diff options
Diffstat (limited to 'net/bridge')
-rw-r--r-- | net/bridge/Makefile | 5 | ||||
-rw-r--r-- | net/bridge/br_device.c | 9 | ||||
-rw-r--r-- | net/bridge/br_fdb.c | 36 | ||||
-rw-r--r-- | net/bridge/br_forward.c | 41 | ||||
-rw-r--r-- | net/bridge/br_if.c | 2 | ||||
-rw-r--r-- | net/bridge/br_input.c | 13 | ||||
-rw-r--r-- | net/bridge/br_ioctl.c | 2 | ||||
-rw-r--r-- | net/bridge/br_mdb.c | 2 | ||||
-rw-r--r-- | net/bridge/br_multicast.c | 147 | ||||
-rw-r--r-- | net/bridge/br_netlink.c | 148 | ||||
-rw-r--r-- | net/bridge/br_netlink_tunnel.c | 294 | ||||
-rw-r--r-- | net/bridge/br_private.h | 72 | ||||
-rw-r--r-- | net/bridge/br_private_tunnel.h | 83 | ||||
-rw-r--r-- | net/bridge/br_stp.c | 2 | ||||
-rw-r--r-- | net/bridge/br_stp_if.c | 4 | ||||
-rw-r--r-- | net/bridge/br_stp_timer.c | 2 | ||||
-rw-r--r-- | net/bridge/br_sysfs_br.c | 2 | ||||
-rw-r--r-- | net/bridge/br_sysfs_if.c | 2 | ||||
-rw-r--r-- | net/bridge/br_vlan.c | 24 | ||||
-rw-r--r-- | net/bridge/br_vlan_tunnel.c | 203 | ||||
-rw-r--r-- | net/bridge/netfilter/ebt_limit.c | 1 | ||||
-rw-r--r-- | net/bridge/netfilter/ebt_log.c | 2 | ||||
-rw-r--r-- | net/bridge/netfilter/ebtables.c | 78 |
23 files changed, 987 insertions, 187 deletions
diff --git a/net/bridge/Makefile b/net/bridge/Makefile index 0aefc011b668..40b1ede527ca 100644 --- a/net/bridge/Makefile +++ b/net/bridge/Makefile @@ -6,7 +6,8 @@ obj-$(CONFIG_BRIDGE) += bridge.o bridge-y := br.o br_device.o br_fdb.o br_forward.o br_if.o br_input.o \ br_ioctl.o br_stp.o br_stp_bpdu.o \ - br_stp_if.o br_stp_timer.o br_netlink.o + br_stp_if.o br_stp_timer.o br_netlink.o \ + br_netlink_tunnel.o bridge-$(CONFIG_SYSFS) += br_sysfs_if.o br_sysfs_br.o @@ -18,7 +19,7 @@ obj-$(CONFIG_BRIDGE_NETFILTER) += br_netfilter.o bridge-$(CONFIG_BRIDGE_IGMP_SNOOPING) += br_multicast.o br_mdb.o -bridge-$(CONFIG_BRIDGE_VLAN_FILTERING) += br_vlan.o +bridge-$(CONFIG_BRIDGE_VLAN_FILTERING) += br_vlan.o br_vlan_tunnel.o bridge-$(CONFIG_NET_SWITCHDEV) += br_switchdev.o diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index ed3b3192fb00..d208ee9ab60a 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -153,8 +153,8 @@ static int br_dev_stop(struct net_device *dev) return 0; } -static struct rtnl_link_stats64 *br_get_stats64(struct net_device *dev, - struct rtnl_link_stats64 *stats) +static void br_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *stats) { struct net_bridge *br = netdev_priv(dev); struct pcpu_sw_netstats tmp, sum = { 0 }; @@ -178,8 +178,6 @@ static struct rtnl_link_stats64 *br_get_stats64(struct net_device *dev, stats->tx_packets = sum.tx_packets; stats->rx_bytes = sum.rx_bytes; stats->rx_packets = sum.rx_packets; - - return stats; } static int br_change_mtu(struct net_device *dev, int new_mtu) @@ -349,8 +347,6 @@ static const struct net_device_ops br_netdev_ops = { .ndo_add_slave = br_add_slave, .ndo_del_slave = br_del_slave, .ndo_fix_features = br_fix_features, - .ndo_neigh_construct = netdev_default_l2upper_neigh_construct, - .ndo_neigh_destroy = netdev_default_l2upper_neigh_destroy, .ndo_fdb_add = br_fdb_add, .ndo_fdb_del = br_fdb_delete, .ndo_fdb_dump = br_fdb_dump, @@ -415,4 +411,5 @@ void br_dev_setup(struct net_device *dev) br_netfilter_rtable_init(br); br_stp_timer_init(br); br_multicast_init(br); + INIT_DELAYED_WORK(&br->gc_work, br_fdb_cleanup); } diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index e4a4176171c9..5693168e88b6 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -154,7 +154,7 @@ static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f) if (f->added_by_external_learn) fdb_del_external_learn(f); - hlist_del_rcu(&f->hlist); + hlist_del_init_rcu(&f->hlist); fdb_notify(br, f, RTM_DELNEIGH); call_rcu(&f->rcu, fdb_rcu_free); } @@ -290,34 +290,43 @@ out: spin_unlock_bh(&br->hash_lock); } -void br_fdb_cleanup(unsigned long _data) +void br_fdb_cleanup(struct work_struct *work) { - struct net_bridge *br = (struct net_bridge *)_data; + struct net_bridge *br = container_of(work, struct net_bridge, + gc_work.work); unsigned long delay = hold_time(br); - unsigned long next_timer = jiffies + br->ageing_time; + unsigned long work_delay = delay; + unsigned long now = jiffies; int i; - spin_lock(&br->hash_lock); for (i = 0; i < BR_HASH_SIZE; i++) { struct net_bridge_fdb_entry *f; struct hlist_node *n; + if (!br->hash[i].first) + continue; + + spin_lock_bh(&br->hash_lock); hlist_for_each_entry_safe(f, n, &br->hash[i], hlist) { unsigned long this_timer; + if (f->is_static) continue; if (f->added_by_external_learn) continue; this_timer = f->updated + delay; - if (time_before_eq(this_timer, jiffies)) + if (time_after(this_timer, now)) + work_delay = min(work_delay, this_timer - now); + else fdb_delete(br, f); - else if (time_before(this_timer, next_timer)) - next_timer = this_timer; } + spin_unlock_bh(&br->hash_lock); + cond_resched(); } - spin_unlock(&br->hash_lock); - mod_timer(&br->gc_timer, round_jiffies_up(next_timer)); + /* Cleanup minimum 10 milliseconds apart */ + work_delay = max_t(unsigned long, work_delay, msecs_to_jiffies(10)); + mod_delayed_work(system_long_wq, &br->gc_work, work_delay); } /* Completely flush all dynamic entries in forwarding database.*/ @@ -382,8 +391,6 @@ struct net_bridge_fdb_entry *__br_fdb_get(struct net_bridge *br, &br->hash[br_mac_hash(addr, vid)], hlist) { if (ether_addr_equal(fdb->addr.addr, addr) && fdb->vlan_id == vid) { - if (unlikely(has_expired(br, fdb))) - break; return fdb; } } @@ -585,12 +592,15 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, br_warn(br, "received packet on %s with own address as source address (addr:%pM, vlan:%u)\n", source->dev->name, addr, vid); } else { + unsigned long now = jiffies; + /* fastpath: update of existing entry */ if (unlikely(source != fdb->dst)) { fdb->dst = source; fdb_modified = true; } - fdb->updated = jiffies; + if (now != fdb->updated) + fdb->updated = now; if (unlikely(added_by_user)) fdb->added_by_user = 1; if (unlikely(fdb_modified)) diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 7cb41aee4c82..6bfac29318f2 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -80,7 +80,7 @@ static void __br_forward(const struct net_bridge_port *to, int br_hook; vg = nbp_vlan_group_rcu(to); - skb = br_handle_vlan(to->br, vg, skb); + skb = br_handle_vlan(to->br, to, vg, skb); if (!skb) return; @@ -220,6 +220,31 @@ out: } #ifdef CONFIG_BRIDGE_IGMP_SNOOPING +static void maybe_deliver_addr(struct net_bridge_port *p, struct sk_buff *skb, + const unsigned char *addr, bool local_orig) +{ + struct net_device *dev = BR_INPUT_SKB_CB(skb)->brdev; + const unsigned char *src = eth_hdr(skb)->h_source; + + if (!should_deliver(p, skb)) + return; + + /* Even with hairpin, no soliloquies - prevent breaking IPv6 DAD */ + if (skb->dev == p->dev && ether_addr_equal(src, addr)) + return; + + skb = skb_copy(skb, GFP_ATOMIC); + if (!skb) { + dev->stats.tx_dropped++; + return; + } + + if (!is_broadcast_ether_addr(addr)) + memcpy(eth_hdr(skb)->h_dest, addr, ETH_ALEN); + + __br_forward(p, skb, local_orig); +} + /* called with rcu_read_lock */ void br_multicast_flood(struct net_bridge_mdb_entry *mdst, struct sk_buff *skb, @@ -241,10 +266,20 @@ void br_multicast_flood(struct net_bridge_mdb_entry *mdst, rport = rp ? hlist_entry(rp, struct net_bridge_port, rlist) : NULL; - port = (unsigned long)lport > (unsigned long)rport ? - lport : rport; + if ((unsigned long)lport > (unsigned long)rport) { + port = lport; + + if (port->flags & BR_MULTICAST_TO_UNICAST) { + maybe_deliver_addr(lport, skb, p->eth_addr, + local_orig); + goto