diff options
Diffstat (limited to 'net/bridge')
49 files changed, 9222 insertions, 1874 deletions
diff --git a/net/bridge/Kconfig b/net/bridge/Kconfig index e143ca67888..aa0d3b2f1bb 100644 --- a/net/bridge/Kconfig +++ b/net/bridge/Kconfig @@ -6,6 +6,7 @@ config BRIDGE tristate "802.1d Ethernet Bridging" select LLC select STP + depends on IPV6 || IPV6=n ---help--- If you say Y here, then your Linux box will be able to act as an Ethernet bridge, which means that the different Ethernet segments it @@ -31,3 +32,31 @@ config BRIDGE will be called bridge. If unsure, say N. + +config BRIDGE_IGMP_SNOOPING + bool "IGMP/MLD snooping" + depends on BRIDGE + depends on INET + default y + ---help--- + If you say Y here, then the Ethernet bridge will be able selectively + forward multicast traffic based on IGMP/MLD traffic received from + each port. + + Say N to exclude this support and reduce the binary size. + + If unsure, say Y. + +config BRIDGE_VLAN_FILTERING + bool "VLAN filtering" + depends on BRIDGE + depends on VLAN_8021Q + default n + ---help--- + If you say Y here, then the Ethernet bridge will be able selectively + receive and forward traffic based on VLAN information in the packet + any VLAN information configured on the bridge port or bridge device. + + Say N to exclude this support and reduce the binary size. + + If unsure, say Y. diff --git a/net/bridge/Makefile b/net/bridge/Makefile index f444c12cde5..8590b942bff 100644 --- a/net/bridge/Makefile +++ b/net/bridge/Makefile @@ -5,11 +5,15 @@ obj-$(CONFIG_BRIDGE) += bridge.o bridge-y := br.o br_device.o br_fdb.o br_forward.o br_if.o br_input.o \ - br_ioctl.o br_notify.o br_stp.o br_stp_bpdu.o \ + br_ioctl.o br_stp.o br_stp_bpdu.o \ br_stp_if.o br_stp_timer.o br_netlink.o bridge-$(CONFIG_SYSFS) += br_sysfs_if.o br_sysfs_br.o bridge-$(CONFIG_BRIDGE_NETFILTER) += br_netfilter.o -obj-$(CONFIG_BRIDGE_NF_EBTABLES) += netfilter/ +bridge-$(CONFIG_BRIDGE_IGMP_SNOOPING) += br_multicast.o br_mdb.o + +bridge-$(CONFIG_BRIDGE_VLAN_FILTERING) += br_vlan.o + +obj-$(CONFIG_NETFILTER) += netfilter/ diff --git a/net/bridge/br.c b/net/bridge/br.c index e1241c76239..1a755a1e541 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -22,23 +22,134 @@ #include "br_private.h" -int (*br_should_route_hook)(struct sk_buff *skb); +/* + * Handle changes in state of network devices enslaved to a bridge. + * + * Note: don't care about up/down if bridge itself is down, because + * port state is checked when bridge is brought up. + */ +static int br_device_event(struct notifier_block *unused, unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct net_bridge_port *p; + struct net_bridge *br; + bool changed_addr; + int err; -static const struct stp_proto br_stp_proto = { - .rcv = br_stp_rcv, + /* register of bridge completed, add sysfs entries */ + if ((dev->priv_flags & IFF_EBRIDGE) && event == NETDEV_REGISTER) { + br_sysfs_addbr(dev); + return NOTIFY_DONE; + } + + /* not a port of a bridge */ + p = br_port_get_rtnl(dev); + if (!p) + return NOTIFY_DONE; + + br = p->br; + + switch (event) { + case NETDEV_CHANGEMTU: + dev_set_mtu(br->dev, br_min_mtu(br)); + break; + + case NETDEV_CHANGEADDR: + spin_lock_bh(&br->lock); + br_fdb_changeaddr(p, dev->dev_addr); + changed_addr = br_stp_recalculate_bridge_id(br); + spin_unlock_bh(&br->lock); + + if (changed_addr) + call_netdevice_notifiers(NETDEV_CHANGEADDR, br->dev); + + break; + + case NETDEV_CHANGE: + br_port_carrier_check(p); + break; + + case NETDEV_FEAT_CHANGE: + netdev_update_features(br->dev); + break; + + case NETDEV_DOWN: + spin_lock_bh(&br->lock); + if (br->dev->flags & IFF_UP) + br_stp_disable_port(p); + spin_unlock_bh(&br->lock); + break; + + case NETDEV_UP: + if (netif_running(br->dev) && netif_oper_up(dev)) { + spin_lock_bh(&br->lock); + br_stp_enable_port(p); + spin_unlock_bh(&br->lock); + } + break; + + case NETDEV_UNREGISTER: + br_del_if(br, dev); + break; + + case NETDEV_CHANGENAME: + err = br_sysfs_renameif(p); + if (err) + return notifier_from_errno(err); + break; + + case NETDEV_PRE_TYPE_CHANGE: + /* Forbid underlaying device to change its type. */ + return NOTIFY_BAD; + + case NETDEV_RESEND_IGMP: + /* Propagate to master device */ + call_netdevice_notifiers(event, br->dev); + break; + } + + /* Events that may cause spanning tree to refresh */ + if (event == NETDEV_CHANGEADDR || event == NETDEV_UP || + event == NETDEV_CHANGE || event == NETDEV_DOWN) + br_ifinfo_notify(RTM_NEWLINK, p); + + return NOTIFY_DONE; +} + +static struct notifier_block br_device_notifier = { + .notifier_call = br_device_event }; +static void __net_exit br_net_exit(struct net *net) +{ + struct net_device *dev; + LIST_HEAD(list); + + rtnl_lock(); + for_each_netdev(net, dev) + if (dev->priv_flags & IFF_EBRIDGE) + br_dev_delete(dev, &list); + + unregister_netdevice_many(&list); + rtnl_unlock(); + +} + static struct pernet_operations br_net_ops = { .exit = br_net_exit, }; +static const struct stp_proto br_stp_proto = { + .rcv = br_stp_rcv, +}; + static int __init br_init(void) { int err; err = stp_proto_register(&br_stp_proto); if (err < 0) { - printk(KERN_ERR "bridge: can't register sap for STP\n"); + pr_err("bridge: can't register sap for STP\n"); return err; } @@ -63,9 +174,8 @@ static int __init br_init(void) goto err_out4; brioctl_set(br_ioctl_deviceless_stub); - br_handle_frame_hook = br_handle_frame; -#if defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE) +#if IS_ENABLED(CONFIG_ATM_LANE) br_fdb_test_addr_hook = br_fdb_test_addr; #endif @@ -96,17 +206,15 @@ static void __exit br_deinit(void) rcu_barrier(); /* Wait for completion of call_rcu()'s */ br_netfilter_fini(); -#if defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE) +#if IS_ENABLED(CONFIG_ATM_LANE) br_fdb_test_addr_hook = NULL; #endif - br_handle_frame_hook = NULL; br_fdb_fini(); } -EXPORT_SYMBOL(br_should_route_hook); - module_init(br_init) module_exit(br_deinit) MODULE_LICENSE("GPL"); MODULE_VERSION(BR_VERSION); +MODULE_ALIAS_RTNL_LINK("bridge"); diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 1a99c4e04e8..568cccd39a3 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -13,42 +13,97 @@ #include <linux/kernel.h> #include <linux/netdevice.h> +#include <linux/netpoll.h> #include <linux/etherdevice.h> #include <linux/ethtool.h> +#include <linux/list.h> +#include <linux/netfilter_bridge.h> #include <asm/uaccess.h> #include "br_private.h" -/* net device transmit always called with no BH (preempt_disabled) */ +#define COMMON_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | \ + NETIF_F_GSO_MASK | NETIF_F_HW_CSUM) + +/* net device transmit always called with BH disabled */ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); const unsigned char *dest = skb->data; struct net_bridge_fdb_entry *dst; + struct net_bridge_mdb_entry *mdst; + struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats); + u16 vid = 0; + + rcu_read_lock(); +#ifdef CONFIG_BRIDGE_NETFILTER + if (skb->nf_bridge && (skb->nf_bridge->mask & BRNF_BRIDGED_DNAT)) { + br_nf_pre_routing_finish_bridge_slow(skb); + rcu_read_unlock(); + return NETDEV_TX_OK; + } +#endif + + u64_stats_update_begin(&brstats->syncp); + brstats->tx_packets++; + brstats->tx_bytes += skb->len; + u64_stats_update_end(&brstats->syncp); - dev->stats.tx_packets++; - dev->stats.tx_bytes += skb->len; + BR_INPUT_SKB_CB(skb)->brdev = dev; skb_reset_mac_header(skb); skb_pull(skb, ETH_HLEN); - if (dest[0] & 1) - br_flood_deliver(br, skb); - else if ((dst = __br_fdb_get(br, dest)) != NULL) + if (!br_allowed_ingress(br, br_get_vlan_info(br), skb, &vid)) + goto out; + + if (is_broadcast_ether_addr(dest)) + br_flood_deliver(br, skb, false); + else if (is_multicast_ether_addr(dest)) { + if (unlikely(netpoll_tx_running(dev))) { + br_flood_deliver(br, skb, false); + goto out; + } + if (br_multicast_rcv(br, NULL, skb, vid)) { + kfree_skb(skb); + goto out; + } + + mdst = br_mdb_get(br, skb, vid); + if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) && + br_multicast_querier_exists(br, eth_hdr(skb))) + br_multicast_deliver(mdst, skb); + else + br_flood_deliver(br, skb, false); + } else if ((dst = __br_fdb_get(br, dest, vid)) != NULL) br_deliver(dst->dst, skb); else - br_flood_deliver(br, skb); + br_flood_deliver(br, skb, true); +out: + rcu_read_unlock(); return NETDEV_TX_OK; } +static int br_dev_init(struct net_device *dev) +{ + struct net_bridge *br = netdev_priv(dev); + + br->stats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); + if (!br->stats) + return -ENOMEM; + + return 0; +} + static int br_dev_open(struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); - br_features_recompute(br); + netdev_update_features(dev); netif_start_queue(dev); br_stp_enable_bridge(br); + br_multicast_open(br); return 0; } @@ -57,15 +112,53 @@ static void br_dev_set_multicast_list(struct net_device *dev) { } +static void br_dev_change_rx_flags(struct net_device *dev, int change) +{ + if (change & IFF_PROMISC) + br_manage_promisc(netdev_priv(dev)); +} + static int