocol(skb); - nf_bridge_push_encap_header(skb); - NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, sk, skb, - skb->dev, NULL, - br_handle_frame_finish, 1); - - return 0; -} - /* Obtain the correct destination MAC address, while preserving the original * source MAC address. If we already know this address, we just copy it. If we * don't, we use the neighbour framework to find out. In both cases, we make * sure that br_handle_frame_finish() is called afterwards. */ -static int br_nf_pre_routing_finish_bridge(struct sock *sk, struct sk_buff *skb) +int br_nf_pre_routing_finish_bridge(struct sock *sk, struct sk_buff *skb) { struct neighbour *neigh; struct dst_entry *dst; @@ -346,8 +296,9 @@ free_skb: return 0; } -static bool daddr_was_changed(const struct sk_buff *skb, - const struct nf_bridge_info *nf_bridge) +static inline bool +br_nf_ipv4_daddr_was_changed(const struct sk_buff *skb, + const struct nf_bridge_info *nf_bridge) { return ip_hdr(skb)->daddr != nf_bridge->ipv4_daddr; } @@ -398,17 +349,15 @@ static int br_nf_pre_routing_finish(struct sock *sk, struct sk_buff *skb) struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); struct rtable *rt; int err; - int frag_max_size; - frag_max_size = IPCB(skb)->frag_max_size; - BR_INPUT_SKB_CB(skb)->frag_max_size = frag_max_size; + nf_bridge->frag_max_size = IPCB(skb)->frag_max_size; if (nf_bridge->pkt_otherhost) { skb->pkt_type = PACKET_OTHERHOST; nf_bridge->pkt_otherhost = false; } - nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING; - if (daddr_was_changed(skb, nf_bridge)) { + nf_bridge->mask &= ~BRNF_NF_BRIDGE_PREROUTING; + if (br_nf_ipv4_daddr_was_changed(skb, nf_bridge)) { if ((err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev))) { struct in_device *in_dev = __in_dev_get_rcu(dev); @@ -486,7 +435,7 @@ static struct net_device *brnf_get_logical_dev(struct sk_buff *skb, const struct } /* Some common code for IPv4/IPv6 */ -static struct net_device *setup_pre_routing(struct sk_buff *skb) +struct net_device *setup_pre_routing(struct sk_buff *skb) { struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); @@ -509,106 +458,6 @@ static struct net_device *setup_pre_routing(struct sk_buff *skb) return skb->dev; } -/* We only check the length. A bridge shouldn't do any hop-by-hop stuff anyway */ -static int check_hbh_len(struct sk_buff *skb) -{ - unsigned char *raw = (u8 *)(ipv6_hdr(skb) + 1); - u32 pkt_len; - const unsigned char *nh = skb_network_header(skb); - int off = raw - nh; - int len = (raw[1] + 1) << 3; - - if ((raw + len) - skb->data > skb_headlen(skb)) - goto bad; - - off += 2; - len -= 2; - - while (len > 0) { - int optlen = nh[off + 1] + 2; - - switch (nh[off]) { - case IPV6_TLV_PAD1: - optlen = 1; - break; - - case IPV6_TLV_PADN: - break; - - case IPV6_TLV_JUMBO: - if (nh[off + 1] != 4 || (off & 3) != 2) - goto bad; - pkt_len = ntohl(*(__be32 *) (nh + off + 2)); - if (pkt_len <= IPV6_MAXPLEN || - ipv6_hdr(skb)->payload_len) - goto bad; - if (pkt_len > skb->len - sizeof(struct ipv6hdr)) - goto bad; - if (pskb_trim_rcsum(skb, - pkt_len + sizeof(struct ipv6hdr))) - goto bad; - nh = skb_network_header(skb); - break; - default: - if (optlen > len) - goto bad; - break; - } - off += optlen; - len -= optlen; - } - if (len == 0) - return 0; -bad: - return -1; - -} - -/* Replicate the checks that IPv6 does on packet reception and pass the packet - * to ip6tables, which doesn't support NAT, so things are fairly simple. */ -static unsigned int br_nf_pre_routing_ipv6(const struct nf_hook_ops *ops, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - const struct ipv6hdr *hdr; - u32 pkt_len; - - if (skb->len < sizeof(struct ipv6hdr)) - return NF_DROP; - - if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) - return