delivered; + } + } else { + port = rport; + } prev = maybe_deliver(prev, port, skb, local_orig); +delivered: if (IS_ERR(prev)) goto out; if (prev == port) diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index ed0dd3340084..8ac1770aa222 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -313,7 +313,7 @@ void br_dev_delete(struct net_device *dev, struct list_head *head) br_vlan_flush(br); br_multicast_dev_del(br); - del_timer_sync(&br->gc_timer); + cancel_delayed_work_sync(&br->gc_work); br_sysfs_delbr(br->dev); unregister_netdevice_queue(br->dev, head); diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 855b72fbe1da..4615a9b3e26c 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -21,6 +21,7 @@ #include <linux/export.h> #include <linux/rculist.h> #include "br_private.h" +#include "br_private_tunnel.h" /* Hook for brouter */ br_should_route_hook_t __rcu *br_should_route_hook __read_mostly; @@ -57,7 +58,7 @@ static int br_pass_frame_up(struct sk_buff *skb) indev = skb->dev; skb->dev = brdev; - skb = br_handle_vlan(br, vg, skb); + skb = br_handle_vlan(br, NULL, vg, skb); if (!skb) return NET_RX_DROP; /* update the multicast stats if the packet is IGMP/MLD */ @@ -194,10 +195,13 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb } if (dst) { + unsigned long now = jiffies; + if (dst->is_local) return br_pass_frame_up(skb); - dst->used = jiffies; + if (now != dst->used) + dst->used = now; br_forward(dst->dst, skb, local_rcv, false); } else { if (!mcast_hit) @@ -261,6 +265,11 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb) return RX_HANDLER_CONSUMED; p = br_port_get_rcu(skb->dev); + if (p->flags & BR_VLAN_TUNNEL) { + if (br_handle_ingress_vlan_tunnel(skb, p, + nbp_vlan_group_rcu(p))) + goto drop; + } if (unlikely(is_link_local_ether_addr(dest))) { u16 fwd_mask = p->br->group_fwd_mask_required; diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c index da8157c57eb1..7970f8540cbb 100644 --- a/net/bridge/br_ioctl.c +++ b/net/bridge/br_ioctl.c @@ -149,7 +149,7 @@ static int old_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) b.hello_timer_value = br_timer_value(&br->hello_timer); b.tcn_timer_value = br_timer_value(&br->tcn_timer); b.topology_change_timer_value = br_timer_value(&br->topology_change_timer); - b.gc_timer_value = br_timer_value(&br->gc_timer); + b.gc_timer_value = br_timer_value(&br->gc_work.timer); rcu_read_unlock(); if (copy_to_user((void __user *)args[1], &b, sizeof(b))) diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 7dbc80d01eb0..056e6ac49d8f 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -531,7 +531,7 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, break; } - p = br_multicast_new_port_group(port, group, *pp, state); + p = br_multicast_new_port_group(port, group, *pp, state, NULL); if (unlikely(!p)) return -ENOMEM; rcu_assign_pointer(*pp, p); diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index b30e77e8427c..b760f2620abf 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -27,6 +27,7 @@ #include <linux/inetdevice.h> #include <linux/mroute.h> #include <net/ip.h> +#include <net/switchdev.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> #include <net/mld.h> @@ -43,12 +44,15 @@ static void br_multicast_add_router(struct net_bridge *br, static void br_ip4_multicast_leave_group(struct net_bridge *br, struct net_bridge_port *port, __be32 group, - __u16 vid); + __u16 vid, + const unsigned char *src); + +static void __del_port_router(struct net_bridge_port *p); #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); + __u16 vid, const unsigned char *src); #endif unsigned int br_mdb_rehash_seq; @@ -540,7 +544,7 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, break; case 2: mld2q = (struct mld2_query *)icmp6_hdr(skb); - mld2q->mld2q_mrc = ntohs((u16)jiffies_to_msecs(interval)); + mld2q->mld2q_mrc = htons((u16)jiffies_to_msecs(interval)); mld2q->mld2q_type = ICMPV6_MGM_QUERY; mld2q->mld2q_code = 0; mld2q->mld2q_cksum = 0; @@ -711,7 +715,8 @@ 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 flags) + unsigned char flags, + const unsigned char *src) { struct net_bridge_port_group *p; @@ -726,12 +731,32 @@ struct net_bridge_port_group *br_multicast_new_port_group( hlist_add_head(&p->mglist, &port->mglist); setup_timer(&p->timer, br_multicast_port_group_expired, (unsigned long)p); + + if (src) + memcpy(p->eth_addr, src, ETH_ALEN); + else + memset(p->eth_addr, 0xff, ETH_ALEN); + return p; } +static bool br_port_group_equal(struct net_bridge_port_group *p, + struct net_bridge_port *port, + const unsigned char *src) +{ + if (p->port != port) + return false; + + if (!(port->flags & BR_MULTICAST_TO_UNICAST)) + return true; + + return ether_addr_equal(src, p->eth_addr); +} + static int br_multicast_add_group(struct net_bridge *br, struct net_bridge_port *port, - struct br_ip *group) + struct br_ip *group, + const unsigned char *src) { struct net_bridge_port_group __rcu **pp; struct net_bridge_port_group *p; @@ -758,13 +783,13 @@ static int br_multicast_add_group(struct net_bridge *br, for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL; pp = &p->next) { - if (p->port == port) + if (br_port_group_equal(p, port, src)) goto found; if ((unsigned long)p->port < (unsigned long)port) break; } - p = br_multicast_new_port_group(port, group, *pp, 0); + p = br_multicast_new_port_group(port, group, *pp, 0, src); if (unlikely(!p)) goto err; rcu_assign_pointer(*pp, p); @@ -783,7 +808,8 @@ err: static int br_ip4_multicast_add_group(struct net_bridge *br, struct net_bridge_port *port, __be32 group, - __u16 vid) + __u16 vid, + const unsigned char *src) { struct br_ip br_group; @@ -794,14 +820,15 @@ static int br_ip4_multicast_add_group(struct net_bridge *br, br_group.proto = htons(ETH_P_IP); br_group.vid = vid; - return br_multicast_add_group(br, port, &br_group); + return br_multicast_add_group(br, port, &br_group, src); } #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, - __u16 vid) + __u16 vid, + const unsigned char *src) { struct br_ip br_group; @@ -812,7 +839,7 @@ static int br_ip6_multicast_add_group(struct net_bridge *br, br_group.proto = htons(ETH_P_IPV6); br_group.vid = vid; - return br_multicast_add_group(br, port, &br_group); + return br_multicast_add_group(br, port, &br_group, src); } #endif @@ -824,16 +851,10 @@ static void br_multicast_router_expired(unsigned long data) spin_lock(&br->multicast_lock); if (port->multicast_router == MDB_RTR_TYPE_DISABLED || port->multicast_router == MDB_RTR_TYPE_PERM || - timer_pending(&port->multicast_router_timer) || - hlist_unhashed(&port->rlist)) + timer_pending(&port->multicast_router_timer)) goto out; - hlist_del_init_rcu(&port->rlist); - br_rtr_notify(br->dev, port, RTM_DELMDB); - /* Don't allow timer refresh if the router expired */ - if (port->multicast_router == MDB_RTR_TYPE_TEMP) - port->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; - + __del_port_router(port); out: spin_unlock(&br->multicast_lock); } @@ -982,6 +1003,18 @@ static void br_ip6_multicast_port_query_expired(unsigned long data) } #endif +static void br_mc_disabled_update(struct net_device *dev, bool value) +{ + struct switchdev_attr attr = { + .orig_dev = dev, + .id = SWITCHDEV_ATTR_ID_BRIDGE_MC_DISABLED, + .flags = SWITCHDEV_F_DEFER, + .u.mc_disabled = value, + }; + + switchdev_port_attr_set(dev, &attr); +} + int br_multicast_add_port(struct net_bridge_port *port) { port->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; @@ -994,6 +1027,8 @@ int br_multicast_add_port(struct net_bridge_port *port) setup_timer(&port->ip6_own_query.timer, br_ip6_multicast_port_query_expired, (unsigned long)port); #endif + br_mc_disabled_update(port->dev, port->br->multicast_disabled); + port->mcast_stats = netdev_alloc_pcpu_stats(struct bridge_mcast_stats); if (!port->mcast_stats) return -ENOMEM; @@ -1061,13 +1096,8 @@ void br_multicast_disable_port(struct net_bridge_port *port) if (!