br_dev_stop(struct net_device *dev) { - br_stp_disable_bridge(netdev_priv(dev)); + struct net_bridge *br = netdev_priv(dev); + + br_stp_disable_bridge(br); + br_multicast_stop(br); netif_stop_queue(dev); return 0; } +static struct rtnl_link_stats64 *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 }; + unsigned int cpu; + + for_each_possible_cpu(cpu) { + unsigned int start; + const struct pcpu_sw_netstats *bstats + = per_cpu_ptr(br->stats, cpu); + do { + start = u64_stats_fetch_begin_irq(&bstats->syncp); + memcpy(&tmp, bstats, sizeof(tmp)); + } while (u64_stats_fetch_retry_irq(&bstats->syncp, start)); + sum.tx_bytes += tmp.tx_bytes; + sum.tx_packets += tmp.tx_packets; + sum.rx_bytes += tmp.rx_bytes; + sum.rx_packets += tmp.rx_packets; + } + + stats->tx_bytes = sum.tx_bytes; + 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) { struct net_bridge *br = netdev_priv(dev); @@ -76,7 +169,7 @@ static int br_change_mtu(struct net_device *dev, int new_mtu) #ifdef CONFIG_BRIDGE_NETFILTER /* remember the MTU in the rtable for PMTU */ - br->fake_rtable.u.dst.metrics[RTAX_MTU - 1] = new_mtu; + dst_metric_set(&br->fake_rtable.dst, RTAX_MTU, new_mtu); #endif return 0; @@ -89,12 +182,13 @@ static int br_set_mac_address(struct net_device *dev, void *p) struct sockaddr *addr = p; if (!is_valid_ether_addr(addr->sa_data)) - return -EINVAL; + return -EADDRNOTAVAIL; spin_lock_bh(&br->lock); - memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN); - br_stp_change_bridge_id(br, addr->sa_data); - br->flags |= BR_SET_MAC_ADDR; + if (!ether_addr_equal(dev->dev_addr, addr->sa_data)) { + /* Mac address will be changed in br_stp_change_bridge_id(). */ + br_stp_change_bridge_id(br, addr->sa_data); + } spin_unlock_bh(&br->lock); return 0; @@ -102,87 +196,198 @@ static int br_set_mac_address(struct net_device *dev, void *p) static void br_getinfo(struct net_device *dev, struct ethtool_drvinfo *info) { - strcpy(info->driver, "bridge"); - strcpy(info->version, BR_VERSION); - strcpy(info->fw_version, "N/A"); - strcpy(info->bus_info, "N/A"); + strlcpy(info->driver, "bridge", sizeof(info->driver)); + strlcpy(info->version, BR_VERSION, sizeof(info->version)); + strlcpy(info->fw_version, "N/A", sizeof(info->fw_version)); + strlcpy(info->bus_info, "N/A", sizeof(info->bus_info)); } -static int br_set_sg(struct net_device *dev, u32 data) +static netdev_features_t br_fix_features(struct net_device *dev, + netdev_features_t features) { struct net_bridge *br = netdev_priv(dev); - if (data) - br->feature_mask |= NETIF_F_SG; - else - br->feature_mask &= ~NETIF_F_SG; + return br_features_recompute(br, features); +} - br_features_recompute(br); - return 0; +#ifdef CONFIG_NET_POLL_CONTROLLER +static void br_poll_controller(struct net_device *br_dev) +{ } -static int br_set_tso(struct net_device *dev, u32 data) +static void br_netpoll_cleanup(struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); + struct net_bridge_port *p; - if (data) - br->feature_mask |= NETIF_F_TSO; - else - br->feature_mask &= ~NETIF_F_TSO; + list_for_each_entry(p, &br->port_list, list) + br_netpoll_disable(p); +} - br_features_recompute(br); - return 0; +static int __br_netpoll_enable(struct net_bridge_port *p) +{ + struct netpoll *np; + int err; + + np = kzalloc(sizeof(*p->np), GFP_KERNEL); + if (!np) + return -ENOMEM; + + err = __netpoll_setup(np, p->dev); + if (err) { + kfree(np); + return err; + } + + p->np = np; + return err; +} + +int br_netpoll_enable(struct net_bridge_port *p) +{ + if (!p->br->dev->npinfo) + return 0; + + return __br_netpoll_enable(p); } -static int br_set_tx_csum(struct net_device *dev, u32 data) +static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni) { struct net_bridge *br = netdev_priv(dev); + struct net_bridge_port *p; + int err = 0; + + list_for_each_entry(p, &br->port_list, list) { + if (!p->dev) + continue; + err = __br_netpoll_enable(p); + if (err) + goto fail; + } + +out: + return err; + +fail: + br_netpoll_cleanup(dev); + goto out; +} - if (data) - br->feature_mask |= NETIF_F_NO_CSUM; - else - br->feature_mask &= ~NETIF_F_ALL_CSUM; +void br_netpoll_disable(struct net_bridge_port *p) +{ + struct netpoll *np = p->np; - br_features_recompute(br); - return 0; + if (!np) + return; + + p->np = NULL; + + __netpoll_free_async(np); +} + +#endif + +static int br_add_slave(struct net_device *dev, struct net_device *slave_dev) + +{ + struct net_bridge *br = netdev_priv(dev); + + return br_add_if(br, slave_dev); +} + +static int br_del_slave(struct net_device *dev, struct net_device *slave_dev) +{ + struct net_bridge *br = netdev_priv(dev); + + return br_del_if(br, slave_dev); } static const struct ethtool_ops br_ethtool_ops = { .get_drvinfo = br_getinfo, .get_link = ethtool_op_get_link, - .get_tx_csum = ethtool_op_get_tx_csum, - .set_tx_csum = br_set_tx_csum, - .get_sg = ethtool_op_get_sg, - .set_sg = br_set_sg, - .get_tso = ethtool_op_get_tso, - .set_tso = br_set_tso, - .get_ufo = ethtool_op_get_ufo, - .set_ufo = ethtool_op_set_ufo, - .get_flags = ethtool_op_get_flags, }; static const struct net_device_ops br_netdev_ops = { .ndo_open = br_dev_open, .ndo_stop = br_dev_stop, + .ndo_init = br_dev_init, .ndo_start_xmit = br_dev_xmit, + .ndo_get_stats64 = br_get_stats64, .ndo_set_mac_address = br_set_mac_address, - .ndo_set_multicast_list = br_dev_set_multicast_list, + .ndo_set_rx_mode = br_dev_set_multicast_list, + .ndo_change_rx_flags = br_dev_change_rx_flags, .ndo_change_mtu = br_change_mtu, .ndo_do_ioctl = br_dev_ioctl, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_netpoll_setup = br_netpoll_setup, + .ndo_netpoll_cleanup = br_netpoll_cleanup, + .ndo_poll_controller = br_poll_controller, +#endif + .ndo_add_slave = br_add_slave, + .ndo_del_slave = br_del_slave, + .ndo_fix_features = br_fix_features, + .ndo_fdb_add = br_fdb_add, + .ndo_fdb_del = br_fdb_delete, + .ndo_fdb_dump = br_fdb_dump, + .ndo_bridge_getlink = br_getlink, + .ndo_bridge_setlink = br_setlink, + .ndo_bridge_dellink = br_dellink, +}; + +static void br_dev_free(struct net_device *dev) +{ + struct net_bridge *br = netdev_priv(dev); + + free_percpu(br->stats); + free_netdev(dev); +} + +static struct device_type br_type = { + .name = "bridge", }; void br_dev_setup(struct net_device *dev) { - random_ether_addr(dev->dev_addr); + struct net_bridge *br = netdev_priv(dev); + + eth_hw_addr_random(dev); ether_setup(dev); dev->netdev_ops = &br_netdev_ops; - dev->destructor = free_netdev; - SET_ETHTOOL_OPS(dev, &br_ethtool_ops); + dev->destructor = br_dev_free; + dev->ethtool_ops = &br_ethtool_ops; + SET_NETDEV_DEVTYPE(dev, &br_type); dev->tx_queue_len = 0; dev->priv_flags = IFF_EBRIDGE; - dev->features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | - NETIF_F_GSO_MASK | NETIF_F_NO_CSUM | NETIF_F_LLTX | - NETIF_F_NETNS_LOCAL | NETIF_F_GSO; + dev->features = COMMON_FEATURES | NETIF_F_LLTX | NETIF_F_NETNS_LOCAL | + NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; + dev->hw_features = COMMON_FEATURES | NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_STAG_TX; + dev->vlan_features = COMMON_FEATURES; + + br->dev = dev; + spin_lock_init(&br->lock); + INIT_LIST_HEAD(&br->port_list); + spin_lock_init(&br->hash_lock); + + br->bridge_id.prio[0] = 0x80; + br->bridge_id.prio[1] = 0x00; + + ether_addr_copy(br->group_addr, eth_reserved_addr_base); + + br->stp_enabled = BR_NO_STP; + br->group_fwd_mask = BR_GROUPFWD_DEFAULT; + br->group_fwd_mask_required = BR_GROUPFWD_DEFAULT; + + br->designated_root = br->bridge_id; + br->bridge_max_age = br->max_age = 20 * HZ; + br->bridge_hello_time = br->hello_time = 2 * HZ; + br->bridge_forward_delay = br->forward_delay = 15 * HZ; + br->ageing_time = 300 * HZ; + + br_netfilter_rtable_init(br); + br_stp_timer_init(br); + br_multicast_init(br); + br_vlan_init(br); } diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 3b8e038ab32..b524c36c127 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -20,13 +20,20 @@ #include <linux/etherdevice.h> #include <linux/jhash.h> #include <linux/random.h> -#include <asm/atomic.h> +#include <linux/slab.h> +#include <linux/atomic.h> #include <asm/unaligned.h> +#include <linux/if_vlan.h> #include "br_private.h" static struct kmem_cache *br_fdb_cache __read_mostly; +static struct net_bridge_fdb_entry *fdb_find(struct hlist_head *head, + const unsigned char *addr, + __u16 vid); static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source, - const unsigned char *addr); + const unsigned char *addr, u16 vid); +static void fdb_notify(struct net_bridge *br, + const struct net_bridge_fdb_entry *, int); static u32 fdb_salt __read_mostly; @@ -61,14 +68,14 @@ static inline int has_expired(const struct net_bridge *br, const struct net_bridge_fdb_entry *fdb) { return !fdb->is_static && - time_before_eq(fdb->ageing_timer + hold_time(br), jiffies); + time_before_eq(fdb->updated + hold_time(br), jiffies); } -static inline int br_mac_hash(const unsigned char *mac) +static inline int br_mac_hash(const unsigned char *mac, __u16 