NF_DROP; - - hdr = ipv6_hdr(skb); - - if (hdr->version != 6) - return NF_DROP; - - pkt_len = ntohs(hdr->payload_len); - - if (pkt_len || hdr->nexthdr != NEXTHDR_HOP) { - if (pkt_len + sizeof(struct ipv6hdr) > skb->len) - return NF_DROP; - if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr))) - return NF_DROP; - } - if (hdr->nexthdr == NEXTHDR_HOP && check_hbh_len(skb)) - return NF_DROP; - - nf_bridge_put(skb->nf_bridge); - if (!nf_bridge_alloc(skb)) - return NF_DROP; - if (!setup_pre_routing(skb)) - return NF_DROP; - - skb->protocol = htons(ETH_P_IPV6); - NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, state->sk, skb, - skb->dev, NULL, - br_nf_pre_routing_finish_ipv6); - - return NF_STOLEN; -} - /* Direct IPv6 traffic to br_nf_pre_routing_ipv6. * Replicate the checks that IPv4 does on packet reception. * Set skb->dev to the bridge device (i.e. parent of the @@ -648,7 +497,7 @@ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops, nf_bridge_pull_encap_header_rcsum(skb); - if (br_parse_ip_options(skb)) + if (br_validate_ipv4(skb)) return NF_DROP; nf_bridge_put(skb->nf_bridge); @@ -692,12 +541,12 @@ static int br_nf_forward_finish(struct sock *sk, struct sk_buff *skb) struct net_device *in; if (!IS_ARP(skb) && !IS_VLAN_ARP(skb)) { - int frag_max_size; - if (skb->protocol == htons(ETH_P_IP)) { - frag_max_size = IPCB(skb)->frag_max_size; - BR_INPUT_SKB_CB(skb)->frag_max_size = frag_max_size; - } + if (skb->protocol == htons(ETH_P_IP)) + nf_bridge->frag_max_size = IPCB(skb)->frag_max_size; + + if (skb->protocol == htons(ETH_P_IPV6)) + nf_bridge->frag_max_size = IP6CB(skb)->frag_max_size; in = nf_bridge->physindev; if (nf_bridge->pkt_otherhost) { @@ -760,12 +609,15 @@ static unsigned int br_nf_forward_ip(const struct nf_hook_ops *ops, } if (pf == NFPROTO_IPV4) { - int frag_max = BR_INPUT_SKB_CB(skb)->frag_max_size; - - if (br_parse_ip_options(skb)) + if (br_validate_ipv4(skb)) return NF_DROP; + IPCB(skb)->frag_max_size = nf_bridge->frag_max_size; + } - IPCB(skb)->frag_max_size = frag_max; + if (pf == NFPROTO_IPV6) { + if (br_validate_ipv6(skb)) + return NF_DROP; + IP6CB(skb)->frag_max_size = nf_bridge->frag_max_size; } nf_bridge->physoutdev = skb->dev; @@ -815,7 +667,7 @@ static unsigned int br_nf_forward_arp(const struct nf_hook_ops *ops, return NF_STOLEN; } -#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) +#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) || IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) static int br_nf_push_frag_xmit(struct sock *sk, struct sk_buff *skb) { struct brnf_frag_data *data; @@ -829,56 +681,120 @@ static int br_nf_push_frag_xmit(struct sock *sk, struct sk_buff *skb) return 0; } + if (data->vlan_tci) { + skb->vlan_tci = data->vlan_tci; + skb->vlan_proto = data->vlan_proto; + } + skb_copy_to_linear_data_offset(skb, -data->size, data->mac, data->size); __skb_push(skb, data->encap_size); + nf_bridge_info_free(skb); return br_dev_queue_push_xmit(sk, skb); } +#endif + +#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) +static int br_nf_ip_fragment(struct sock *sk, struct sk_buff *skb, + int (*output)(struct sock *, struct sk_buff *)) +{ + unsigned int mtu = ip_skb_dst_mtu(skb); + struct iphdr *iph = ip_hdr(skb); + struct rtable *rt = skb_rtable(skb); + struct net_device *dev = rt->dst.dev; + + if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) || + (IPCB(skb)->frag_max_size && + IPCB(skb)->frag_max_size > mtu))) { + IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS); + kfree_skb(skb); + return -EMSGSIZE; + } + + return ip_do_fragment(sk, skb, output); +} +#endif + +static unsigned int nf_bridge_mtu_reduction(const struct sk_buff *skb) +{ + if (skb->nf_bridge->orig_proto == BRNF_PROTO_PPPOE) + return