(pg->flags & MDB_PG_FLAGS_PERMANENT)) br_multicast_del_pg(br, pg); - if (!hlist_unhashed(&port->rlist)) { - hlist_del_init_rcu(&port->rlist); - br_rtr_notify(br->dev, port, RTM_DELMDB); - /* Don't allow timer refresh if disabling */ - if (port->multicast_router == MDB_RTR_TYPE_TEMP) - port->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; - } + __del_port_router(port); + del_timer(&port->multicast_router_timer); del_timer(&port->ip4_own_query.timer); #if IS_ENABLED(CONFIG_IPV6) @@ -1081,6 +1111,7 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br, struct sk_buff *skb, u16 vid) { + const unsigned char *src; struct igmpv3_report *ih; struct igmpv3_grec *grec; int i; @@ -1121,12 +1152,14 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br, continue; } + src = eth_hdr(skb)->h_source; 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); + br_ip4_multicast_leave_group(br, port, group, vid, src); } else { - err = br_ip4_multicast_add_group(br, port, group, vid); + err = br_ip4_multicast_add_group(br, port, group, vid, + src); if (err) break; } @@ -1141,6 +1174,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, struct sk_buff *skb, u16 vid) { + const unsigned char *src; struct icmp6hdr *icmp6h; struct mld2_grec *grec; int i; @@ -1188,14 +1222,16 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, continue; } + src = eth_hdr(skb)->h_source; 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); + vid, src); } else { err = br_ip6_multicast_add_group(br, port, - &grec->grec_mca, vid); + &grec->grec_mca, vid, + src); if (err) break; } @@ -1281,6 +1317,19 @@ br_multicast_update_query_timer(struct net_bridge *br, mod_timer(&query->timer, jiffies + br->multicast_querier_interval); } +static void br_port_mc_router_state_change(struct net_bridge_port *p, + bool is_mc_router) +{ + struct switchdev_attr attr = { + .orig_dev = p->dev, + .id = SWITCHDEV_ATTR_ID_PORT_MROUTER, + .flags = SWITCHDEV_F_DEFER, + .u.mrouter = is_mc_router, + }; + + switchdev_port_attr_set(p->dev, &attr); +} + /* * Add port to router_list * list is maintained ordered by pointer value @@ -1306,6 +1355,7 @@ static void br_multicast_add_router(struct net_bridge *br, else hlist_add_head_rcu(&port->rlist, &br->router_list); br_rtr_notify(br->dev, port, RTM_NEWMDB); + br_port_mc_router_state_change(port, true); } static void br_multicast_mark_router(struct net_bridge *br, @@ -1511,7 +1561,8 @@ 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 bridge_mcast_own_query *own_query, + const unsigned char *src) { struct net_bridge_mdb_htable *mdb; struct net_bridge_mdb_entry *mp; @@ -1535,7 +1586,7 @@ br_multicast_leave_group(struct net_bridge *br, for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL; pp = &p->next) { - if (p->port != port) + if (!br_port_group_equal(p, port, src)) continue; rcu_assign_pointer(*pp, p->next); @@ -1566,7 +1617,7 @@ br_multicast_leave_group(struct net_bridge *br, for (p = mlock_dereference(mp->ports, br); p != NULL; p = mlock_dereference(p->next, br)) { - if (p->port != port) + if (!br_port_group_equal(p, port, src)) continue; if (!hlist_unhashed(&p->mglist) && @@ -1617,7 +1668,8 @@ out: static void br_ip4_multicast_leave_group(struct net_bridge *br, struct net_bridge_port *port, __be32 group, - __u16 vid) + __u16 vid, + const unsigned char *src) { struct br_ip br_group; struct bridge_mcast_own_query *own_query; @@ -1632,14 +1684,15 @@ static void br_ip4_multicast_leave_group(struct net_bridge *br, br_group.vid = vid; br_multicast_leave_group(br, port, &br_group, &br->ip4_other_query, - own_query); + own_query, src); } #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) + __u16 vid, + const unsigned char *src) { struct br_ip br_group; struct bridge_mcast_own_query *own_query; @@ -1654,7 +1707,7 @@ static void br_ip6_multicast_leave_group(struct net_bridge *br, br_group.vid = vid; br_multicast_leave_group(br, port, &br_group, &br->ip6_other_query, - own_query); + own_query, src); } #endif @@ -1712,6 +1765,7 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, u16 vid) { struct sk_buff *skb_trimmed = NULL; + const unsigned char *src; struct igmphdr *ih; int err; @@ -1731,13 +1785,14 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, } ih = igmp_hdr(skb); + src = eth_hdr(skb)->h_source; BR_INPUT_SKB_CB(skb)->igmp = ih->type; switch (ih->type) { case IGMP_HOST_MEMBERSHIP_REPORT: case IGMPV2_HOST_MEMBERSHIP_REPORT: BR_INPUT_SKB_CB(skb)->mrouters_only = 1; - err = br_ip4_multicast_add_group(br, port, ih->group, vid); + err = br_ip4_multicast_add_group(br, port, ih->group, vid, src); break; case IGMPV3_HOST_MEMBERSHIP_REPORT: err = br_ip4_multicast_igmp3_report(br, port, skb_trimmed, vid); @@ -1746,7 +1801,7 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, 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); + br_ip4_multicast_leave_group(br, port, ih->group, vid, src); break; } @@ -1766,6 +1821,7 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, u16 vid) { struct sk_buff *skb_trimmed = NULL; + const unsigned char *src; struct mld_msg *mld; int err; @@ -1785,8 +1841,10 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, switch (mld->mld_type) { case ICMPV6_MGM_REPORT: + src = eth_hdr(skb)->h_source; BR_INPUT_SKB_CB(skb)->mrouters_only = 1; - err = br_ip6_multicast_add_group(br, port, &mld->mld_mca, vid); + err = br_ip6_multicast_add_group(br, port, &mld->mld_mca, vid, + src); break; case ICMPV6_MLD2_REPORT: err = br_ip6_multicast_mld2_report(br, port, skb_trimmed, vid); @@ -1795,7 +1853,8 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, err = br_ip6_multicast_query(br, port, skb_trimmed, vid); break; case ICMPV6_MGM_REDUCTION: - br_ip6_multicast_leave_group(br, port, &mld->mld_mca, vid); + src = eth_hdr(skb)->h_source; + br_ip6_multicast_leave_group(br, port, &mld->mld_mca, vid, src); break; } @@ -2004,6 +2063,11 @@ static void __del_port_router(struct net_bridge_port *p) return; hlist_del_init_rcu(&p->rlist); br_rtr_notify(p->br->dev, p, RTM_DELMDB); + br_port_mc_router_state_change(p, false); + + /* don't allow timer refresh */ + if (p->multicast_router == MDB_RTR_TYPE_TEMP) + p->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; } int br_multicast_set_port_router(struct net_bridge_port *p, unsigned long val) @@ -2081,6 +2145,7 @@ int br_multicast_toggle(struct net_bridge *br, unsigned long val) if (br->multicast_disabled == !val) goto unlock; + br_mc_disabled_update(br->dev, !val); br->multicast_disabled = !val; if (br->multicast_disabled) goto unlock; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 7109b389ea58..a8f6acd23e30 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -20,6 +20,7 @@ #include "br_private.h" #include "br_private_stp.h" +#include "br_private_tunnel.h" static int __get_num_vlan_infos(struct net_bridge_vlan_group *vg, u32 filter_mask) @@ -95,9 +96,10 @@ static size_t br_get_link_af_size_filtered(const struct net_device *dev, u32 filter_mask) { struct net_bridge_vlan_group *vg = NULL; - struct net_bridge_port *p; + struct net_bridge_port *p = NULL; struct net_bridge *br; int num_vlan_infos; + size_t