vid) { - /* use 1 byte of OUI cnd 3 bytes of NIC */ + /* use 1 byte of OUI and 3 bytes of NIC */ u32 key = get_unaligned((u32 *)(mac + 2)); - return jhash_1word(key, fdb_salt) & (BR_HASH_SIZE - 1); + return jhash_2words(key, vid, fdb_salt) & (BR_HASH_SIZE - 1); } static void fdb_rcu_free(struct rcu_head *head) @@ -78,16 +85,114 @@ static void fdb_rcu_free(struct rcu_head *head) kmem_cache_free(br_fdb_cache, ent); } -static inline void fdb_delete(struct net_bridge_fdb_entry *f) +/* When a static FDB entry is added, the mac address from the entry is + * added to the bridge private HW address list and all required ports + * are then updated with the new information. + * Called under RTNL. + */ +static void fdb_add_hw(struct net_bridge *br, const unsigned char *addr) +{ + int err; + struct net_bridge_port *p, *tmp; + + ASSERT_RTNL(); + + list_for_each_entry(p, &br->port_list, list) { + if (!br_promisc_port(p)) { + err = dev_uc_add(p->dev, addr); + if (err) + goto undo; + } + } + + return; +undo: + list_for_each_entry(tmp, &br->port_list, list) { + if (tmp == p) + break; + if (!br_promisc_port(tmp)) + dev_uc_del(tmp->dev, addr); + } +} + +/* When a static FDB entry is deleted, the HW address from that entry is + * also removed from the bridge private HW address list and updates all + * the ports with needed information. + * Called under RTNL. + */ +static void fdb_del_hw(struct net_bridge *br, const unsigned char *addr) +{ + struct net_bridge_port *p; + + ASSERT_RTNL(); + + list_for_each_entry(p, &br->port_list, list) { + if (!br_promisc_port(p)) + dev_uc_del(p->dev, addr); + } +} + +static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f) { + if (f->is_static) + fdb_del_hw(br, f->addr.addr); + hlist_del_rcu(&f->hlist); + fdb_notify(br, f, RTM_DELNEIGH); call_rcu(&f->rcu, fdb_rcu_free); } +/* Delete a local entry if no other port had the same address. */ +static void fdb_delete_local(struct net_bridge *br, + const struct net_bridge_port *p, + struct net_bridge_fdb_entry *f) +{ + const unsigned char *addr = f->addr.addr; + u16 vid = f->vlan_id; + struct net_bridge_port *op; + + /* Maybe another port has same hw addr? */ + list_for_each_entry(op, &br->port_list, list) { + if (op != p && ether_addr_equal(op->dev->dev_addr, addr) && + (!vid || nbp_vlan_find(op, vid))) { + f->dst = op; + f->added_by_user = 0; + return; + } + } + + /* Maybe bridge device has same hw addr? */ + if (p && ether_addr_equal(br->dev->dev_addr, addr) && + (!vid || br_vlan_find(br, vid))) { + f->dst = NULL; + f->added_by_user = 0; + return; + } + + fdb_delete(br, f); +} + +void br_fdb_find_delete_local(struct net_bridge *br, + const struct net_bridge_port *p, + const unsigned char *addr, u16 vid) +{ + struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)]; + struct net_bridge_fdb_entry *f; + + spin_lock_bh(&br->hash_lock); + f = fdb_find(head, addr, vid); + if (f && f->is_local && !f->added_by_user && f->dst == p) + fdb_delete_local(br, p, f); + spin_unlock_bh(&br->hash_lock); +} + void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr) { struct net_bridge *br = p->br; + struct net_port_vlans *pv = nbp_get_vlan_info(p); + bool no_vlan = !pv; int i; + u16 vid; spin_lock_bh(&br->hash_lock); @@ -98,28 +203,68 @@ void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr) struct net_bridge_fdb_entry *f; f = hlist_entry(h, struct net_bridge_fdb_entry, hlist); - if (f->dst == p && f->is_local) { - /* maybe another port has same hw addr? */ - struct net_bridge_port *op; - list_for_each_entry(op, &br->port_list, list) { - if (op != p && - !compare_ether_addr(op->dev->dev_addr, - f->addr.addr)) { - f->dst = op; - goto insert; - } - } - + if (f->dst == p && f->is_local && !f->added_by_user) { /* delete old one */ - fdb_delete(f); - goto insert; + fdb_delete_local(br, p, f); + + /* if this port has no vlan information + * configured, we can safely be done at + * this point. + */ + if (no_vlan) + goto insert; } } } - insert: + +insert: /* insert new address, may fail if invalid address or dup. */ - fdb_insert(br, p, newaddr); + fdb_insert(br, p, newaddr, 0); + + if (no_vlan) + goto done; + + /* Now add entries for every VLAN configured on the port. + * This function runs under RTNL so the bitmap will not change + * from under us. + */ + for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) + fdb_insert(br, p, newaddr, vid); + +done: + spin_unlock_bh(&br->hash_lock); +} + +void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr) +{ + struct net_bridge_fdb_entry *f; + struct net_port_vlans *pv; + u16 vid = 0; + + spin_lock_bh(&br->hash_lock); + /* If old entry was unassociated with any port, then delete it. */ + f = __br_fdb_get(br, br->dev->dev_addr, 0); + if (f && f->is_local && !f->dst) + fdb_delete_local(br, NULL, f); + + fdb_insert(br, NULL, newaddr, 0); + + /* Now remove and add entries for every VLAN configured on the + * bridge. This function runs under RTNL so the bitmap will not + * change from under us. + */ + pv = br_get_vlan_info(br); + if (!pv) + goto out; + + for_each_set_bit_from(vid, pv->vlan_bitmap, VLAN_N_VID) { + f = __br_fdb_get(br, br->dev->dev_addr, vid); + if (f && f->is_local && !f->dst) + fdb_delete_local(br, NULL, f); + fdb_insert(br, NULL, newaddr, vid); + } +out: spin_unlock_bh(&br->hash_lock); } @@ -127,30 +272,28 @@ void br_fdb_cleanup(unsigned long _data) { struct net_bridge *br = (struct net_bridge *)_data; unsigned long delay = hold_time(br); - unsigned long next_timer = jiffies + br->forward_delay; + unsigned long next_timer = jiffies + br->ageing_time; int i; - spin_lock_bh(&br->hash_lock); + spin_lock(&br->hash_lock); for (i = 0; i < BR_HASH_SIZE; i++) { struct net_bridge_fdb_entry *f; - struct hlist_node *h, *n; + struct hlist_node *n; - hlist_for_each_entry_safe(f, h, n, &br->hash[i], hlist) { + hlist_for_each_entry_safe(f, n, &br->hash[i], hlist) { unsigned long this_timer; if (f->is_static) continue; - this_timer = f->ageing_timer + delay; + this_timer = f->updated + delay; if (time_before_eq(this_timer, jiffies)) - fdb_delete(f); + fdb_delete(br, f); else if (time_before(this_timer, next_timer)) next_timer = this_timer; } } - spin_unlock_bh(&br->hash_lock); + spin_unlock(&br->hash_lock); - /* Add HZ/4 to ensure we round the jiffies upwards to be after the next - * timer, otherwise we might round down and will have no-op run. */ - mod_timer(&br->gc_timer, round_jiffies(next_timer + HZ/4)); + mod_timer(&br->gc_timer, round_jiffies_up(next_timer)); } /* Completely flush all dynamic entries in forwarding database.*/ @@ -161,16 +304,16 @@ void br_fdb_flush(struct net_bridge *br) spin_lock_bh(&br->hash_lock); for (i = 0; i < BR_HASH_SIZE; i++) { struct net_bridge_fdb_entry *f; - struct hlist_node *h, *n; - hlist_for_each_entry_safe(f, h, n, &br->hash[i], hlist) { + struct hlist_node *n; + hlist_for_each_entry_safe(f, n, &br->hash[i], hlist) { if (!f->is_static) - fdb_delete(f); + fdb_delete(br, f); } } spin_unlock_bh(&br->hash_lock); } -/* Flush all entries refering to a specific port. +/* Flush all entries referring to a specific port. * if do_all is set also flush static entries */ void br_fdb_delete_by_port(struct net_bridge *br, @@ -191,39 +334,27 @@ void br_fdb_delete_by_port(struct net_bridge *br, if (f->is_static && !do_all) continue; - /* - * if multiple ports all have the same device address - * then when one port is deleted, assign - * the local entry to other port - */ - if (f->is_local) { - struct net_bridge_port *op; - list_for_each_entry(op, &br->port_list, list) { - if (op != p && - !compare_ether_addr(op->dev->dev_addr, - f->addr.addr)) { - f->dst = op; - goto skip_delete; - } - } - } - fdb_delete(f); - skip_delete: ; + if (f->is_local) + fdb_delete_local(br, p, f); + else + fdb_delete(br, f); } } spin_unlock_bh(&br->hash_lock); } -/* No locking or refcounting, assumes caller has no preempt (rcu_read_lock) */ +/* No locking or refcounting, assumes caller has rcu_read_lock */ struct net_bridge_fdb_entry *__br_fdb_get(struct net_bridge *br, - const unsigned char *addr) + const unsigned char *addr, + __u16 vid) { - struct hlist_node *h; struct net_bridge_fdb_entry *fdb; - hlist_for_each_entry_rcu(fdb, h, &br->hash[br_mac_hash(addr)], hlist) { - if (!compare_ether_addr(fdb->addr.addr, addr)) { + hlist_for_each_entry_rcu(fdb, + &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; @@ -233,21 +364,24 @@ struct net_bridge_fdb_entry *__br_fdb_get(struct net_bridge *br, return NULL; } -#if defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE) +#if IS_ENABLED(CONFIG_ATM_LANE) /* Interface used by ATM LANE hook to test * if an addr is on some other bridge port */ int br_fdb_test_addr(struct net_device *dev, unsigned char *addr) { struct net_bridge_fdb_entry *fdb; + struct net_bridge_port *port; int ret; - if (!dev->br_port) - return 0; - rcu_read_lock(); - fdb = __br_fdb_get(dev->br_port->br, addr); - ret = fdb && fdb->dst->dev != dev && - fdb->dst->state == BR_STATE_FORWARDING; + port = br_port_get_rcu(dev); + if (!port) + ret = 0; + else { + fdb = __br_fdb_get(port->br, addr, 0); + ret = fdb && fdb->dst && fdb->dst->dev != dev && + fdb->dst->state == BR_STATE_FORWARDING; + } rcu_read_unlock(); return ret; @@ -263,20 +397,23 @@ int br_fdb_fillbuf(struct net_bridge *br, void *buf, { struct __fdb_entry *fe = buf; int i, num = 0; - struct hlist_node *h; struct net_bridge_fdb_entry *f; memset(buf, 0, maxnum*sizeof(struct __fdb_entry)); rcu_read_lock(); for (i = 0; i < BR_HASH_SIZE; i++) { - hlist_for_each_entry_rcu(f, h, &br->hash[i], hlist) { + hlist_for_each_entry_rcu(f, &br->hash[i], hlist) { if (num >= maxnum) goto out; if (has_expired(br, f)) continue; + /* ignore pseudo entry for local MAC address */ + if (!f->dst) + continue; + if (skip) { --skip; continue; @@ -291,7 +428,7 @@ int br_fdb_fillbuf(struct net_bridge *br, void *buf, fe->is_local = f->is_local; if (!f->is_static) - fe->ageing_timer_value = jiffies_to_clock_t(jiffies - f->ageing_timer); + fe->ageing_timer_value = jiffies_delta_to_clock_t(jiffies - f->updated); ++fe; ++num; } @@ -303,14 +440,29 @@ int br_fdb_fillbuf(struct net_bridge *br, void *buf, return num; } -static inline struct net_bridge_fdb_entry *fdb_find(struct hlist_head *head, - const unsigned char *addr) +static struct net_bridge_fdb_entry *fdb_find(struct hlist_head *head, + const unsigned char *addr, + __u16 vid) +{ + struct net_bridge_fdb_entry *fdb; + + hlist_for_each_entry(fdb, head, hlist) { + if (ether_addr_equal(fdb->addr.addr, addr) && + fdb->vlan_id == vid) + return fdb; + } + return NULL; +} + +static struct net_bridge_fdb_entry *fdb_find_rcu(struct hlist_head *head, + const unsigned char *addr, + __u16 vid) { - struct hlist_node *h; struct net_bridge_fdb_entry *fdb; - hlist_for_each_entry_rcu(fdb, h, head, hlist) { - if (!compare_ether_addr(fdb->addr.addr, addr)) + hlist_for_each_entry_rcu(fdb, head, hlist) { + if (ether_addr_equal(fdb->addr.addr, addr) && + fdb->vlan_id == vid) return fdb; } return NULL; @@ -319,68 +471,74 @@ static inline struct net_bridge_fdb_entry *fdb_find(struct hlist_head *head, static struct net_bridge_fdb_entry *fdb_create(struct hlist_head *head, struct net_bridge_port *source, const unsigned char *addr, - int is_local) + __u16 vid) { struct net_bridge_fdb_entry *fdb; fdb = kmem_cache_alloc(br_fdb_cache, GFP_ATOMIC); if (fdb) { memcpy(fdb->addr.addr, addr, ETH_ALEN); - hlist_add_head_rcu(&fdb->hlist, head); - fdb->dst = source; - fdb->is_local = is_local; - fdb->is_static = is_local; - fdb->ageing_timer = jiffies; + fdb->vlan_id = vid; + fdb->is_local = 0; + fdb->is_static = 0; + fdb->added_by_user = 0; + fdb->updated = fdb->used = jiffies; + hlist_add_head_rcu(&fdb->hlist, head); } return fdb; } static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source, - const unsigned char *addr) + const unsigned char *addr, u16 vid) { - struct hlist_head *head = &br->hash[br_mac_hash(addr)]; + struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)]; struct net_bridge_fdb_entry *fdb; if (!is_valid_ether_addr(addr)) return -EINVAL; - fdb = fdb_find(head, addr); + fdb = fdb_find(head, addr, vid); if (fdb) { /* it is okay to have multiple ports with same * address, just use the first one. */ if (fdb->is_local) return 0; - - printk(KERN_WARNING "%s adding interface with same address " + br_warn(br, "adding interface %s with same address " "as a received packet\n", - source->dev->name); - fdb_delete(fdb); + source ? source->dev->name : br->dev->name); + fdb_delete(br, fdb); } - if (!fdb_create(head, source, addr, 1)) + fdb = fdb_create(head, source, addr, vid); + if (!fdb) return -ENOMEM; + fdb->is_local = fdb->is_static = 1; + fdb_add_hw(br, addr); + fdb_notify(br, fdb, RTM_NEWNEIGH); return 0; } +/* Add entry for local address of interface */ int br_fdb_insert(struct net_bridge *br, struct net_bridge_port *source, - const unsigned char *addr) + const unsigned char *addr, u16 vid) { int ret; spin_lock_bh(&br->hash_lock); - ret = fdb_insert(br, source, addr); + ret = fdb_insert(br, source, addr, vid); spin_unlock_bh(&br->hash_lock); return ret; } void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, - const unsigned char *addr) + const unsigned char *addr, u16 vid, bool added_by_user) { - struct hlist_head *head = &br->hash[br_mac_hash(addr)]; + struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)]; struct net_bridge_fdb_entry *fdb; + bool fdb_modified = false; /* some users want to always flood. */ if (hold_time(br) == 0) @@ -391,26 +549,456 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, source->state == BR_STATE_FORWARDING)) return; - fdb = fdb_find(head, addr); + fdb = fdb_find_rcu(head, addr, vid); if (likely(fdb)) { /* attempt to update an entry for a local interface */ if (unlikely(fdb->is_local)) { if (net_ratelimit()) - printk(KERN_WARNING "%s: received packet with " - "own address as source address\n", - source->dev->name); + br_warn(br, "received packet on %s with " + "own address as source address\n", + source->dev->name); } else { /* fastpath: update of existing entry */ - fdb->dst = source; - fdb->ageing_timer = jiffies; + if (unlikely(source != fdb->dst)) { + fdb->dst = source; + fdb_modified = true; + } + fdb->updated = jiffies; + if (unlikely(added_by_user)) + fdb->added_by_user = 1; + if (unlikely(fdb_modified)) + fdb_notify(br, fdb, RTM_NEWNEIGH); } } else { spin_lock(&br->hash_lock); - if (!fdb_find(head, addr)) - fdb_create(head, source, addr, 0); + if (likely(!fdb_find(head, addr, vid))) { + fdb = fdb_create(head, source, addr, vid); + if (fdb) { + if (unlikely(added_by_user)) + fdb->added_by_user = 1; + fdb_notify(br, fdb, RTM_NEWNEIGH); + } + } /* else we lose race and someone else inserts * it first, don't bother updating */ spin_unlock(&br->hash_lock); } } + +static int fdb_to_nud(const struct net_bridge_fdb_entry *fdb) +{ + if (fdb->is_local) + return NUD_PERMANENT; + else if (fdb->is_static) + return NUD_NOARP; + else if (has_expired(fdb->dst->br, fdb)) + return NUD_STALE; + else + return NUD_REACHABLE; +} + +static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br, + const struct net_bridge_fdb_entry *fdb, + u32 portid, u32 seq, int type, unsigned int flags) +{ + unsigned long now = jiffies; + struct nda_cacheinfo ci; + struct nlmsghdr *nlh; + struct ndmsg *ndm; + + nlh = nlmsg_put(skb, portid, seq, type, sizeof(*ndm), flags); + if (nlh == NULL) + return -EMSGSIZE; + + ndm = nlmsg_data(nlh); + ndm->ndm_family = AF_BRIDGE; + ndm->ndm_pad1 = 0; + ndm->ndm_pad2 = 0; + ndm->ndm_flags = 0; + ndm->ndm_type = 0; + ndm->ndm_ifindex = fdb->dst ? fdb->dst->dev->ifindex : br->dev->ifindex; + ndm->ndm_state = fdb_to_nud(fdb); + + if (nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->addr)) + goto nla_put_failure; + if (nla_put_u32(skb, NDA_MASTER, br->dev->ifindex)) + goto nla_put_failure; + ci.ndm_used = jiffies_to_clock_t(now - fdb->used); + ci.ndm_confirmed = 0; + ci.ndm_updated = jiffies_to_clock_t(now - fdb->updated); + ci.ndm_refcnt = 0; + if (nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci)) + goto nla_put_failure; + + if (nla_put(skb, NDA_VLAN, sizeof(u16), &fdb->vlan_id)) + goto nla_put_failure; + + return nlmsg_end(skb, nlh); + +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +static inline size_t fdb_nlmsg_size(void) +{ + return NLMSG_ALIGN(sizeof(struct ndmsg)) + + nla_total_size(ETH_ALEN) /* NDA_LLADDR */ + + nla_total_size(sizeof(u32)) /* NDA_MASTER */ + + nla_total_size(sizeof(u16)) /* NDA_VLAN */ + + nla_total_size(sizeof(struct nda_cacheinfo)); +} + +static void fdb_notify(struct net_bridge *br, + const struct net_bridge_fdb_entry *fdb, int type) +{ + struct net *net = dev_net(br->dev); + struct sk_buff *skb; + int err = -ENOBUFS; + + skb = nlmsg_new(fdb_nlmsg_size(), GFP_ATOMIC); + if (skb == NULL) + goto errout; + + err = fdb_fill_info(skb, br, fdb, 0, 0, type, 0); + if (err < 0) { + /* -EMSGSIZE implies BUG in fdb_nlmsg_size() */ + WARN_ON(err == -EMSGSIZE); + kfree_skb(skb); + goto errout; + } + rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC); + return; +errout: + rtnl_set_sk_err(net, RTNLGRP_NEIGH, err); +} + +/* Dump information about entries, in response to GETNEIGH */ +int br_fdb_dump(struct sk_buff *skb, + struct netlink_callback *cb, + struct net_device *dev, + int idx) +{ + struct net_bridge *br = netdev_priv(dev); + int i; + + if (!(dev->priv_flags & IFF_EBRIDGE)) + goto out; + + for (i = 0; i < BR_HASH_SIZE; i++) { + struct net_bridge_fdb_entry *f; + + hlist_for_each_entry_rcu(f, &br->hash[i], hlist) { + if (idx < cb->args[0]) + goto skip; + + if (fdb_fill_info(skb, br, f, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_NEWNEIGH, + NLM_F_MULTI) < 0) + break; +skip: + ++idx; + } + } + +out: + return idx; +} + +/* Update (create or replace) forwarding database entry */ +static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr, + __u16 state, __u16 flags, __u16 vid) +{ + struct net_bridge *br = source->br; + struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)]; + struct net_bridge_fdb_entry *fdb; + bool modified = false; + + fdb = fdb_find(head, addr, vid); + if (fdb == NULL) { + if (!