PPPOE_SES_HLEN; + return 0; +} static int br_nf_dev_queue_xmit(struct sock *sk, struct sk_buff *skb) { - int ret; - int frag_max_size; + struct nf_bridge_info *nf_bridge; unsigned int mtu_reserved; - if (skb_is_gso(skb) || skb->protocol != htons(ETH_P_IP)) + mtu_reserved = nf_bridge_mtu_reduction(skb); + + if (skb_is_gso(skb) || skb->len + mtu_reserved <= skb->dev->mtu) { + nf_bridge_info_free(skb); return br_dev_queue_push_xmit(sk, skb); + } - mtu_reserved = nf_bridge_mtu_reduction(skb); + nf_bridge = nf_bridge_info_get(skb); + +#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) /* This is wrong! We should preserve the original fragment * boundaries by preserving frag_list rather than refragmenting. */ - if (skb->len + mtu_reserved > skb->dev->mtu) { + if (skb->protocol == htons(ETH_P_IP)) { struct brnf_frag_data *data; - frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size; - if (br_parse_ip_options(skb)) - /* Drop invalid packet */ - return NF_DROP; - IPCB(skb)->frag_max_size = frag_max_size; + if (br_validate_ipv4(skb)) + goto drop; + + IPCB(skb)->frag_max_size = nf_bridge->frag_max_size; nf_bridge_update_protocol(skb); data = this_cpu_ptr(&brnf_frag_data_storage); + + data->vlan_tci = skb->vlan_tci; + data->vlan_proto = skb->vlan_proto; data->encap_size = nf_bridge_encap_header_len(skb); data->size = ETH_HLEN + data->encap_size; skb_copy_from_linear_data_offset(skb, -data->size, data->mac, data->size); - ret = ip_fragment(sk, skb, br_nf_push_frag_xmit); - } else { - ret = br_dev_queue_push_xmit(sk, skb); + return br_nf_ip_fragment(sk, skb, br_nf_push_frag_xmit); } +#endif +#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) + if (skb->protocol == htons(ETH_P_IPV6)) { + const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops(); + struct brnf_frag_data *data; - return ret; -} -#else -static int br_nf_dev_queue_xmit(struct sock *sk, struct sk_buff *skb) -{ - return br_dev_queue_push_xmit(sk, skb); -} + if (br_validate_ipv6(skb)) + goto drop; + + IP6CB(skb)->frag_max_size = nf_bridge->frag_max_size; + + nf_bridge_update_protocol(skb); + + data = this_cpu_ptr(&brnf_frag_data_storage); + data->encap_size = nf_bridge_encap_header_len(skb); + data->size = ETH_HLEN + data->encap_size; + + skb_copy_from_linear_data_offset(skb, -data->size, data->mac, + data->size); + + if (v6ops) + return v6ops->fragment(sk, skb, br_nf_push_frag_xmit); + + kfree_skb(skb); + return -EMSGSIZE; + } #endif + nf_bridge_info_free(skb); + return br_dev_queue_push_xmit(sk, skb); + drop: + kfree_skb(skb); + return 0; +} /* PF_BRIDGE/POST_ROUTING ********************************************/ static unsigned int br_nf_post_routing(const struct nf_hook_ops *ops, @@ -964,6 +880,8 @@ static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb) nf_bridge->neigh_header, ETH_HLEN - ETH_ALEN); skb->dev = nf_bridge->physindev; + + nf_bridge->physoutdev = NULL; br_handle_frame_finish(NULL, skb); } diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c new file mode 100644 index 000000000..13b7d1e3d --- /dev/null +++ b/net/bridge/br_netfilter_ipv6.c @@ -0,0 +1,245 @@ +/* + * Handle firewalling + * Linux ethernet bridge + * + * Authors: + * Lennert Buytenhek <buytenh@gnu.org> + * Bart De Schuymer <bdschuym@pandora.be> + * + * 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. + * + * Lennert dedicates this file to Kerstin Wurdinger. + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/ip.h> +#include <linux/netdevice.h> +#include <linux/skbuff.h> +#include <linux/if_arp.h> +#include <linux/if_ether.h> +#include <linux/if_vlan.h> +#include <linux/if_pppox.h> +#include <linux/ppp_defs.h> +#include <linux/netfilter_bridge.h> +#include <linux/netfilter_ipv4.h> +#include <linux/netfilter_ipv6.h> +#include <linux/netfilter_arp.h> +#include <linux/in_route.h> +#include <linux/inetdevice.h> + +#include <net/ip.h> +#include <net/ipv6.h> +#include <net/addrconf.h> +#include <net/route.h> +#include <net/netfilter/br_netfilter.h> + +#include <asm/uaccess.h> +#include "br_private.h" +#ifdef CONFIG_SYSCTL +#include <linux/sysctl.h> +#endif + +/* We only check the length. A bridge shouldn't do any hop-by-hop stuff + * anyway + */ +static int br_nf_check_hbh_len(struct sk_buff *skb) +{ + unsigned char *raw = (u8 *)(ipv6_hdr(skb) + 1); + u32 pkt_len; + const unsigned char *nh = skb_network_header(skb); + int off = raw - nh; + int len = (raw[1] + 1) << 3; + + if ((raw + len) - skb->data > skb_headlen(skb)) + goto bad; + + off += 2; + len -= 2; + + while (len > 0) { + int optlen = nh[off + 1] + 2; + + switch (nh[off]) { + case IPV6_TLV_PAD1: + optlen = 1; + break; + + case IPV6_TLV_PADN: + break; + + case IPV6_TLV_JUMBO: + if (nh[off + 1] != 4 || (off & 3) != 2) + goto bad; + pkt_len = ntohl(*(__be32 *)(nh + off + 2)); + if (pkt_len <= IPV6_MAXPLEN || + ipv6_hdr(skb)->payload_len) + goto bad; + if (pkt_len > skb->len - sizeof(struct ipv6hdr)) + goto bad; + if (pskb_trim_rcsum(skb, + pkt_len + sizeof(struct ipv6hdr))) + goto bad; + nh = skb_network_header(skb); + break; + default: + if (optlen > len) + goto bad; + break; + } + off += optlen; + len -= optlen; + } + if (len == 0) + return 0; +bad: + return -1; +} + +int br_validate_ipv6(struct sk_buff *skb) +{ + const struct ipv6hdr *hdr; + struct net_device *dev = skb->dev; + struct inet6_dev *idev = __in6_dev_get(skb->dev); + u32 pkt_len; + u8 ip6h_len = sizeof(struct ipv6hdr); + + if (!pskb_may_pull(skb, ip6h_len)) + goto inhdr_error; + + if (skb->len < ip6h_len) + goto drop; + + hdr = ipv6_hdr(skb); + + if (hdr->version != 6) + goto inhdr_error; + + pkt_len = ntohs(hdr->payload_len); + + if (pkt_len || hdr->nexthdr != NEXTHDR_HOP) { + if (pkt_len + ip6h_len > skb->len) { + IP6_INC_STATS_BH(dev_net(dev), idev, + IPSTATS_MIB_INTRUNCATEDPKTS); + goto drop; + } + if (pskb_trim_rcsum(skb, pkt_len + ip6h_len)) { + IP6_INC_STATS_BH(dev_net(dev), idev, + IPSTATS_MIB_INDISCARDS); + goto drop; + } + } + if (hdr->nexthdr == NEXTHDR_HOP && br_nf_check_hbh_len(skb)) + goto drop; + + memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm)); + /* No IP options in IPv6 header; however it should be + * checked if some next headers need special treatment + */ + return 0; + +inhdr_error: + IP6_INC_STATS_BH(dev_net(dev), idev, IPSTATS_MIB_INHDRERRORS); +drop: + return -1; +} + +static inline bool +br_nf_ipv6_daddr_was_changed(const struct sk_buff *skb, + const struct nf_bridge_info *nf_bridge) +{ + return memcmp(&nf_bridge->ipv6_daddr, &ipv6_hdr(skb)->daddr, + sizeof(ipv6_hdr(skb)->daddr)) != 0; +} + +/* PF_BRIDGE/PRE_ROUTING: Undo the changes made for ip6tables + * PREROUTING and continue the bridge PRE_ROUTING hook. See comment + * for br_nf_pre_routing_finish(), same logic is used here but + * equivalent IPv6 function ip6_route_input() called indirectly. + */ +static int br_nf_pre_routing_finish_ipv6(struct sock *sk, struct sk_buff *skb) +{ + struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); + struct rtable *rt; + struct net_device *dev = skb->dev; + const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops(); + + nf_bridge->frag_max_size = IP6CB(skb)->frag_max_size; + + if (nf_bridge->pkt_otherhost) { + skb->pkt_type = PACKET_OTHERHOST; + nf_bridge->pkt_otherhost = false; + } + nf_bridge->mask &= ~BRNF_NF_BRIDGE_PREROUTING; + if (br_nf_ipv6_daddr_was_changed(skb, nf_bridge)) { + skb_dst_drop(skb); + v6ops->route_input(skb); + + if (skb_dst(skb)->error) { + kfree_skb(skb); + return 0; + } + + if (skb_dst(skb)->dev == dev) { + skb->dev = nf_bridge->physindev; + nf_bridge_update_protocol(skb); + nf_bridge_push_encap_header(skb); + NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, + sk, skb, skb->dev, NULL, + br_nf_pre_routing_finish_bridge, + 1); + return 0; + } + ether_addr_copy(eth_hdr(skb)->h_dest, dev->dev_addr); + skb->pkt_type = PACKET_HOST; + } else { + rt = bridge_parent_rtable(nf_bridge->physindev); + if (!rt) { + kfree_skb(skb); + return 0; + } + skb_dst_set_noref(skb, &rt->dst); + } + + skb->dev = nf_bridge->physindev; + nf_bridge_update_protocol(skb); + nf_bridge_push_encap_header(skb); + NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, sk, skb, + skb->dev, NULL, + br_handle_frame_finish, 1); + + return 0; +} + +/* Replicate the checks that IPv6 does on packet reception and pass the packet + * to ip6tables. + */ +unsigned int br_nf_pre_routing_ipv6(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct nf_bridge_info *nf_bridge; + + if (br_validate_ipv6(skb)) + return NF_DROP; + + nf_bridge_put(skb->nf_bridge); + if (!nf_bridge_alloc(skb)) + return NF_DROP; + if (!setup_pre_routing(skb)) + return NF_DROP; + + nf_bridge = nf_bridge_info_get(skb); + nf_bridge->ipv6_daddr = ipv6_hdr(skb)->daddr; + + skb->protocol = htons(ETH_P_IPV6); + NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, state->sk, skb, + skb->dev, NULL, + br_nf_pre_routing_finish_ipv6); + + return NF_STOLEN; +} diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 4b5c23699..4d74a0639 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -112,6 +112,8 @@ static inline size_t br_port_info_size(void) + nla_total_size(1) /* IFLA_BRPORT_FAST_LEAVE */ + nla_total_size(1) /* IFLA_BRPORT_LEARNING */ + nla_total_size(1) /* IFLA_BRPORT_UNICAST_FLOOD */ + + nla_total_size(1) /* IFLA_BRPORT_PROXYARP */ + + nla_total_size(1) /* IFLA_BRPORT_PROXYARP_WIFI */ + 0; } @@ -457,6 +459,8 @@ static int br_afspec(struct net_bridge *br, if (nla_len(attr) != sizeof(struct bridge_vlan_info)) return -EINVAL; vinfo = nla_data(attr); + if (!vinfo->vid || vinfo->vid >= VLAN_VID_MASK) + return -EINVAL; if (vinfo->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) { if (vinfo_start) return -EINVAL; @@ -504,6 +508,8 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_FAST_LEAVE]= { .type = NLA_U8 }, [IFLA_BRPORT_LEARNING] = { .type = NLA_U8 }, [IFLA_BRPORT_UNICAST_FLOOD] = { .type = NLA_U8 }, + [IFLA_BRPORT_PROXYARP] = { .type = NLA_U8 }, + [IFLA_BRPORT_PROXYARP_WIFI] = { .type = NLA_U8 }, }; /* Change the state of the port and notify spanning tree */ @@ -586,7 +592,7 @@ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags) struct nlattr *afspec; struct net_bridge_port *p; struct nlattr *tb[IFLA_BRPORT_MAX + 1]; - int err = 0, ret_offload = 0; + int err = 0; protinfo = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_PROTINFO); afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); @@ -628,16 +634,6 @@ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags) afspec, RTM_SETLINK); } - if (p && !(flags & BRIDGE_FLAGS_SELF)) { - /* set bridge attributes in hardware if supported - */ - ret_offload = netdev_switch_port_bridge_setlink(dev, nlh, - flags); - if (ret_offload && ret_offload != -EOPNOTSUPP) - br_warn(p->br, "error setting attrs on port %u(%s)\n", - (unsigned int)p->port_no, p->dev->name); - } - if (err == 0) br_ifinfo_notify(RTM_NEWLINK, p); out: @@ -649,7 +645,7 @@ int br_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags) { struct nlattr *afspec; struct net_bridge_port *p; - int err = 0, ret_offload = 0; + int err = 0; afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); if (!afspec) @@ -668,16 +664,6 @@ int br_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags) */ br_ifinfo_notify(RTM_NEWLINK, p); - if (p && !