vinfo_sz = 0; rcu_read_lock(); if (br_port_exists(dev)) { @@ -110,8 +112,13 @@ static size_t br_get_link_af_size_filtered(const struct net_device *dev, num_vlan_infos = br_get_num_vlan_infos(vg, filter_mask); rcu_read_unlock(); + if (p && (p->flags & BR_VLAN_TUNNEL)) + vinfo_sz += br_get_vlan_tunnel_info_size(vg); + /* Each VLAN is returned in bridge_vlan_info along with flags */ - return num_vlan_infos * nla_total_size(sizeof(struct bridge_vlan_info)); + vinfo_sz += num_vlan_infos * nla_total_size(sizeof(struct bridge_vlan_info)); + + return vinfo_sz; } static inline size_t br_port_info_size(void) @@ -123,10 +130,12 @@ static inline size_t br_port_info_size(void) + nla_total_size(1) /* IFLA_BRPORT_GUARD */ + nla_total_size(1) /* IFLA_BRPORT_PROTECT */ + nla_total_size(1) /* IFLA_BRPORT_FAST_LEAVE */ + + nla_total_size(1) /* IFLA_BRPORT_MCAST_TO_UCAST */ + 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 */ + + nla_total_size(1) /* IFLA_BRPORT_VLAN_TUNNEL */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_ROOT_ID */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_BRIDGE_ID */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_PORT */ @@ -173,6 +182,8 @@ static int br_port_fill_attrs(struct sk_buff *skb, !!(p->flags & BR_ROOT_BLOCK)) || nla_put_u8(skb, IFLA_BRPORT_FAST_LEAVE, !!(p->flags & BR_MULTICAST_FAST_LEAVE)) || + nla_put_u8(skb, IFLA_BRPORT_MCAST_TO_UCAST, + !!(p->flags & BR_MULTICAST_TO_UNICAST)) || nla_put_u8(skb, IFLA_BRPORT_LEARNING, !!(p->flags & BR_LEARNING)) || nla_put_u8(skb, IFLA_BRPORT_UNICAST_FLOOD, !!(p->flags & BR_FLOOD)) || @@ -191,7 +202,9 @@ static int br_port_fill_attrs(struct sk_buff *skb, nla_put_u16(skb, IFLA_BRPORT_NO, p->port_no) || nla_put_u8(skb, IFLA_BRPORT_TOPOLOGY_CHANGE_ACK, p->topology_change_ack) || - nla_put_u8(skb, IFLA_BRPORT_CONFIG_PENDING, p->config_pending)) + nla_put_u8(skb, IFLA_BRPORT_CONFIG_PENDING, p->config_pending) || + nla_put_u8(skb, IFLA_BRPORT_VLAN_TUNNEL, !!(p->flags & + BR_VLAN_TUNNEL))) return -EMSGSIZE; timerval = br_timer_value(&p->message_age_timer); @@ -414,6 +427,9 @@ static int br_fill_ifinfo(struct sk_buff *skb, err = br_fill_ifvlaninfo_compressed(skb, vg); else err = br_fill_ifvlaninfo(skb, vg); + + if (port && (port->flags & BR_VLAN_TUNNEL)) + err = br_fill_vlan_tunnel_info(skb, vg); rcu_read_unlock(); if (err) goto nla_put_failure; @@ -514,60 +530,88 @@ static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p, return err; } +static int br_process_vlan_info(struct net_bridge *br, + struct net_bridge_port *p, int cmd, + struct bridge_vlan_info *vinfo_curr, + struct bridge_vlan_info **vinfo_last) +{ + if (!vinfo_curr->vid || vinfo_curr->vid >= VLAN_VID_MASK) + return -EINVAL; + + if (vinfo_curr->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) { + /* check if we are already processing a range */ + if (*vinfo_last) + return -EINVAL; + *vinfo_last = vinfo_curr; + /* don't allow range of pvids */ + if ((*vinfo_last)->flags & BRIDGE_VLAN_INFO_PVID) + return -EINVAL; + return 0; + } + + if (*vinfo_last) { + struct bridge_vlan_info tmp_vinfo; + int v, err; + + if (!(vinfo_curr->flags & BRIDGE_VLAN_INFO_RANGE_END)) + return -EINVAL; + + if (vinfo_curr->vid <= (*vinfo_last)->vid) + return -EINVAL; + + memcpy(&tmp_vinfo, *vinfo_last, + sizeof(struct bridge_vlan_info)); + for (v = (*vinfo_last)->vid; v <= vinfo_curr->vid; v++) { + tmp_vinfo.vid = v; + err = br_vlan_info(br, p, cmd, &tmp_vinfo); + if (err) + break; + } + *vinfo_last = NULL; + + return 0; + } + + return br_vlan_info(br, p, cmd, vinfo_curr); +} + static int br_afspec(struct net_bridge *br, struct net_bridge_port *p, struct nlattr *af_spec, int cmd) { - struct bridge_vlan_info *vinfo_start = NULL; - struct bridge_vlan_info *vinfo = NULL; + struct bridge_vlan_info *vinfo_curr = NULL; + struct bridge_vlan_info *vinfo_last = NULL; struct nlattr *attr; - int err = 0; - int rem; + struct vtunnel_info tinfo_last = {}; + struct vtunnel_info tinfo_curr = {}; + int err = 0, rem; nla_for_each_nested(attr, af_spec, rem) { - if (nla_type(attr) != IFLA_BRIDGE_VLAN_INFO) - continue; - 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; - vinfo_start = vinfo; - /* don't allow range of pvids */ - if (vinfo_start->flags & BRIDGE_VLAN_INFO_PVID) - return -EINVAL; - continue; - } - - if (vinfo_start) { - struct bridge_vlan_info tmp_vinfo; - int v; - - if (!(vinfo->flags & BRIDGE_VLAN_INFO_RANGE_END)) + err = 0; + switch (nla_type(attr)) { + case IFLA_BRIDGE_VLAN_TUNNEL_INFO: + if (!(p->flags & BR_VLAN_TUNNEL)) return -EINVAL; - - if (vinfo->vid <= vinfo_start->vid) + err = br_parse_vlan_tunnel_info(attr, &tinfo_curr); + if (err) + return err; + err = br_process_vlan_tunnel_info(br, p, cmd, + &tinfo_curr, + &tinfo_last); + if (err) + return err; + break; + case IFLA_BRIDGE_VLAN_INFO: + if (nla_len(attr) != sizeof(struct bridge_vlan_info)) return -EINVAL; - - memcpy(&tmp_vinfo, vinfo_start, - sizeof(struct bridge_vlan_info)); - - for (v = vinfo_start->vid; v <= vinfo->vid; v++) { - tmp_vinfo.vid = v; - err = br_vlan_info(br, p, cmd, &tmp_vinfo); - if (err) - break; - } - vinfo_start = NULL; - } else { - err = br_vlan_info(br, p, cmd, vinfo); - } - if (err) + vinfo_curr = nla_data(attr); + err = br_process_vlan_info(br, p, cmd, vinfo_curr, + &vinfo_last); + if (err) + return err; break; + } } return err; @@ -586,6 +630,7 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_PROXYARP] = { .type = NLA_U8 }, [IFLA_BRPORT_PROXYARP_WIFI] = { .type = NLA_U8 }, [IFLA_BRPORT_MULTICAST_ROUTER] = { .type = NLA_U8 }, + [IFLA_BRPORT_MCAST_TO_UCAST] = { .type = NLA_U8 }, }; /* Change the state of the port and notify spanning tree */ @@ -626,8 +671,9 @@ static void br_set_port_flag(struct net_bridge_port *p, struct nlattr *tb[], /* Process bridge protocol info on port */ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[]) { - int err; unsigned long old_flags = p->flags; + bool br_vlan_tunnel_old = false; + int err; br_set_port_flag(p, tb, IFLA_BRPORT_MODE, BR_HAIRPIN_MODE); br_set_port_flag(p, tb, IFLA_BRPORT_GUARD, BR_BPDU_GUARD); @@ -636,9 +682,15 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[]) br_set_port_flag(p, tb, IFLA_BRPORT_LEARNING, BR_LEARNING); br_set_port_flag(p, tb, IFLA_BRPORT_UNICAST_FLOOD, BR_FLOOD); br_set_port_flag(p, tb, IFLA_BRPORT_MCAST_FLOOD, BR_MCAST_FLOOD); + br_set_port_flag(p, tb, IFLA_BRPORT_MCAST_TO_UCAST, BR_MULTICAST_TO_UNICAST); br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP, BR_PROXYARP); br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP_WIFI, BR_PROXYARP_WIFI); + br_vlan_tunnel_old = (p->flags & BR_VLAN_TUNNEL) ? true : false; + br_set_port_flag(p, tb, IFLA_BRPORT_VLAN_TUNNEL, BR_VLAN_TUNNEL); + if (br_vlan_tunnel_old && !(p->flags & BR_VLAN_TUNNEL)) + nbp_vlan_tunnel_info_flush(p); + if (tb[IFLA_BRPORT_COST]) { err = br_stp_set_path_cost(p, nla_get_u32(tb[IFLA_BRPORT_COST])); if (err) @@ -1195,7 +1247,7 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) if (nla_put_u64_64bit(skb, IFLA_BR_TOPOLOGY_CHANGE_TIMER, clockval, IFLA_BR_PAD)) return -EMSGSIZE; - clockval = br_timer_value(&br->gc_timer); + clockval = br_timer_value(&br->gc_work.timer); if (nla_put_u64_64bit(skb, IFLA_BR_GC_TIMER, clockval, IFLA_BR_PAD)) return -EMSGSIZE; diff --git a/net/bridge/br_netlink_tunnel.c b/net/bridge/br_netlink_tunnel.c new file mode 100644 index 000000000000..c913491495ab --- /dev/null +++ b/net/bridge/br_netlink_tunnel.c @@ -0,0 +1,294 @@ +/* + * Bridge per vlan tunnel port dst_metadata netlink control interface + * + * Authors: + * Roopa Prabhu <roopa@cumulusnetworks.