(flags & NLM_F_CREATE)) + return -ENOENT; + + fdb = fdb_create(head, source, addr, vid); + if (!fdb) + return -ENOMEM; + + modified = true; + } else { + if (flags & NLM_F_EXCL) + return -EEXIST; + + if (fdb->dst != source) { + fdb->dst = source; + modified = true; + } + } + + if (fdb_to_nud(fdb) != state) { + if (state & NUD_PERMANENT) { + fdb->is_local = 1; + if (!fdb->is_static) { + fdb->is_static = 1; + fdb_add_hw(br, addr); + } + } else if (state & NUD_NOARP) { + fdb->is_local = 0; + if (!fdb->is_static) { + fdb->is_static = 1; + fdb_add_hw(br, addr); + } + } else { + fdb->is_local = 0; + if (fdb->is_static) { + fdb->is_static = 0; + fdb_del_hw(br, addr); + } + } + + modified = true; + } + fdb->added_by_user = 1; + + fdb->used = jiffies; + if (modified) { + fdb->updated = jiffies; + fdb_notify(br, fdb, RTM_NEWNEIGH); + } + + return 0; +} + +static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge_port *p, + const unsigned char *addr, u16 nlh_flags, u16 vid) +{ + int err = 0; + + if (ndm->ndm_flags & NTF_USE) { + rcu_read_lock(); + br_fdb_update(p->br, p, addr, vid, true); + rcu_read_unlock(); + } else { + spin_lock_bh(&p->br->hash_lock); + err = fdb_add_entry(p, addr, ndm->ndm_state, + nlh_flags, vid); + spin_unlock_bh(&p->br->hash_lock); + } + + return err; +} + +/* Add new permanent fdb entry with RTM_NEWNEIGH */ +int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], + struct net_device *dev, + const unsigned char *addr, u16 nlh_flags) +{ + struct net_bridge_port *p; + int err = 0; + struct net_port_vlans *pv; + unsigned short vid = VLAN_N_VID; + + if (!(ndm->ndm_state & (NUD_PERMANENT|NUD_NOARP|NUD_REACHABLE))) { + pr_info("bridge: RTM_NEWNEIGH with invalid state %#x\n", ndm->ndm_state); + return -EINVAL; + } + + if (tb[NDA_VLAN]) { + if (nla_len(tb[NDA_VLAN]) != sizeof(unsigned short)) { + pr_info("bridge: RTM_NEWNEIGH with invalid vlan\n"); + return -EINVAL; + } + + vid = nla_get_u16(tb[NDA_VLAN]); + + if (!vid || vid >= VLAN_VID_MASK) { + pr_info("bridge: RTM_NEWNEIGH with invalid vlan id %d\n", + vid); + return -EINVAL; + } + } + + if (is_zero_ether_addr(addr)) { + pr_info("bridge: RTM_NEWNEIGH with invalid ether address\n"); + return -EINVAL; + } + + p = br_port_get_rtnl(dev); + if (p == NULL) { + pr_info("bridge: RTM_NEWNEIGH %s not a bridge port\n", + dev->name); + return -EINVAL; + } + + pv = nbp_get_vlan_info(p); + if (vid != VLAN_N_VID) { + if (!pv || !test_bit(vid, pv->vlan_bitmap)) { + pr_info("bridge: RTM_NEWNEIGH with unconfigured " + "vlan %d on port %s\n", vid, dev->name); + return -EINVAL; + } + + /* VID was specified, so use it. */ + err = __br_fdb_add(ndm, p, addr, nlh_flags, vid); + } else { + if (!pv || bitmap_empty(pv->vlan_bitmap, VLAN_N_VID)) { + err = __br_fdb_add(ndm, p, addr, nlh_flags, 0); + goto out; + } + + /* We have vlans configured on this port and user didn't + * specify a VLAN. To be nice, add/update entry for every + * vlan on this port. + */ + for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { + err = __br_fdb_add(ndm, p, addr, nlh_flags, vid); + if (err) + goto out; + } + } + +out: + return err; +} + +static int fdb_delete_by_addr(struct net_bridge *br, const u8 *addr, u16 vlan) +{ + 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) + return -ENOENT; + + fdb_delete(br, fdb); + return 0; +} + +static int __br_fdb_delete(struct net_bridge_port *p, + const unsigned char *addr, u16 vid) +{ + int err; + + spin_lock_bh(&p->br->hash_lock); + err = fdb_delete_by_addr(p->br, addr, vid); + spin_unlock_bh(&p->br->hash_lock); + + return err; +} + +/* Remove neighbor entry with RTM_DELNEIGH */ +int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], + struct net_device *dev, + const unsigned char *addr) +{ + struct net_bridge_port *p; + int err; + struct net_port_vlans *pv; + unsigned short vid = VLAN_N_VID; + + if (tb[NDA_VLAN]) { + if (nla_len(tb[NDA_VLAN]) != sizeof(unsigned short)) { + pr_info("bridge: RTM_NEWNEIGH with invalid vlan\n"); + return -EINVAL; + } + + vid = nla_get_u16(tb[NDA_VLAN]); + + if (!vid || vid >= VLAN_VID_MASK) { + pr_info("bridge: RTM_NEWNEIGH with invalid vlan id %d\n", + vid); + return -EINVAL; + } + } + p = br_port_get_rtnl(dev); + if (p == NULL) { + pr_info("bridge: RTM_DELNEIGH %s not a bridge port\n", + dev->name); + return -EINVAL; + } + + pv = nbp_get_vlan_info(p); + if (vid != VLAN_N_VID) { + if (!pv || !test_bit(vid, pv->vlan_bitmap)) { + pr_info("bridge: RTM_DELNEIGH with unconfigured " + "vlan %d on port %s\n", vid, dev->name); + return -EINVAL; + } + + err = __br_fdb_delete(p, addr, vid); + } else { + if (!pv || bitmap_empty(pv->vlan_bitmap, VLAN_N_VID)) { + err = __br_fdb_delete(p, addr, 0); + goto out; + } + + /* We have vlans configured on this port and user didn't + * specify a VLAN. To be nice, add/update entry for every + * vlan on this port. + */ + err = -ENOENT; + for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { + err &= __br_fdb_delete(p, addr, vid); + } + } +out: + return err; +} + +int br_fdb_sync_static(struct net_bridge *br, struct net_bridge_port *p) +{ + struct net_bridge_fdb_entry *fdb, *tmp; + int i; + int err; + + ASSERT_RTNL(); + + for (i = 0; i < BR_HASH_SIZE; i++) { + hlist_for_each_entry(fdb, &br->hash[i], hlist) { + /* We only care for static entries */ + if (!fdb->is_static) + continue; + + err = dev_uc_add(p->dev, fdb->addr.addr); + if (err) + goto rollback; + } + } + return 0; + +rollback: + for (i = 0; i < BR_HASH_SIZE; i++) { + hlist_for_each_entry(tmp, &br->hash[i], hlist) { + /* If we reached the fdb that failed, we can stop */ + if (tmp == fdb) + break; + + /* We only care for static entries */ + if (!tmp->is_static) + continue; + + dev_uc_del(p->dev, tmp->addr.addr); + } + } + return err; +} + +void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p) +{ + struct net_bridge_fdb_entry *fdb; + int i; + + ASSERT_RTNL(); + + for (i = 0; i < BR_HASH_SIZE; i++) { + hlist_for_each_entry_rcu(fdb, &br->hash[i], hlist) { + /* We only care for static entries */ + if (!fdb->is_static) + continue; + + dev_uc_del(p->dev, fdb->addr.addr); + } + } +} diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index bc1704ac6cd..056b67b0e27 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -11,40 +11,40 @@ * 2 of the License, or (at your option) any later version. */ +#include <linux/err.h> +#include <linux/slab.h> #include <linux/kernel.h> #include <linux/netdevice.h> +#include <linux/netpoll.h> #include <linux/skbuff.h> #include <linux/if_vlan.h> #include <linux/netfilter_bridge.h> #include "br_private.h" -/* Don't forward packets to originating port or forwarding diasabled */ +static int deliver_clone(const struct net_bridge_port *prev, + struct sk_buff *skb, + void (*__packet_hook)(const struct net_bridge_port *p, + struct sk_buff *skb)); + +/* Don't forward packets to originating port or forwarding disabled */ static inline int should_deliver(const struct net_bridge_port *p, const struct sk_buff *skb) { - return (((p->flags & BR_HAIRPIN_MODE) || skb->dev != p->dev) && - p->state == BR_STATE_FORWARDING); -} - -static inline unsigned packet_length(const struct sk_buff *skb) -{ - return skb->len - (skb->protocol == htons(ETH_P_8021Q) ? VLAN_HLEN : 0); + return ((p->flags & BR_HAIRPIN_MODE) || skb->dev != p->dev) && + br_allowed_egress(p->br, nbp_get_vlan_info(p), skb) && + p->state == BR_STATE_FORWARDING; } int br_dev_queue_push_xmit(struct sk_buff *skb) { - /* drop mtu oversized packets except gso */ - if (packet_length(skb) > skb->dev->mtu && !skb_is_gso(skb)) + /* ip_fragment doesn't copy the MAC header */ + if (nf_bridge_maybe_copy_header(skb) || + !is_skb_forwardable(skb->dev, skb)) { kfree_skb(skb); - else { - /* ip_refrag calls ip_fragment, doesn't copy the MAC header. */ - if (nf_bridge_maybe_copy_header(skb)) - kfree_skb(skb); - else { - skb_push(skb, ETH_HLEN); - - dev_queue_xmit(skb); - } + } else { + skb_push(skb, ETH_HLEN); + br_drop_fake_rtable(skb); + dev_queue_xmit(skb); } return 0; @@ -52,16 +52,31 @@ int br_dev_queue_push_xmit(struct sk_buff *skb) int br_forward_finish(struct sk_buff *skb) { - return NF_HOOK(PF_BRIDGE, NF_BR_POST_ROUTING, skb, NULL, skb->dev, + return NF_HOOK(NFPROTO_BRIDGE, NF_BR_POST_ROUTING, skb, NULL, skb->dev, br_dev_queue_push_xmit); } static void __br_deliver(const struct net_bridge_port *to, struct sk_buff *skb) { + skb = br_handle_vlan(to->br, nbp_get_vlan_info(to), skb); + if (!skb) + return; + skb->dev = to->dev; - NF_HOOK(PF_BRIDGE, NF_BR_LOCAL_OUT, skb, NULL, skb->dev, - br_forward_finish); + + if (unlikely(netpoll_tx_running(to->br->dev))) { + if (!is_skb_forwardable(skb->dev, skb)) + kfree_skb(skb); + else { + skb_push(skb, ETH_HLEN); + br_netpoll_send_skb(to, skb); + } + return; + } + + NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, skb, NULL, skb->dev, + br_forward_finish); } static void __br_forward(const struct net_bridge_port *to, struct sk_buff *skb) @@ -73,18 +88,22 @@ static void __br_forward(const struct net_bridge_port *to, struct sk_buff *skb) return; } + skb = br_handle_vlan(to->br, nbp_get_vlan_info(to), skb); + if (!skb) + return; + indev = skb->dev; skb->dev = to->dev; skb_forward_csum(skb); - NF_HOOK(PF_BRIDGE, NF_BR_FORWARD, skb, indev, skb->dev, - br_forward_finish); + NF_HOOK(NFPROTO_BRIDGE, NF_BR_FORWARD, skb, indev, skb->dev, + br_forward_finish); } /* called with rcu_read_lock */ void br_deliver(const struct net_bridge_port *to, struct sk_buff *skb) { - if (should_deliver(to, skb)) { + if (to && should_deliver(to, skb)) { __br_deliver(to, skb); return; } @@ -93,61 +112,169 @@ void br_deliver(const struct net_bridge_port *to, struct sk_buff *skb) } /* called with rcu_read_lock */ -void br_forward(const struct net_bridge_port *to, struct sk_buff *skb) +void br_forward(const struct net_bridge_port *to, struct sk_buff *skb, struct sk_buff *skb0) { if (should_deliver(to, skb)) { - __br_forward(to, skb); + if (skb0) + deliver_clone(to, skb, __br_forward); + else + __br_forward(to, skb); return; } - kfree_skb(skb); + if (!skb0) + kfree_skb(skb); } -/* called under bridge lock */ -static void br_flood(struct net_bridge *br, struct sk_buff *skb, +static int deliver_clone(const struct net_bridge_port *prev, + struct sk_buff *skb, + void (*__packet_hook)(const struct net_bridge_port *p, + struct sk_buff *skb)) +{ + struct net_device *dev = BR_INPUT_SKB_CB(skb)->brdev; + + skb = skb_clone(skb, GFP_ATOMIC); + if (!skb) { + dev->stats.tx_dropped++; + return -ENOMEM; + } + + __packet_hook(prev, skb); + return 0; +} + +static struct net_bridge_port *maybe_deliver( + struct net_bridge_port *prev, struct net_bridge_port *p, + struct sk_buff *skb, void (*__packet_hook)(const struct net_bridge_port *p, struct sk_buff *skb)) { + int err; + + if (!should_deliver(p, skb)) + return prev; + + if (!prev) + goto out; + + err = deliver_clone(prev, skb, __packet_hook); + if (err) + return ERR_PTR(err); + +out: + return p; +} + +/* called under bridge lock */ +static void br_flood(struct net_bridge *br, struct sk_buff *skb, + struct sk_buff *skb0, + void (*__packet_hook)(const struct net_bridge_port *p, + struct sk_buff *skb), + bool unicast) +{ struct net_bridge_port *p; struct net_bridge_port *prev; prev = NULL; list_for_each_entry_rcu(p, &br->port_list, list) { - if (should_deliver(p, skb)) { - if (prev != NULL) { - struct sk_buff *skb2; + /* Do not flood unicast traffic to ports that turn it off */ + if (unicast && !(p->flags & BR_FLOOD)) + continue; + prev = maybe_deliver(prev, p, skb, __packet_hook); + if (IS_ERR(prev)) + goto out; + } - if ((skb2 = skb_clone(skb, GFP_ATOMIC)) == NULL) { - br->dev->stats.tx_dropped++; - kfree_skb(skb); - return; - } + if (!prev) + goto out; - __packet_hook(prev, skb2); - } + if (skb0) + deliver_clone(prev, skb, __packet_hook); + else + __packet_hook(prev, skb); + return; - prev = p; - } +out: + if (!skb0) + kfree_skb(skb); +} + + +/* called with rcu_read_lock */ +void br_flood_deliver(struct net_bridge *br, struct sk_buff *skb, bool unicast) +{ + br_flood(br, skb, NULL, __br_deliver, unicast); +} + +/* called under bridge lock */ +void br_flood_forward(struct net_bridge *br, struct sk_buff *skb, + struct sk_buff *skb2, bool unicast) +{ + br_flood(br, skb, skb2, __br_forward, unicast); +} + +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING +/* called with rcu_read_lock */ +static void br_multicast_flood(struct net_bridge_mdb_entry *mdst, + struct sk_buff *skb, struct sk_buff *skb0, + void (*__packet_hook)( + const struct net_bridge_port *p, + struct sk_buff *skb)) +{ + struct net_device *dev = BR_INPUT_SKB_CB(skb)->brdev; + struct net_bridge *br = netdev_priv(dev); + struct net_bridge_port *prev = NULL; + struct net_bridge_port_group *p; + struct hlist_node *rp; + + rp = rcu_dereference(hlist_first_rcu(&br->router_list)); + p = mdst ? rcu_dereference(mdst->ports) : NULL; + while (p || rp) { + struct net_bridge_port *port, *lport, *rport; + + lport = p ? p->port : NULL; + rport = rp ? hlist_entry(rp, struct net_bridge_port, rlist) : + NULL; + + port = (unsigned long)lport > (unsigned long)rport ? + lport : rport; + + prev = maybe_deliver(prev, port, skb, __packet_hook); + if (IS_ERR(prev)) + goto out; + + if ((unsigned long)lport >= (unsigned long)port) + p = rcu_dereference(p->next); + if ((unsigned long)rport >= (unsigned long)port) + rp = rcu_dereference(hlist_next_rcu(rp)); } - if (prev != NULL) { + if (!prev) + goto out; + + if (skb0) + deliver_clone(prev, skb, __packet_hook); + else __packet_hook(prev, skb); - return; - } + return; - kfree_skb(skb); +out: + if (!skb0) + kfree_skb(skb); } - /* called with rcu_read_lock */ -void br_flood_deliver(struct net_bridge *br, struct sk_buff *skb) +void br_multicast_deliver(struct net_bridge_mdb_entry *mdst, + struct sk_buff *skb) { - br_flood(br, skb, __br_deliver); + br_multicast_flood(mdst, skb, NULL, __br_deliver); } -/* called under bridge lock */ -void br_flood_forward(struct net_bridge *br, struct sk_buff *skb) +/* called with rcu_read_lock */ +void br_multicast_forward(struct net_bridge_mdb_entry *mdst, + struct sk_buff *skb, struct sk_buff *skb2) { - br_flood(br, skb, __br_forward); + br_multicast_flood(mdst, skb, skb2, __br_forward); } +#endif diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index a2cbe61f6e6..3eca3fdf8fe 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -13,13 +13,17 @@ #include <linux/kernel.h> #include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <linux/netpoll.h> #include <linux/ethtool.h> #include <linux/if_arp.h> #include <linux/module.h> #include <linux/init.h> #include <linux/rtnetlink.h> #include <linux/if_ether.h> +#include <linux/slab.h> #include <net/sock.h> +#include <linux/if_vlan.h> #include "br_private.h" @@ -31,20 +35,18 @@ */ static int port_cost(struct net_device *dev) { - if (dev->ethtool_ops && dev->ethtool_ops->get_settings) { - struct ethtool_cmd ecmd = { .cmd = ETHTOOL_GSET, }; - - if (!dev->ethtool_ops->get_settings(dev, &ecmd)) { - switch(ecmd.speed) { - case SPEED_10000: - return 2; - case SPEED_1000: - return 4; - case SPEED_100: - return 19; - case SPEED_10: - return 100; - } + struct ethtool_cmd ecmd; + + if (!__ethtool_get_settings(dev, &ecmd)) { + switch (ethtool_cmd_speed(&ecmd)) { + case SPEED_10000: + return 2; + case SPEED_1000: + return 4; + case SPEED_100: + return 19; + case SPEED_10: + return 100; } } @@ -59,32 +61,135 @@ static int port_cost(struct net_device *dev) } -/* - * Check for port carrier transistions. - * Called from work queue to allow for calling functions that - * might sleep (such as speed check), and to debounce. - */ +/* Check for port carrier transitions. */ void br_port_carrier_check(struct net_bridge_port *p) { struct net_device *dev = p->dev; struct net_bridge *br = p->br; - if (netif_carrier_ok(dev)) + if (!(p->flags & BR_ADMIN_COST) && + netif_running(dev) && netif_oper_up(dev)) p->path_cost = port_cost(dev); - if (netif_running(br->dev)) { - spin_lock_bh(&br->lock); - if (netif_carrier_ok(dev)) { - if (p->state == BR_STATE_DISABLED) - br_stp_enable_port(p); + if (!netif_running(br->dev)) + return; + + spin_lock_bh(&br->lock); + if (netif_running(dev) && netif_oper_up(dev)) { + if (p->state == BR_STATE_DISABLED) + br_stp_enable_port(p); + } else { + if (p->state != BR_STATE_DISABLED) + br_stp_disable_port(p); + } + spin_unlock_bh(&br->lock); +} + +static void br_port_set_promisc(struct net_bridge_port *p) +{ + int err = 0; + + if (br_promisc_port(p)) + return; + + err = dev_set_promiscuity(p->dev, 1); + if (err) + return; + + br_fdb_unsync_static(p->br, p); + p->flags |= BR_PROMISC; +} + +static void br_port_clear_promisc(struct net_bridge_port *p) +{ + int err; + + /* Check if the port is already non-promisc or if it doesn't + * support UNICAST filtering. Without unicast filtering support + * we'll end up re-enabling promisc mode anyway, so just check for + * it here. + */ + if (!br_promisc_port(p) || !