(flags & BRIDGE_FLAGS_SELF)) { - /* del bridge attributes in hardware - */ - ret_offload = netdev_switch_port_bridge_dellink(dev, nlh, - flags); - if (ret_offload && ret_offload != -EOPNOTSUPP) - br_warn(p->br, "error deleting attrs on port %u (%s)\n", - (unsigned int)p->port_no, p->dev->name); - } - return err; } static int br_validate(struct nlattr *tb[], struct nlattr *data[]) @@ -711,9 +697,17 @@ static int br_port_slave_changelink(struct net_device *brdev, struct nlattr *tb[], struct nlattr *data[]) { + struct net_bridge *br = netdev_priv(brdev); + int ret; + if (!data) return 0; - return br_setport(br_port_get_rtnl(dev), data); + + spin_lock_bh(&br->lock); + ret = br_setport(br_port_get_rtnl(dev), data); + spin_unlock_bh(&br->lock); + + return ret; } static int br_port_fill_slave_info(struct sk_buff *skb, diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 3362c2940..8b21146b2 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -18,6 +18,7 @@ #include <linux/netpoll.h> #include <linux/u64_stats_sync.h> #include <net/route.h> +#include <net/ip6_fib.h> #include <linux/if_vlan.h> #define BR_HASH_BITS 8 @@ -33,8 +34,8 @@ /* Control of forwarding link local multicast */ #define BR_GROUPFWD_DEFAULT 0 -/* Don't allow forwarding control protocols like STP and LLDP */ -#define BR_GROUPFWD_RESTRICTED 0x4007u +/* Don't allow forwarding of control protocols like STP, MAC PAUSE and LACP */ +#define BR_GROUPFWD_RESTRICTED 0x0007u /* The Nearest Customer Bridge Group Address, 01-80-C2-00-00-[00,0B,0C,0D,0F] */ #define BR_GROUPFWD_8021AD 0xB801u @@ -214,7 +215,10 @@ struct net_bridge spinlock_t hash_lock; struct hlist_head hash[BR_HASH_SIZE]; #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) - struct rtable fake_rtable; + union { + struct rtable fake_rtable; + struct rt6_info fake_rt6_info; + }; bool nf_call_iptables; bool nf_call_ip6tables; bool nf_call_arptables; @@ -304,7 +308,6 @@ struct br_input_skb_cb { int mrouters_only; #endif - u16 frag_max_size; bool proxyarp_replied; #ifdef CONFIG_BRIDGE_VLAN_FILTERING @@ -384,7 +387,7 @@ void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr); void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr); void br_fdb_cleanup(unsigned long arg); void br_fdb_delete_by_port(struct net_bridge *br, - const struct net_bridge_port *p, int do_all); + const struct net_bridge_port *p, u16 vid, int do_all); struct net_bridge_fdb_entry *__br_fdb_get(struct net_bridge *br, const unsigned char *addr, __u16 vid); int br_fdb_test_addr(struct net_device *dev, unsigned char *addr); diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index fb3ebe615..ed74ffaa8 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -39,10 +39,14 @@ void br_log_state(const struct net_bridge_port *p) void br_set_state(struct net_bridge_port *p, unsigned int state) { + struct switchdev_attr attr = { + .id = SWITCHDEV_ATTR_PORT_STP_STATE, + .u.stp_state = state, + }; int err; p->state = state; - err = netdev_switch_port_stp_update(p->dev, state); + err = switchdev_port_attr_set(p->dev, &attr); if (err && err != -EOPNOTSUPP) br_warn(p->br, "error setting offload STP state on port %u(%s)\n", (unsigned int) p->port_no, p->dev->name); @@ -205,8 +209,9 @@ void br_transmit_config(struct net_bridge_port *p) br_send_config_bpdu(p, &bpdu); p->topology_change_ack = 0; p->config_pending = 0; - mod_timer(&p->hold_timer, - round_jiffies(jiffies + BR_HOLD_TIME)); + if (p->br->stp_enabled == BR_KERNEL_STP) + mod_timer(&p->hold_timer, + round_jiffies(jiffies + BR_HOLD_TIME)); } } @@ -424,7 +429,6 @@ static void br_make_forwarding(struct net_bridge_port *p) else br_set_state(p, BR_STATE_LEARNING); - br_multicast_enable_port(p); br_log_state(p); br_ifinfo_notify(RTM_NEWLINK, p); @@ -458,6 +462,12 @@ void br_port_state_selection(struct net_bridge *br) } } + if (p->state != BR_STATE_BLOCKING) + br_multicast_enable_port(p); + /* Multicast is not disabled for the port when it goes in + * blocking state because the timers will expire and stop by + * themselves without sending more queries. + */ if (p->state == BR_STATE_FORWARDING) ++liveports; } diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index 7832d07f4..4ca449a16 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -48,7 +48,8 @@ void br_stp_enable_bridge(struct net_bridge *br) struct net_bridge_port *p; spin_lock_bh(&br->lock); - mod_timer(&br->hello_timer, jiffies + br->hello_time); + if (br->stp_enabled == BR_KERNEL_STP) + mod_timer(&br->hello_timer, jiffies + br->hello_time); mod_timer(&br->gc_timer, jiffies + HZ/10); br_config_bpdu_generation(br); @@ -111,7 +112,7 @@ void br_stp_disable_port(struct net_bridge_port *p) del_timer(&p->forward_delay_timer); del_timer(&p->hold_timer); - br_fdb_delete_by_port(br, p, 0); + br_fdb_delete_by_port(br, p, 0, 0); br_multicast_disable_port(p); br_configuration_update(br); @@ -127,6 +128,7 @@ static void br_stp_start(struct net_bridge *br) int r; char *argv[] = { BR_STP_PROG, br->dev->name, "start", NULL }; char *envp[] = { NULL }; + struct net_bridge_port *p; r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC); @@ -140,6 +142,10 @@ static void br_stp_start(struct net_bridge *br) if (r == 0) { br->stp_enabled = BR_USER_STP; br_debug(br, "userspace STP started\n"); + /* Stop hello and hold timers */ + del_timer(&br->hello_timer); + list_for_each_entry(p, &br->port_list, list) + del_timer(&p->hold_timer); } else { br->stp_enabled = BR_KERNEL_STP; br_debug(br, "using kernel STP\n"); @@ -156,12 +162,17 @@ static void br_stp_stop(struct net_bridge *br) int r; char *argv[] = { BR_STP_PROG, br->dev->name, "stop", NULL }; char *envp[] = { NULL }; + struct net_bridge_port *p; if (br->stp_enabled == BR_USER_STP) { r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC); br_info(br, "userspace STP stopped, return code %d\n", r); /* To start timers on any ports left in blocking */ + mod_timer(&br->hello_timer, jiffies + br->hello_time); + list_for_each_entry(p, &br->port_list, list) + mod_timer(&p->hold_timer, + round_jiffies(jiffies + BR_HOLD_TIME)); spin_lock_bh(&br->lock); br_port_state_selection(br); spin_unlock_bh(&br->lock); diff --git a/net/bridge/br_stp_timer.c b/net/bridge/br_stp_timer.c index 7caf7fae2..5f0f5af0e 100644 --- a/net/bridge/br_stp_timer.c +++ b/net/bridge/br_stp_timer.c @@ -40,7 +40,9 @@ static void br_hello_timer_expired(unsigned long arg) if (br->dev->flags & IFF_UP) { br_config_bpdu_generation(br); - mod_timer(&br->hello_timer, round_jiffies(jiffies + br->hello_time)); + if (br->stp_enabled != BR_USER_STP) + mod_timer(&br->hello_timer, + round_jiffies(jiffies + br->hello_time)); } spin_unlock(&br->lock); } diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index 4905845a9..efe415ad8 100644 --- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -160,7 +160,7 @@ static BRPORT_ATTR(hold_timer, S_IRUGO, show_hold_timer, NULL); static int store_flush(struct net_bridge_port *p, unsigned long v) { - br_fdb_delete_by_port(p->br, p, 0); // Don't delete local entry + br_fdb_delete_by_port(p->br, p, 0, 0); // Don't delete local entry return 0; } static BRPORT_ATTR(flush, S_IWUSR, NULL, store_flush); diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 13013fe8d..0d41f8183 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -2,6 +2,7 @@ #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/slab.h> +#include <net/switchdev.h> #include "br_private.h" @@ -36,6 +37,36 @@ static void __vlan_add_flags(struct net_port_vlans *v, u16 vid, u16 flags) clear_bit(vid, v->untagged_bitmap); } +static int __vlan_vid_add(struct net_device *dev, struct net_bridge *br, + u16 vid, u16 flags) +{ + const struct net_device_ops *ops = dev->netdev_ops; + int err; + + /* If driver uses VLAN ndo ops, use 8021q to install vid + * on device, otherwise try switchdev ops to install vid. + */ + + if (ops->ndo_vlan_rx_add_vid) { + err = vlan_vid_add(dev, br->vlan_proto, vid); + } else { + struct switchdev_obj vlan_obj = { + .id = SWITCHDEV_OBJ_PORT_VLAN, + .u.vlan = { + .flags = flags, + .vid_begin = vid, + .vid_end = vid, + }, + }; + + err = switchdev_port_obj_add(dev, &vlan_obj); + if (err == -EOPNOTSUPP) + err = 0; + } + + return err; +} + static int __vlan_add(struct net_port_vlans *v, u16 vid, u16 flags) { struct net_bridge_port *p = NULL; @@ -62,7 +93,7 @@ static int __vlan_add(struct net_port_vlans *v, u16 vid, u16 flags) * This ensures tagged traffic enters the bridge when * promiscuous mode is disabled by br_manage_promisc(). */ - err = vlan_vid_add(dev, br->vlan_proto, vid); + err = __vlan_vid_add(dev, br, vid, flags); if (err) return err; } @@ -86,6 +117,30 @@ out_filt: return err; } +static void __vlan_vid_del(struct net_device *dev, struct net_bridge *br, + u16 vid) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + /* If driver uses VLAN ndo ops, use 8021q to delete vid + * on device, otherwise try switchdev ops to delete vid. + */ + + if (ops->ndo_vlan_rx_kill_vid) { + vlan_vid_del(dev, br->vlan_proto, vid); + } else { + struct switchdev_obj vlan_obj = { + .id = SWITCHDEV_OBJ_PORT_VLAN, + .u.vlan = { + .vid_begin = vid, + .vid_end = vid, + }, + }; + + switchdev_port_obj_del(dev, &vlan_obj); + } +} + static int __vlan_del(struct net_port_vlans *v, u16 vid) { if (!test_bit(vid, v->vlan_bitmap)) @@ -96,7 +151,7 @@ static int __vlan_del(struct net_port_vlans *v, u16 vid) if (v->port_idx) { struct net_bridge_port *p = v->parent.port; - vlan_vid_del(p->dev, p->br->vlan_proto, vid); + __vlan_vid_del(p->dev, p->br, vid); } clear_bit(vid, v->vlan_bitmap); @@ -686,6 +741,7 @@ int nbp_vlan_delete(struct net_bridge_port *port, u16 vid) return -EINVAL; br_fdb_find_delete_local(port->br, port, port->dev->dev_addr, vid); + br_fdb_delete_by_port(port->br, port, vid, 0); return __vlan_del(pv, vid); } diff --git a/net/bridge/netfilter/ebt_stp.c b/net/bridge/netfilter/ebt_stp.c index 071d87214..0c4057006 100644 --- a/net/bridge/netfilter/ebt_stp.c +++ b/net/bridge/netfilter/ebt_stp.c @@ -164,8 +164,10 @@ static int ebt_stp_mt_check(const struct xt_mtchk_param *par) !(info->bitmask & EBT_STP_MASK)) return -EINVAL; /* Make sure the match only receives stp frames */ - if (!ether_addr_equal(e->destmac, bridge_ula) || - !ether_addr_equal(e->destmsk, msk) || !(e->bitmask & EBT_DESTMAC)) + if (!par->nft_compat && + (!ether_addr_equal(e->destmac, bridge_ula) || + !ether_addr_equal(e->destmsk, msk) || + !(e->bitmask & EBT_DESTMAC))) return -EINVAL; return 0; diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 91180a7fc..18ca4b24c 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -6,7 +6,7 @@ * * ebtables.c,v 2.0, July, 2002 * - * This code is stongly inspired on the iptables code which is + * This code is strongly inspired by the iptables code which is * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling * * This program is free software; you can redistribute it and/or @@ -139,7 +139,7 @@ ebt_basic_match(const struct ebt_entry *e, const struct sk_buff *skb, ethproto = h->h_proto; if (e->bitmask & EBT_802_3) { - if (FWINV2(ntohs(ethproto) >= ETH_P_802_3_MIN, EBT_IPROTO)) + if (FWINV2(eth_proto_is_802_3(ethproto), EBT_IPROTO)) return 1; } else if (!(e->bitmask & EBT_NOPROTO) && FWINV2(e->ethproto != ethproto, EBT_IPROTO)) |