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/etherdevice.h> +#include <net/rtnetlink.h> +#include <net/net_namespace.h> +#include <net/sock.h> +#include <uapi/linux/if_bridge.h> +#include <net/dst_metadata.h> + +#include "br_private.h" +#include "br_private_tunnel.h" + +static size_t __get_vlan_tinfo_size(void) +{ + return nla_total_size(0) + /* nest IFLA_BRIDGE_VLAN_TUNNEL_INFO */ + nla_total_size(sizeof(u32)) + /* IFLA_BRIDGE_VLAN_TUNNEL_ID */ + nla_total_size(sizeof(u16)) + /* IFLA_BRIDGE_VLAN_TUNNEL_VID */ + nla_total_size(sizeof(u16)); /* IFLA_BRIDGE_VLAN_TUNNEL_FLAGS */ +} + +static bool vlan_tunid_inrange(struct net_bridge_vlan *v_curr, + struct net_bridge_vlan *v_last) +{ + __be32 tunid_curr = tunnel_id_to_key32(v_curr->tinfo.tunnel_id); + __be32 tunid_last = tunnel_id_to_key32(v_last->tinfo.tunnel_id); + + return (be32_to_cpu(tunid_curr) - be32_to_cpu(tunid_last)) == 1; +} + +static int __get_num_vlan_tunnel_infos(struct net_bridge_vlan_group *vg) +{ + struct net_bridge_vlan *v, *vtbegin = NULL, *vtend = NULL; + int num_tinfos = 0; + + /* Count number of vlan infos */ + list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { + /* only a context, bridge vlan not activated */ + if (!br_vlan_should_use(v) || !v->tinfo.tunnel_id) + continue; + + if (!vtbegin) { + goto initvars; + } else if ((v->vid - vtend->vid) == 1 && + vlan_tunid_inrange(v, vtend)) { + vtend = v; + continue; + } else { + if ((vtend->vid - vtbegin->vid) > 0) + num_tinfos += 2; + else + num_tinfos += 1; + } +initvars: + vtbegin = v; + vtend = v; + } + + if (vtbegin && vtend) { + if ((vtend->vid - vtbegin->vid) > 0) + num_tinfos += 2; + else + num_tinfos += 1; + } + + return num_tinfos; +} + +int br_get_vlan_tunnel_info_size(struct net_bridge_vlan_group *vg) +{ + int num_tinfos; + + if (!vg) + return 0; + + rcu_read_lock(); + num_tinfos = __get_num_vlan_tunnel_infos(vg); + rcu_read_unlock(); + + return num_tinfos * __get_vlan_tinfo_size(); +} + +static int br_fill_vlan_tinfo(struct sk_buff *skb, u16 vid, + __be64 tunnel_id, u16 flags) +{ + __be32 tid = tunnel_id_to_key32(tunnel_id); + struct nlattr *tmap; + + tmap = nla_nest_start(skb, IFLA_BRIDGE_VLAN_TUNNEL_INFO); + if (!tmap) + return -EMSGSIZE; + if (nla_put_u32(skb, IFLA_BRIDGE_VLAN_TUNNEL_ID, + be32_to_cpu(tid))) + goto nla_put_failure; + if (nla_put_u16(skb, IFLA_BRIDGE_VLAN_TUNNEL_VID, + vid)) + goto nla_put_failure; + if (nla_put_u16(skb, IFLA_BRIDGE_VLAN_TUNNEL_FLAGS, + flags)) + goto nla_put_failure; + nla_nest_end(skb, tmap); + + return 0; + +nla_put_failure: + nla_nest_cancel(skb, tmap); + + return -EMSGSIZE; +} + +static int br_fill_vlan_tinfo_range(struct sk_buff *skb, + struct net_bridge_vlan *vtbegin, + struct net_bridge_vlan *vtend) +{ + int err; + + if (vtend && (vtend->vid - vtbegin->vid) > 0) { + /* add range to skb */ + err = br_fill_vlan_tinfo(skb, vtbegin->vid, + vtbegin->tinfo.tunnel_id, + BRIDGE_VLAN_INFO_RANGE_BEGIN); + if (err) + return err; + + err = br_fill_vlan_tinfo(skb, vtend->vid, + vtend->tinfo.tunnel_id, + BRIDGE_VLAN_INFO_RANGE_END); + if (err) + return err; + } else { + err = br_fill_vlan_tinfo(skb, vtbegin->vid, + vtbegin->tinfo.tunnel_id, + 0); + if (err) + return err; + } + + return 0; +} + +int br_fill_vlan_tunnel_info(struct sk_buff *skb, + struct net_bridge_vlan_group *vg) +{ + struct net_bridge_vlan *vtbegin = NULL; + struct net_bridge_vlan *vtend = NULL; + struct net_bridge_vlan *v; + int err; + + /* Count number of vlan infos */ + list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { + /* only a context, bridge vlan not activated */ + if (!br_vlan_should_use(v)) + continue; + + if (!v->tinfo.tunnel_dst) + continue; + + if (!vtbegin) { + goto initvars; + } else if ((v->vid - vtend->vid) == 1 && + vlan_tunid_inrange(v, vtend)) { + vtend = v; + continue; + } else { + err = br_fill_vlan_tinfo_range(skb, vtbegin, vtend); + if (err) + return err; + } +initvars: + vtbegin = v; + vtend = v; + } + + if (vtbegin) { + err = br_fill_vlan_tinfo_range(skb, vtbegin, vtend); + if (err) + return err; + } + + return 0; +} + +static const struct nla_policy vlan_tunnel_policy[IFLA_BRIDGE_VLAN_TUNNEL_MAX + 1] = { + [IFLA_BRIDGE_VLAN_TUNNEL_ID] = { .type = NLA_U32 }, + [IFLA_BRIDGE_VLAN_TUNNEL_VID] = { .type = NLA_U16 }, + [IFLA_BRIDGE_VLAN_TUNNEL_FLAGS] = { .type = NLA_U16 }, +}; + +static int br_vlan_tunnel_info(struct net_bridge_port *p, int cmd, + u16 vid, u32 tun_id) +{ + int err = 0; + + if (!p) + return -EINVAL; + + switch (cmd) { + case RTM_SETLINK: + err = nbp_vlan_tunnel_info_add(p, vid, tun_id); + break; + case RTM_DELLINK: + nbp_vlan_tunnel_info_delete(p, vid); + break; + } + + return err; +} + +int br_parse_vlan_tunnel_info(struct nlattr *attr, + struct vtunnel_info *tinfo) +{ + struct nlattr *tb[IFLA_BRIDGE_VLAN_TUNNEL_MAX + 1]; + u32 tun_id; + u16 vid, flags = 0; + int err; + + memset(tinfo, 0, sizeof(*tinfo)); + + err = nla_parse_nested(tb, IFLA_BRIDGE_VLAN_TUNNEL_MAX, + attr, vlan_tunnel_policy); + if (err < 0) + return err; + + if (!tb[IFLA_BRIDGE_VLAN_TUNNEL_ID] || + !tb[IFLA_BRIDGE_VLAN_TUNNEL_VID]) + return -EINVAL; + + tun_id = nla_get_u32(tb[IFLA_BRIDGE_VLAN_TUNNEL_ID]); + vid = nla_get_u16(tb[IFLA_BRIDGE_VLAN_TUNNEL_VID]); + if (vid >= VLAN_VID_MASK) + return -ERANGE; + + if (tb[IFLA_BRIDGE_VLAN_TUNNEL_FLAGS]) + flags = nla_get_u16(tb[IFLA_BRIDGE_VLAN_TUNNEL_FLAGS]); + + tinfo->tunid = tun_id; + tinfo->vid = vid; + tinfo->flags = flags; + + return 0; +} + +int br_process_vlan_tunnel_info(struct net_bridge *br, + struct net_bridge_port *p, int cmd, + struct vtunnel_info *tinfo_curr, + struct vtunnel_info *tinfo_last) +{ + int err; + + if (tinfo_curr->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) { + if (tinfo_last->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) + return -EINVAL; + memcpy(tinfo_last, tinfo_curr, sizeof(struct vtunnel_info)); + } else if (tinfo_curr->flags & BRIDGE_VLAN_INFO_RANGE_END) { + int t, v; + + if (!(tinfo_last->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN)) + return -EINVAL; + if ((tinfo_curr->vid - tinfo_last->vid) != + (tinfo_curr->tunid - tinfo_last->tunid)) + return -EINVAL; + t = tinfo_last->tunid; + for (v = tinfo_last->vid; v <= tinfo_curr->vid; v++) { + err = br_vlan_tunnel_info(p, cmd, v, t); + if (err) + return err; + t++; + } + memset(tinfo_last, 0, sizeof(struct vtunnel_info)); + memset(tinfo_curr, 0, sizeof(struct vtunnel_info)); + } else { + if (tinfo_last->flags) + return -EINVAL; + err = br_vlan_tunnel_info(p, cmd, tinfo_curr->vid, + tinfo_curr->tunid); + if (err) + return err; + memset(tinfo_last, 0, sizeof(struct vtunnel_info)); + memset(tinfo_curr, 0, sizeof(struct vtunnel_info)); + } + + return 0; +} diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 8ce621e8345c..1cbbf63a5ef7 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -91,6 +91,11 @@ struct br_vlan_stats { struct u64_stats_sync syncp; }; +struct br_tunnel_info { + __be64 tunnel_id; + struct metadata_dst *tunnel_dst; +}; + /** * struct net_bridge_vlan - per-vlan entry * @@ -113,6 +118,7 @@ struct br_vlan_stats { */ struct net_bridge_vlan { struct rhash_head vnode; + struct rhash_head tnode; u16 vid; u16 flags; struct br_vlan_stats __percpu *stats; @@ -124,6 +130,9 @@ struct net_bridge_vlan { atomic_t refcnt; struct net_bridge_vlan *brvlan; }; + + struct br_tunnel_info tinfo; + struct list_head vlist; struct rcu_head rcu; @@ -145,24 +154,27 @@ struct net_bridge_vlan { */ struct net_bridge_vlan_group { struct rhashtable