(p->dev->priv_flags & IFF_UNICAST_FLT)) + return; + + /* Since we'll be clearing the promisc mode, program the port + * first so that we don't have interruption in traffic. + */ + err = br_fdb_sync_static(p->br, p); + if (err) + return; + + dev_set_promiscuity(p->dev, -1); + p->flags &= ~BR_PROMISC; +} + +/* When a port is added or removed or when certain port flags + * change, this function is called to automatically manage + * promiscuity setting of all the bridge ports. We are always called + * under RTNL so can skip using rcu primitives. + */ +void br_manage_promisc(struct net_bridge *br) +{ + struct net_bridge_port *p; + bool set_all = false; + + /* If vlan filtering is disabled or bridge interface is placed + * into promiscuous mode, place all ports in promiscuous mode. + */ + if ((br->dev->flags & IFF_PROMISC) || !br_vlan_enabled(br)) + set_all = true; + + list_for_each_entry(p, &br->port_list, list) { + if (set_all) { + br_port_set_promisc(p); } else { - if (p->state != BR_STATE_DISABLED) - br_stp_disable_port(p); + /* If the number of auto-ports is <= 1, then all other + * ports will have their output configuration + * statically specified through fdbs. Since ingress + * on the auto-port becomes forwarding/egress to other + * ports and egress configuration is statically known, + * we can say that ingress configuration of the + * auto-port is also statically known. + * This lets us disable promiscuous mode and write + * this config to hw. + */ + if (br->auto_cnt == 0 || + (br->auto_cnt == 1 && br_auto_port(p))) + br_port_clear_promisc(p); + else + br_port_set_promisc(p); } - spin_unlock_bh(&br->lock); } } +static void nbp_update_port_count(struct net_bridge *br) +{ + struct net_bridge_port *p; + u32 cnt = 0; + + list_for_each_entry(p, &br->port_list, list) { + if (br_auto_port(p)) + cnt++; + } + if (br->auto_cnt != cnt) { + br->auto_cnt = cnt; + br_manage_promisc(br); + } +} + +static void nbp_delete_promisc(struct net_bridge_port *p) +{ + /* If port is currently promiscuous, unset promiscuity. + * Otherwise, it is a static port so remove all addresses + * from it. + */ + dev_set_allmulti(p->dev, -1); + if (br_promisc_port(p)) + dev_set_promiscuity(p->dev, -1); + else + br_fdb_unsync_static(p->br, p); +} + static void release_nbp(struct kobject *kobj) { struct net_bridge_port *p @@ -131,9 +236,9 @@ static void del_nbp(struct net_bridge_port *p) struct net_bridge *br = p->br; struct net_device *dev = p->dev; - sysfs_remove_link(br->ifobj, dev->name); + sysfs_remove_link(br->ifobj, p->dev->name); - dev_set_promiscuity(dev, -1); + nbp_delete_promisc(p); spin_lock_bh(&br->lock); br_stp_disable_port(p); @@ -141,78 +246,47 @@ static void del_nbp(struct net_bridge_port *p) br_ifinfo_notify(RTM_DELLINK, p); + list_del_rcu(&p->list); + + nbp_vlan_flush(p); br_fdb_delete_by_port(br, p, 1); + nbp_update_port_count(br); - list_del_rcu(&p->list); + dev->priv_flags &= ~IFF_BRIDGE_PORT; + + netdev_rx_handler_unregister(dev); - rcu_assign_pointer(dev->br_port, NULL); + netdev_upper_dev_unlink(dev, br->dev); + + br_multicast_del_port(p); kobject_uevent(&p->kobj, KOBJ_REMOVE); kobject_del(&p->kobj); + br_netpoll_disable(p); + call_rcu(&p->rcu, destroy_nbp_rcu); } -/* called with RTNL */ -static void del_br(struct net_bridge *br, struct list_head *head) +/* Delete bridge device */ +void br_dev_delete(struct net_device *dev, struct list_head *head) { + struct net_bridge *br = netdev_priv(dev); struct net_bridge_port *p, *n; list_for_each_entry_safe(p, n, &br->port_list, list) { del_nbp(p); } + br_fdb_delete_by_port(br, NULL, 1); + + br_vlan_flush(br); del_timer_sync(&br->gc_timer); br_sysfs_delbr(br->dev); unregister_netdevice_queue(br->dev, head); } -static struct net_device *new_bridge_dev(struct net *net, const char *name) -{ - struct net_bridge *br; - struct net_device *dev; - - dev = alloc_netdev(sizeof(struct net_bridge), name, - br_dev_setup); - - if (!dev) - return NULL; - dev_net_set(dev, net); - - br = netdev_priv(dev); - br->dev = dev; - - spin_lock_init(&br->lock); - INIT_LIST_HEAD(&br->port_list); - spin_lock_init(&br->hash_lock); - - br->bridge_id.prio[0] = 0x80; - br->bridge_id.prio[1] = 0x00; - - memcpy(br->group_addr, br_group_address, ETH_ALEN); - - br->feature_mask = dev->features; - br->stp_enabled = BR_NO_STP; - br->designated_root = br->bridge_id; - br->root_path_cost = 0; - br->root_port = 0; - br->bridge_max_age = br->max_age = 20 * HZ; - br->bridge_hello_time = br->hello_time = 2 * HZ; - br->bridge_forward_delay = br->forward_delay = 15 * HZ; - br->topology_change = 0; - br->topology_change_detected = 0; - br->ageing_time = 300 * HZ; - - br_netfilter_rtable_init(br); - - INIT_LIST_HEAD(&br->age_list); - - br_stp_timer_init(br); - - return dev; -} - /* find an available port number */ static int find_portno(struct net_bridge *br) { @@ -256,50 +330,33 @@ static struct net_bridge_port *new_nbp(struct net_bridge *br, p->path_cost = port_cost(dev); p->priority = 0x8000 >> BR_PORT_BITS; p->port_no = index; - p->flags = 0; + p->flags = BR_LEARNING | BR_FLOOD; br_init_port(p); p->state = BR_STATE_DISABLED; br_stp_port_timer_init(p); + br_multicast_add_port(p); return p; } -static struct device_type br_type = { - .name = "bridge", -}; - int br_add_bridge(struct net *net, const char *name) { struct net_device *dev; - int ret; + int res; + + dev = alloc_netdev(sizeof(struct net_bridge), name, + br_dev_setup); - dev = new_bridge_dev(net, name); if (!dev) return -ENOMEM; - rtnl_lock(); - if (strchr(dev->name, '%')) { - ret = dev_alloc_name(dev, dev->name); - if (ret < 0) - goto out_free; - } - - SET_NETDEV_DEVTYPE(dev, &br_type); - - ret = register_netdevice(dev); - if (ret) - goto out_free; - - ret = br_sysfs_addbr(dev); - if (ret) - unregister_netdevice(dev); - out: - rtnl_unlock(); - return ret; + dev_net_set(dev, net); + dev->rtnl_link_ops = &br_link_ops; -out_free: - free_netdev(dev); - goto out; + res = register_netdev(dev); + if (res) + free_netdev(dev); + return res; } int br_del_bridge(struct net *net, const char *name) @@ -323,7 +380,7 @@ int br_del_bridge(struct net *net, const char *name) } else - del_br(netdev_priv(dev), NULL); + br_dev_delete(dev, NULL); rtnl_unlock(); return ret; @@ -351,15 +408,16 @@ int br_min_mtu(const struct net_bridge *br) /* * Recomputes features using slave's features */ -void br_features_recompute(struct net_bridge *br) +netdev_features_t br_features_recompute(struct net_bridge *br, + netdev_features_t features) { struct net_bridge_port *p; - unsigned long features, mask; + netdev_features_t mask; - features = mask = br->feature_mask; if (list_empty(&br->port_list)) - goto done; + return features; + mask = features; features &= ~NETIF_F_ONE_FOR_ALL; list_for_each_entry(p, &br->port_list, list) { @@ -367,8 +425,7 @@ void br_features_recompute(struct net_bridge *br) p->dev->features, mask); } -done: - br->dev->features = netdev_fix_features(features, NULL); + return features; } /* called with RTNL */ @@ -376,10 +433,12 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) { struct net_bridge_port *p; int err = 0; + bool changed_addr; /* Don't allow bridging non-ethernet like devices */ if ((dev->flags & IFF_LOOPBACK) || - dev->type != ARPHRD_ETHER || dev->addr_len != ETH_ALEN) + dev->type != ARPHRD_ETHER || dev->addr_len != ETH_ALEN || + !is_valid_ether_addr(dev->dev_addr)) return -EINVAL; /* No bridging of bridges */ @@ -387,7 +446,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) return -ELOOP; /* Device is already being bridged */ - if (dev->br_port != NULL) + if (br_port_exists(dev)) return -EBUSY; /* No bridging devices that dislike that (e.g. wireless) */ @@ -398,51 +457,79 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) if (IS_ERR(p)) return PTR_ERR(p); - err = dev_set_promiscuity(dev, 1); + call_netdevice_notifiers(NETDEV_JOIN, dev); + + err = dev_set_allmulti(dev, 1); if (err) goto put_back; err = kobject_init_and_add(&p->kobj, &brport_ktype, &(dev->dev.kobj), SYSFS_BRIDGE_PORT_ATTR); if (err) - goto err0; - - err = br_fdb_insert(br, p, dev->dev_addr); - if (err) goto err1; err = br_sysfs_addif(p); if (err) goto err2; - rcu_assign_pointer(dev->br_port, p); + err = br_netpoll_enable(p); + if (err) + goto err3; + + err = netdev_master_upper_dev_link(dev, br->dev); + if (err) + goto err4; + + err = netdev_rx_handler_register(dev, br_handle_frame, p); + if (err) + goto err5; + + dev->priv_flags |= IFF_BRIDGE_PORT; + dev_disable_lro(dev); list_add_rcu(&p->list, &br->port_list); + nbp_update_port_count(br); + + netdev_update_features(br->dev); + + if (br->dev->needed_headroom < dev->needed_headroom) + br->dev->needed_headroom = dev->needed_headroom; + + if (br_fdb_insert(br, p, dev->dev_addr, 0)) + netdev_err(dev, "failed insert local address bridge forwarding table\n"); + spin_lock_bh(&br->lock); - br_stp_recalculate_bridge_id(br); - br_features_recompute(br); + changed_addr = br_stp_recalculate_bridge_id(br); - if ((dev->flags & IFF_UP) && netif_carrier_ok(dev) && + if (netif_running(dev) && netif_oper_up(dev) && (br->dev->flags & IFF_UP)) br_stp_enable_port(p); spin_unlock_bh(&br->lock); br_ifinfo_notify(RTM_NEWLINK, p); + if (changed_addr) + call_netdevice_notifiers(NETDEV_CHANGEADDR, br->dev); + dev_set_mtu(br->dev, br_min_mtu(br)); kobject_uevent(&p->kobj, KOBJ_ADD); return 0; + +err5: + netdev_upper_dev_unlink(dev, br->dev); +err4: + br_netpoll_disable(p); +err3: + sysfs_remove_link(br->ifobj, p->dev->name); err2: - br_fdb_delete_by_port(br, p, 1); -err1: kobject_put(&p->kobj); p = NULL; /* kobject_put frees */ -err0: - dev_set_promiscuity(dev, -1); +err1: + dev_set_allmulti(dev, -1); put_back: dev_put(dev); kfree(p); @@ -452,32 +539,35 @@ put_back: /* called with RTNL */ int br_del_if(struct net_bridge *br, struct net_device *dev) { - struct net_bridge_port *p = dev->br_port; + struct net_bridge_port *p; + bool changed_addr; + p = br_port_get_rtnl(dev); if (!p || p->br != br) return -EINVAL; + /* Since more than one interface can be attached to a bridge, + * there still maybe an alternate path for netconsole to use; + * therefore there is no reason for a NETDEV_RELEASE event. + */ del_nbp(p); spin_lock_bh(&br->lock); - br_stp_recalculate_bridge_id(br); - br_features_recompute(br); + changed_addr = br_stp_recalculate_bridge_id(br); spin_unlock_bh(&br->lock); + if (changed_addr) + call_netdevice_notifiers(NETDEV_CHANGEADDR, br->dev); + + netdev_update_features(br->dev); + return 0; } -void br_net_exit(struct net *net) +void br_port_flags_change(struct net_bridge_port *p, unsigned long mask) { - struct net_device *dev; - LIST_HEAD(list); - - rtnl_lock(); - for_each_netdev(net, dev) - if (dev->priv_flags & IFF_EBRIDGE) - del_br(netdev_priv(dev), &list); - - unregister_netdevice_many(&list); - rtnl_unlock(); + struct net_bridge *br = p->br; + if (mask & BR_AUTO_MASK) + nbp_update_port_count(br); } diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 5ee1a3682bf..366c4364907 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -11,48 +11,84 @@ * 2 of the License, or (at your option) any later version. */ +#include <linux/slab.