vlan_hash; + struct rhashtable tunnel_hash; struct list_head vlan_list; u16 num_vlans; u16 pvid; }; -struct net_bridge_fdb_entry -{ +struct net_bridge_fdb_entry { struct hlist_node hlist; struct net_bridge_port *dst; - unsigned long updated; - unsigned long used; mac_addr addr; __u16 vlan_id; unsigned char is_local:1, is_static:1, added_by_user:1, added_by_external_learn:1; + + /* write-heavy members should not affect lookups */ + unsigned long updated ____cacheline_aligned_in_smp; + unsigned long used; + struct rcu_head rcu; }; @@ -177,6 +189,7 @@ struct net_bridge_port_group { struct timer_list timer; struct br_ip addr; unsigned char flags; + unsigned char eth_addr[ETH_ALEN]; }; struct net_bridge_mdb_entry @@ -201,12 +214,16 @@ struct net_bridge_mdb_htable u32 ver; }; -struct net_bridge_port -{ +struct net_bridge_port { struct net_bridge *br; struct net_device *dev; struct list_head list; + unsigned long flags; +#ifdef CONFIG_BRIDGE_VLAN_FILTERING + struct net_bridge_vlan_group __rcu *vlgrp; +#endif + /* STP */ u8 priority; u8 state; @@ -227,8 +244,6 @@ struct net_bridge_port struct kobject kobj; struct rcu_head rcu; - unsigned long flags; - #ifdef CONFIG_BRIDGE_IGMP_SNOOPING struct bridge_mcast_own_query ip4_own_query; #if IS_ENABLED(CONFIG_IPV6) @@ -248,9 +263,6 @@ struct net_bridge_port #ifdef CONFIG_NET_POLL_CONTROLLER struct netpoll *np; #endif -#ifdef CONFIG_BRIDGE_VLAN_FILTERING - struct net_bridge_vlan_group __rcu *vlgrp; -#endif #ifdef CONFIG_NET_SWITCHDEV int offload_fwd_mark; #endif @@ -272,14 +284,21 @@ static inline struct net_bridge_port *br_port_get_rtnl(const struct net_device * rtnl_dereference(dev->rx_handler_data) : NULL; } -struct net_bridge -{ +struct net_bridge { spinlock_t lock; + spinlock_t hash_lock; struct list_head port_list; struct net_device *dev; - struct pcpu_sw_netstats __percpu *stats; - spinlock_t hash_lock; + /* These fields are accessed on each packet */ +#ifdef CONFIG_BRIDGE_VLAN_FILTERING + u8 vlan_enabled; + u8 vlan_stats_enabled; + __be16 vlan_proto; + u16 default_pvid; + struct net_bridge_vlan_group __rcu *vlgrp; +#endif + struct hlist_head hash[BR_HASH_SIZE]; #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) union { @@ -297,6 +316,9 @@ struct net_bridge bridge_id designated_root; bridge_id bridge_id; u32 root_path_cost; + unsigned char topology_change; + unsigned char topology_change_detected; + u16 root_port; unsigned long max_age; unsigned long hello_time; unsigned long forward_delay; @@ -308,7 +330,6 @@ struct net_bridge u8 group_addr[ETH_ALEN]; bool group_addr_set; - u16 root_port; enum { BR_NO_STP, /* no spanning tree */ @@ -316,9 +337,6 @@ struct net_bridge BR_USER_STP, /* new RSTP in userspace */ } stp_enabled; - unsigned char topology_change; - unsigned char topology_change_detected; - #ifdef CONFIG_BRIDGE_IGMP_SNOOPING unsigned char multicast_router; @@ -363,21 +381,13 @@ struct net_bridge struct timer_list hello_timer; struct timer_list tcn_timer; struct timer_list topology_change_timer; - struct timer_list gc_timer; + struct delayed_work gc_work; struct kobject *ifobj; u32 auto_cnt; #ifdef CONFIG_NET_SWITCHDEV int offload_fwd_mark; #endif - -#ifdef CONFIG_BRIDGE_VLAN_FILTERING - struct net_bridge_vlan_group __rcu *vlgrp; - u8 vlan_enabled; - u8 vlan_stats_enabled; - __be16 vlan_proto; - u16 default_pvid; -#endif }; struct br_input_skb_cb { @@ -494,7 +504,7 @@ void br_fdb_find_delete_local(struct net_bridge *br, const unsigned char *addr, u16 vid); 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_cleanup(struct work_struct *work); void br_fdb_delete_by_port(struct net_bridge *br, const struct net_bridge_port *p, u16 vid, int do_all); struct net_bridge_fdb_entry *__br_fdb_get(struct net_bridge *br, @@ -599,7 +609,7 @@ void br_multicast_free_pg(struct rcu_head *head); 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 flags); + unsigned char flags, const unsigned char *src); void br_mdb_init(void); void br_mdb_uninit(void); void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port, @@ -764,6 +774,7 @@ bool br_allowed_egress(struct net_bridge_vlan_group *vg, const struct sk_buff *skb); bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid); struct sk_buff *br_handle_vlan(struct net_bridge *br, + const struct net_bridge_port *port, struct net_bridge_vlan_group *vg, struct sk_buff *skb); int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags); @@ -863,6 +874,7 @@ static inline bool br_should_learn(struct net_bridge_port *p, } static inline struct sk_buff *br_handle_vlan(struct net_bridge *br, + const struct net_bridge_port *port, struct net_bridge_vlan_group *vg, struct sk_buff *skb) { diff --git a/net/bridge/br_private_tunnel.h b/net/bridge/br_private_tunnel.h new file mode 100644 index 000000000000..4a447a378ab3 --- /dev/null +++ b/net/bridge/br_private_tunnel.h @@ -0,0 +1,83 @@ +/* + * Bridge per vlan tunnels + * + * Authors: + * Roopa Prabhu <roopa@cumulusnetworks.com> + * + * 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. + */ + +#ifndef _BR_PRIVATE_TUNNEL_H +#define _BR_PRIVATE_TUNNEL_H + +struct vtunnel_info { + u32 tunid; + u16 vid; + u16 flags; +}; + +/* br_netlink_tunnel.c */ +int br_parse_vlan_tunnel_info(struct nlattr *attr, + struct vtunnel_info *tinfo); +int br_process_vlan_tunnel_info(struct net_bridge *br, + struct net_bridge_port *p, + int cmd, + struct vtunnel_info *tinfo_curr, + struct vtunnel_info *tinfo_last); +int br_get_vlan_tunnel_info_size(struct net_bridge_vlan_group *vg); +int br_fill_vlan_tunnel_info(struct sk_buff *skb, + struct net_bridge_vlan_group *vg); + +#ifdef CONFIG_BRIDGE_VLAN_FILTERING +/* br_vlan_tunnel.c */ +int vlan_tunnel_init(struct net_bridge_vlan_group *vg); +void vlan_tunnel_deinit(struct net_bridge_vlan_group *vg); +int nbp_vlan_tunnel_info_delete(struct net_bridge_port *port, u16 vid); +int nbp_vlan_tunnel_info_add(struct net_bridge_port *port, u16 vid, u32 tun_id); +void nbp_vlan_tunnel_info_flush(struct net_bridge_port *port); +void vlan_tunnel_info_del(struct net_bridge_vlan_group *vg, + struct net_bridge_vlan *vlan); +int br_handle_ingress_vlan_tunnel(struct sk_buff *skb, + struct net_bridge_port *p, + struct net_bridge_vlan_group *vg); +int br_handle_egress_vlan_tunnel(struct sk_buff *skb, + struct net_bridge_vlan *vlan); +#else +static inline int vlan_tunnel_init(struct net_bridge_vlan_group *vg) +{ + return 0; +} + +static inline int nbp_vlan_tunnel_info_delete(struct net_bridge_port *port, + u16 vid) +{ + return 0; +} + +static inline int nbp_vlan_tunnel_info_add(struct net_bridge_port *port, + u16 vid, u32 tun_id) +{ + return 0; +} + +static inline void nbp_vlan_tunnel_info_flush(struct net_bridge_port *port) +{ +} + +static inline void vlan_tunnel_info_del(struct net_bridge_vlan_group *vg, + struct net_bridge_vlan *vlan) +{ +} + +static inline int br_handle_ingress_vlan_tunnel(struct sk_buff *skb, + struct net_bridge_port *p, + struct net_bridge_vlan_group *vg) +{ + return 0; +} +#endif + +#endif diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index 71fd1a4e63cc..8f56c2d1f1a7 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -602,7 +602,7 @@ int br_set_ageing_time(struct net_bridge *br, clock_t ageing_time) br->ageing_time = t; spin_unlock_bh(&br->lock); - mod_timer(&br->gc_timer, jiffies); + mod_delayed_work(system_long_wq, &br->gc_work, 0); return 0; } diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index 6c1e21411125..08341d2aa9c9 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -57,7 +57,7 @@ void br_stp_enable_bridge(struct net_bridge *br) spin_lock_bh(&br->lock); if (br->stp_enabled == BR_KERNEL_STP) mod_timer(&br->hello_timer, jiffies + br->hello_time); - mod_timer(&br->gc_timer, jiffies + HZ/10); + mod_delayed_work(system_long_wq, &br->gc_work, HZ / 10); br_config_bpdu_generation(br); @@ -88,7 +88,7 @@ void br_stp_disable_bridge(struct net_bridge *br) del_timer_sync(&br->hello_timer); del_timer_sync(&br->topology_change_timer); del_timer_sync(&br->tcn_timer); - del_timer_sync(&br->gc_timer); + cancel_delayed_work_sync(&br->gc_work); } /* called under bridge lock */ diff --git a/net/bridge/br_stp_timer.c b/net/bridge/br_stp_timer.c index 7ddb38e0a06e..c98b3e5c140a 100644 --- a/net/bridge/br_stp_timer.c +++ b/net/bridge/br_stp_timer.c @@ -153,8 +153,6 @@ void br_stp_timer_init(struct net_bridge *br) setup_timer(&br->topology_change_timer, br_topology_change_timer_expired, (unsigned long) br); - - setup_timer(&br->gc_timer, br_fdb_cleanup, (unsigned long) br); } void br_stp_port_timer_init(struct net_bridge_port *p) diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c index a18148213b08..0f4034934d56 100644 --- a/net/bridge/br_sysfs_br.c +++ b/net/bridge/br_sysfs_br.c @@ -263,7 +263,7 @@ static ssize_t gc_timer_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); - return sprintf(buf, "%ld\n", br_timer_value(&br->gc_timer)); + return sprintf(buf, "%ld\n", br_timer_value(&br->gc_work.timer)); } static DEVICE_ATTR_RO(gc_timer); diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index 8bd569695e76..05e8946ccc03 100644 --- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -188,6 +188,7 @@ static BRPORT_ATTR(multicast_router, S_IRUGO | S_IWUSR, show_multicast_router, store_multicast_router); BRPORT_ATTR_FLAG(multicast_fast_leave, BR_MULTICAST_FAST_LEAVE); +BRPORT_ATTR_FLAG(multicast_to_unicast, BR_MULTICAST_TO_UNICAST); #endif static const struct brport_attribute *brport_attrs[] = { @@ -214,6 +215,7 @@ static const struct brport_attribute *brport_attrs[] = { #ifdef CONFIG_BRIDGE_IGMP_SNOOPING &brport_attr_multicast_router, &brport_attr_multicast_fast_leave, + &brport_attr_multicast_to_unicast, #endif &brport_attr_proxyarp, &brport_attr_proxyarp_wifi, diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index b6de4f457161..62e68c0dc687 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -5,6 +5,7 @@ #include <net/switchdev.h> #include "br_private.h" +#include "br_private_tunnel.h" static inline int br_vlan_cmp(struct rhashtable_compare_arg *arg, const void *ptr) @@ -310,6 +311,7 @@ static int __vlan_del(struct net_bridge_vlan *v) } if (masterv != v) { + vlan_tunnel_info_del(vg, v); rhashtable_remove_fast(&vg->vlan_hash, &v->vnode, br_vlan_rht_params); __vlan_del_list(v); @@ -325,6 +327,7 @@ static void __vlan_group_free(struct net_bridge_vlan_group *vg) { WARN_ON(!list_empty(&vg->vlan_list)); rhashtable_destroy(&vg->vlan_hash); + vlan_tunnel_deinit(vg); kfree(vg); } @@ -338,6 +341,7 @@ static void __vlan_flush(struct net_bridge_vlan_group *vg) } struct sk_buff *br_handle_vlan(struct net_bridge *br, + const struct net_bridge_port *p, struct net_bridge_vlan_group *vg, struct sk_buff *skb) { @@ -378,6 +382,12 @@ struct sk_buff *br_handle_vlan(struct net_bridge *br, if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED) skb->vlan_tci = 0; + + if (p && (p->flags & BR_VLAN_TUNNEL) && + br_handle_egress_vlan_tunnel(skb, v)) { + kfree_skb(skb); + return NULL; + } out: return skb; } @@ -613,6 +623,8 @@ int br_vlan_delete(struct net_bridge *br, u16 vid) br_fdb_find_delete_local(br, NULL, br->dev->dev_addr, vid); br_fdb_delete_by_port(br, NULL, vid, 0); + vlan_tunnel_info_del(vg, v); + return __vlan_del(v); } @@ -918,6 +930,9 @@ int br_vlan_init(struct net_bridge *br) ret = rhashtable_init(&vg->vlan_hash, &br_vlan_rht_params); if (ret) goto err_rhtbl; + ret = vlan_tunnel_init(vg); + if (ret) + goto err_tunnel_init; INIT_LIST_HEAD(&vg->vlan_list); br->vlan_proto = htons(ETH_P_8021Q); br->default_pvid = 1; @@ -932,6 +947,8 @@ out: return ret; err_vlan_add: + vlan_tunnel_deinit(vg); +err_tunnel_init: rhashtable_destroy(&vg->vlan_hash); err_rhtbl: kfree(vg); @@ -961,6 +978,9 @@ int nbp_vlan_init(struct net_bridge_port *p) ret = rhashtable_init(&vg->vlan_hash, &br_vlan_rht_params); if (ret) goto err_rhtbl; + ret = vlan_tunnel_init(vg); + if (ret) + goto err_tunnel_init; INIT_LIST_HEAD(&vg->vlan_list); rcu_assign_pointer(p->vlgrp, vg); if (p->br->default_pvid) { @@ -976,8 +996,10 @@ out: err_vlan_add: RCU_INIT_POINTER(p->vlgrp, NULL); synchronize_rcu(); - rhashtable_destroy(&vg->vlan_hash); + vlan_tunnel_deinit(vg); err_vlan_enabled: +err_tunnel_init: + rhashtable_destroy(&vg->vlan_hash); err_rhtbl: kfree(vg); diff --git a/net/bridge/br_vlan_tunnel.c b/net/bridge/br_vlan_tunnel.c new file mode 100644 index 000000000000..b2b79a070162 --- /dev/null +++ b/net/bridge/br_vlan_tunnel.c @@ -0,0 +1,203 @@ +/* + * Bridge per vlan tunnel port dst_metadata handling code + * + * Authors: + * Roopa Prabhu <roopa@cumulusnetworks.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/kernel.h> +#include <linux/netdevice.h> +#include <linux/rtnetlink.h> +#include <linux/slab.h> +#include <net/switchdev.h> +#include <net/dst_metadata.h> + +#include "br_private.h" +#include "br_private_tunnel.h" + +static inline int br_vlan_tunid_cmp(struct rhashtable_compare_arg *arg, + const void *ptr) +{ + const struct net_bridge_vlan *vle = ptr; + __be64 tunid = *(__be64 *)arg->key; + + return vle->tinfo.tunnel_id != tunid; +} + +static const struct rhashtable_params br_vlan_tunnel_rht_params = { + .head_offset = offsetof(struct net_bridge_vlan, tnode), + .key_offset = offsetof(struct net_bridge_vlan, tinfo.tunnel_id), + .key_len = sizeof(__be64), + .nelem_hint = 3, + .locks_mul = 1, + .obj_cmpfn = br_vlan_tunid_cmp, + .automatic_shrinking = true, +}; + +static struct net_bridge_vlan *br_vlan_tunnel_lookup(struct rhashtable *tbl, + u64 tunnel_id) +{ + return rhashtable_lookup_fast(tbl, &tunnel_id, + br_vlan_tunnel_rht_params); +} + +void vlan_tunnel_info_del(struct net_bridge_vlan_group *vg, + struct net_bridge_vlan *vlan) +{ + if (!vlan->tinfo.tunnel_dst) + return; + rhashtable_remove_fast(&vg->tunnel_hash, &vlan->tnode, + br_vlan_tunnel_rht_params); + vlan->tinfo.tunnel_id = 0; + dst_release(&vlan->tinfo.tunnel_dst->dst); + vlan->tinfo.tunnel_dst = NULL; +} + +static int __vlan_tunnel_info_add(struct net_bridge_vlan_group *vg, + struct net_bridge_vlan *vlan, u32 tun_id) +{ + struct metadata_dst *metadata = NULL; + __be64 key = key32_to_tunnel_id(cpu_to_be32(tun_id)); + int err; + + if (vlan->tinfo.tunnel_dst) + return -EEXIST; + + metadata = __ip_tun_set_dst(0, 0, 0, 0, 0, TUNNEL_KEY, + key, 0); + if (!metadata) + return -EINVAL; + + metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX | IP_TUNNEL_INFO_BRIDGE; + vlan->tinfo.tunnel_dst = metadata; + vlan->tinfo.tunnel_id = key; + + err = rhashtable_lookup_insert_fast(&vg->tunnel_hash, &vlan->tnode, + br_vlan_tunnel_rht_params); + if (err) + goto out; + + return 0; +out: + dst_release(&vlan->tinfo.tunnel_dst->dst); + + return err; +} + +/* Must be protected by RTNL. + * Must be called with vid in range from 1 to 4094 inclusive. + */ +int nbp_vlan_tunnel_info_add(struct net_bridge_port *port, u16 vid, u32 tun_id) +{ + struct net_bridge_vlan_group *vg; + struct net_bridge_vlan *vlan; + + ASSERT_RTNL(); + + vg = nbp_vlan_group(port); + vlan = br_vlan_find(vg, vid); + if (!vlan) + return -EINVAL; + + return __vlan_tunnel_info_add(vg, vlan, tun_id); +} + +/* Must be protected by RTNL. + * Must be called with vid in range from 1 to 4094 inclusive. + */ +int nbp_vlan_tunnel_info_delete(struct net_bridge_port *port, u16 vid) +{ + struct net_bridge_vlan_group *vg; + struct net_bridge_vlan *v; + + ASSERT_RTNL(); + + vg = nbp_vlan_group(port); + v = br_vlan_find(vg, vid); + if (!v) + return -ENOENT; + + vlan_tunnel_info_del(vg, v); + + return 0; +} + +static void __vlan_tunnel_info_flush(struct net_bridge_vlan_group *vg) +{ + struct net_bridge_vlan *vlan, *tmp; + + list_for_each_entry_safe(vlan, tmp, &vg->vlan_list, vlist) + vlan_tunnel_info_del(vg, vlan); +} + +void nbp_vlan_tunnel_info_flush(struct net_bridge_port *port) +{ + struct net_bridge_vlan_group *vg; + + ASSERT_RTNL(); + + vg = nbp_vlan_group(port); + __vlan_tunnel_info_flush(vg); +} + +int vlan_tunnel_init(struct net_bridge_vlan_group *vg) +{ + return rhashtable_init(&vg->tunnel_hash, &br_vlan_tunnel_rht_params); +} + +void vlan_tunnel_deinit(struct net_bridge_vlan_group *vg) +{ + rhashtable_destroy(&vg->tunnel_hash); +} + +int br_handle_ingress_vlan_tunnel(struct sk_buff *skb, + struct net_bridge_port *p, + struct net_bridge_vlan_group *vg) +{ + struct ip_tunnel_info *tinfo = skb_tunnel_info(skb); + struct net_bridge_vlan *vlan; + + if (!vg || !tinfo) + return 0; + + /* if already tagged, ignore */ + if (skb_vlan_tagged(skb)) + return 0; + + /* lookup vid, given tunnel id */ + vlan = br_vlan_tunnel_lookup(&vg->tunnel_hash, tinfo->key.tun_id); + if (!vlan) + return 0; + + skb_dst_drop(skb); + + __vlan_hwaccel_put_tag(skb, p->br->vlan_proto, vlan->vid); + + return 0; +} + +int br_handle_egress_vlan_tunnel(struct sk_buff *skb, + struct net_bridge_vlan *vlan) +{ + int err; + + if (!vlan || !vlan->tinfo.tunnel_id) + return 0; + + if (unlikely(!skb_vlan_tag_present(skb))) + return 0; + + skb_dst_drop(skb); + err = skb_vlan_pop(skb); + if (err) + return err; + + skb_dst_set(skb, dst_clone(&vlan->tinfo.tunnel_dst->dst)); + + return 0; +} diff --git a/net/bridge/netfilter/ebt_limit.c b/net/bridge/netfilter/ebt_limit.c index 517e78befcb2..61a9f1be1263 100644 --- a/net/bridge/netfilter/ebt_limit.c +++ b/net/bridge/netfilter/ebt_limit.c @@ -105,6 +105,7 @@ static struct xt_match ebt_limit_mt_reg __read_mostly = { .match = ebt_limit_mt, .checkentry = ebt_limit_mt_check, .matchsize = sizeof(struct ebt_limit_info), + .usersize = offsetof(struct ebt_limit_info, prev), #ifdef CONFIG_COMPAT .compatsize = sizeof(struct ebt_compat_limit_info), #endif diff --git a/net/bridge/netfilter/ebt_log.c b/net/bridge/netfilter/ebt_log.c index e88bd4827ac1..98b9c8e8615e 100644 --- a/net/bridge/netfilter/ebt_log.c +++ b/net/bridge/netfilter/ebt_log.c @@ -78,7 +78,7 @@ ebt_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum, unsigned int bitmask; /* FIXME: Disabled from containers until syslog ns is supported */ - if (!net_eq(net, &init_net)) + if (!net_eq(net, &init_net) && !sysctl_nf_log_all_netns) return; spin_lock_bh(&ebt_log_lock); diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 537e3d506fc2..79b69917f521 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1346,56 +1346,72 @@ static int update_counters(struct net *net, const void __user *user, hlp.num_counters, user, len); } -static inline int ebt_make_matchname(const struct ebt_entry_match *m, - const char *base, char __user *ubase) +static inline int ebt_obj_to_user(char __user *um, const char *_name, + const char *data, int entrysize, + int usersize, int datasize) { - char __user *hlp = ubase + ((char *)m - base); - char name[EBT_FUNCTION_MAXNAMELEN] = {}; + char name[EBT_FUNCTION_MAXNAMELEN] = {0}; /* ebtables expects 32 bytes long names but xt_match names are 29 bytes * long. Copy 29 bytes and fill remaining bytes with zeroes. */ - strlcpy(name, m->u.match->name, sizeof(name)); - if (copy_to_user(hlp, name, EBT_FUNCTION_MAXNAMELEN)) + strlcpy(name, _name, sizeof(name)); + if (copy_to_user(um, name, EBT_FUNCTION_MAXNAMELEN) || + put_user(datasize, (int __user *)(um + EBT_FUNCTION_MAXNAMELEN)) || + xt_data_to_user(um + entrysize, data, usersize, datasize)) return -EFAULT; + return 0; } -static inline int ebt_make_watchername(const struct ebt_entry_watcher *w, - const char *base, char __user *ubase) +static inline int ebt_match_to_user(const struct ebt_entry_match *m, + const char *base, char __user *ubase) { - char __user *hlp = ubase + ((char *)w - base); - char name[EBT_FUNCTION_MAXNAMELEN] = {}; + return ebt_obj_to_user(ubase + ((char *)m - base), + m->u.match->name, m->data, sizeof(*m), + m->u.match->usersize, m->match_size); +} - strlcpy(name, w->u.watcher->name, sizeof(name)); - if (copy_to_user(hlp, name, EBT_FUNCTION_MAXNAMELEN)) - return -EFAULT; - return 0; +static inline int ebt_watcher_to_user(const struct ebt_entry_watcher *w, + const char *base, char __user *ubase) +{ + return ebt_obj_to_user(ubase + ((char *)w - base), + w->u.watcher->name, w->data, sizeof(*w), + w->u.watcher->usersize, w->watcher_size); } -static inline int ebt_make_names(struct ebt_entry *e, const char *base, - char __user *ubase) +static inline int ebt_entry_to_user(struct ebt_entry *e, const char *base, + char __user *ubase) { int ret; char __user *hlp; const struct ebt_entry_target *t; - char name[EBT_FUNCTION_MAXNAMELEN] = {}; - if (e->bitmask == 0) + if (e->bitmask == 0) { + /* special case !EBT_ENTRY_OR_ENTRIES */ + if (copy_to_user(ubase + ((char *)e - base), e, + sizeof(struct ebt_entries))) + return -EFAULT; return 0; + } + + if (copy_to_user(ubase + ((char *)e - base), e, sizeof(*e))) + return -EFAULT; hlp = ubase + (((char *)e + e->target_offset) - base); t = (struct ebt_entry_target *)(((char *)e) + e->target_offset); - ret = EBT_MATCH_ITERATE(e, ebt_make_matchname, base, ubase); + ret = EBT_MATCH_ITERATE(e, ebt_match_to_user, base, ubase); if (ret != 0) return ret; - ret = EBT_WATCHER_ITERATE(e, ebt_make_watchername, base, ubase); + ret = EBT_WATCHER_ITERATE(e, ebt_watcher_to_user, base, ubase); if (ret != 0) return ret; - strlcpy(name, t->u.target->name, sizeof(name)); - if (copy_to_user(hlp, name, EBT_FUNCTION_MAXNAMELEN)) - return -EFAULT; + ret = ebt_obj_to_user(hlp, t->u.target->name, t->data, sizeof(*t), + t->u.target->usersize, t->target_size); + if (ret != 0) + return ret; + return 0; } @@ -1475,13 +1491,9 @@ static int copy_everything_to_user(struct ebt_table *t, void __user *user, if (ret) return ret; - if (copy_to_user(tmp.entries, entries, entries_size)) { - BUGPRINT("Couldn't copy entries to userspace\n"); - return -EFAULT; - } /* set the match/watcher/target names right */ return EBT_ENTRY_ITERATE(entries, entries_size, - ebt_make_names, entries, tmp.entries); + ebt_entry_to_user, entries, tmp.entries); } static int do_ebt_set_ctl(struct sock *sk, @@ -1630,8 +1642,10 @@ static int compat_match_to_user(struct ebt_entry_match *m, void __user **dstptr, if (match->compat_to_user) { if (match->compat_to_user(cm->data, m->data)) return -EFAULT; - } else if (copy_to_user(cm->data, m->data, msize)) + } else { + if (xt_data_to_user(cm->data, m->data, match->usersize, msize)) return -EFAULT; + } *size -= ebt_compat_entry_padsize() + off; *dstptr = cm->data; @@ -1657,8 +1671,10 @@ static int compat_target_to_user(struct ebt_entry_target *t, if (target->compat_to_user) { if (target->compat_to_user(cm->data, t->data)) return -EFAULT; - } else if (copy_to_user(cm->data, t->data, tsize)) - return -EFAULT; + } else { + if (xt_data_to_user(cm->data, t->data, target->usersize, tsize)) + return -EFAULT; + } *size -= ebt_compat_entry_padsize() + off; *dstptr = cm->data; |