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/netfilter_bridge.h> +#include <linux/export.h> +#include <linux/rculist.h> #include "br_private.h" -/* Bridge group multicast address 802.1d (pg 51). */ -const u8 br_group_address[ETH_ALEN] = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 }; +/* Hook for brouter */ +br_should_route_hook_t __rcu *br_should_route_hook __read_mostly; +EXPORT_SYMBOL(br_should_route_hook); -static void br_pass_frame_up(struct net_bridge *br, struct sk_buff *skb) +static int br_pass_frame_up(struct sk_buff *skb) { - struct net_device *indev, *brdev = br->dev; - - brdev->stats.rx_packets++; - brdev->stats.rx_bytes += skb->len; + struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev; + struct net_bridge *br = netdev_priv(brdev); + struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats); + struct net_port_vlans *pv; + + u64_stats_update_begin(&brstats->syncp); + brstats->rx_packets++; + brstats->rx_bytes += skb->len; + u64_stats_update_end(&brstats->syncp); + + /* Bridge is just like any other port. Make sure the + * packet is allowed except in promisc modue when someone + * may be running packet capture. + */ + pv = br_get_vlan_info(br); + if (!(brdev->flags & IFF_PROMISC) && + !br_allowed_egress(br, pv, skb)) { + kfree_skb(skb); + return NET_RX_DROP; + } indev = skb->dev; skb->dev = brdev; + skb = br_handle_vlan(br, pv, skb); + if (!skb) + return NET_RX_DROP; - NF_HOOK(PF_BRIDGE, NF_BR_LOCAL_IN, skb, indev, NULL, - netif_receive_skb); + return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, skb, indev, NULL, + netif_receive_skb); } -/* note: already called with rcu_read_lock (preempt_disabled) */ +/* note: already called with rcu_read_lock */ int br_handle_frame_finish(struct sk_buff *skb) { const unsigned char *dest = eth_hdr(skb)->h_dest; - struct net_bridge_port *p = rcu_dereference(skb->dev->br_port); + struct net_bridge_port *p = br_port_get_rcu(skb->dev); struct net_bridge *br; struct net_bridge_fdb_entry *dst; + struct net_bridge_mdb_entry *mdst; struct sk_buff *skb2; + bool unicast = true; + u16 vid = 0; if (!p || p->state == BR_STATE_DISABLED) goto drop; + if (!br_allowed_ingress(p->br, nbp_get_vlan_info(p), skb, &vid)) + goto out; + /* insert into forwarding database after filtering to avoid spoofing */ br = p->br; - br_fdb_update(br, p, eth_hdr(skb)->h_source); + if (p->flags & BR_LEARNING) + br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, false); + + if (!is_broadcast_ether_addr(dest) && is_multicast_ether_addr(dest) && + br_multicast_rcv(br, p, skb, vid)) + goto drop; if (p->state == BR_STATE_LEARNING) goto drop; + BR_INPUT_SKB_CB(skb)->brdev = br->dev; + /* The packet skb2 goes to the local host (NULL to skip). */ skb2 = NULL; @@ -61,28 +97,43 @@ int br_handle_frame_finish(struct sk_buff *skb) dst = NULL; - if (is_multicast_ether_addr(dest)) { - br->dev->stats.multicast++; + if (is_broadcast_ether_addr(dest)) { skb2 = skb; - } else if ((dst = __br_fdb_get(br, dest)) && dst->is_local) { + unicast = false; + } else if (is_multicast_ether_addr(dest)) { + mdst = br_mdb_get(br, skb, vid); + if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) && + br_multicast_querier_exists(br, eth_hdr(skb))) { + if ((mdst && mdst->mglist) || + br_multicast_is_router(br)) + skb2 = skb; + br_multicast_forward(mdst, skb, skb2); + skb = NULL; + if (!skb2) + goto out; + } else + skb2 = skb; + + unicast = false; + br->dev->stats.multicast++; + } else if ((dst = __br_fdb_get(br, dest, vid)) && + dst->is_local) { skb2 = skb; /* Do not forward the packet since it's local. */ skb = NULL; } - if (skb2 == skb) - skb2 = skb_clone(skb, GFP_ATOMIC); - - if (skb2) - br_pass_frame_up(br, skb2); - if (skb) { - if (dst) - br_forward(dst->dst, skb); - else - br_flood_forward(br, skb); + if (dst) { + dst->used = jiffies; + br_forward(dst->dst, skb, skb2); + } else + br_flood_forward(br, skb, skb2, unicast); } + if (skb2) + return br_pass_frame_up(skb2); + out: return 0; drop: @@ -90,81 +141,108 @@ drop: goto out; } -/* note: already called with rcu_read_lock (preempt_disabled) */ +/* note: already called with rcu_read_lock */ static int br_handle_local_finish(struct sk_buff *skb) { - struct net_bridge_port *p = rcu_dereference(skb->dev->br_port); + struct net_bridge_port *p = br_port_get_rcu(skb->dev); + u16 vid = 0; - if (p) - br_fdb_update(p->br, p, eth_hdr(skb)->h_source); + /* check if vlan is allowed, to avoid spoofing */ + if (p->flags & BR_LEARNING && br_should_learn(p, skb, &vid)) + br_fdb_update(p->br, p, eth_hdr(skb)->h_source, vid, false); return 0; /* process further */ } -/* Does address match the link local multicast address. - * 01:80:c2:00:00:0X - */ -static inline int is_link_local(const unsigned char *dest) -{ - __be16 *a = (__be16 *)dest; - static const __be16 *b = (const __be16 *)br_group_address; - static const __be16 m = cpu_to_be16(0xfff0); - - return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | ((a[2] ^ b[2]) & m)) == 0; -} - /* - * Called via br_handle_frame_hook. * Return NULL if skb is handled - * note: already called with rcu_read_lock (preempt_disabled) + * note: already called with rcu_read_lock */ -struct sk_buff *br_handle_frame(struct net_bridge_port *p, struct sk_buff *skb) +rx_handler_result_t br_handle_frame(struct sk_buff **pskb) { + struct net_bridge_port *p; + struct sk_buff *skb = *pskb; const unsigned char *dest = eth_hdr(skb)->h_dest; - int (*rhook)(struct sk_buff *skb); + br_should_route_hook_t *rhook; + + if (unlikely(skb->pkt_type == PACKET_LOOPBACK)) + return RX_HANDLER_PASS; if (!is_valid_ether_addr(eth_hdr(skb)->h_source)) goto drop; skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) - return NULL; - - if (unlikely(is_link_local(dest))) { - /* Pause frames shouldn't be passed up by driver anyway */ - if (skb->protocol == htons(ETH_P_PAUSE)) + return RX_HANDLER_CONSUMED; + + p = br_port_get_rcu(skb->dev); + + if (unlikely(is_link_local_ether_addr(dest))) { + u16 fwd_mask = p->br->group_fwd_mask_required; + + /* + * See IEEE 802.1D Table 7-10 Reserved addresses + * + * Assignment Value + * Bridge Group Address 01-80-C2-00-00-00 + * (MAC Control) 802.3 01-80-C2-00-00-01 + * (Link Aggregation) 802.3 01-80-C2-00-00-02 + * 802.1X PAE address 01-80-C2-00-00-03 + * + * 802.1AB LLDP 01-80-C2-00-00-0E + * + * Others reserved for future standardization + */ + switch (dest[5]) { + case 0x00: /* Bridge Group Address */ + /* If STP is turned off, + then must forward to keep loop detection */ + if (p->br->stp_enabled == BR_NO_STP || + fwd_mask & (1u << dest[5])) + goto forward; + break; + + case 0x01: /* IEEE MAC (Pause) */ goto drop; - /* If STP is turned off, then forward */ - if (p->br->stp_enabled == BR_NO_STP && dest[5] == 0) - goto forward; + default: + /* Allow selective forwarding for most other protocols */ + fwd_mask |= p->br->group_fwd_mask; + if (fwd_mask & (1u << dest[5])) + goto forward; + } - if (NF_HOOK(PF_BRIDGE, NF_BR_LOCAL_IN, skb, skb->dev, - NULL, br_handle_local_finish)) - return NULL; /* frame consumed by filter */ - else - return skb; /* continue processing */ + /* Deliver packet to local host only */ + if (NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, skb, skb->dev, + NULL, br_handle_local_finish)) { + return RX_HANDLER_CONSUMED; /* consumed by filter */ + } else { + *pskb = skb; + return RX_HANDLER_PASS; /* continue processing */ + } } forward: switch (p->state) { case BR_STATE_FORWARDING: rhook = rcu_dereference(br_should_route_hook); - if (rhook != NULL) { - if (rhook(skb)) - return skb; + if (rhook) { + if ((*rhook)(skb)) { + *pskb = skb; + return RX_HANDLER_PASS; + } dest = eth_hdr(skb)->h_dest; } /* fall through */ case BR_STATE_LEARNING: - if (!compare_ether_addr(p->br->dev->dev_addr, dest)) + if (ether_addr_equal(p->br->dev->dev_addr, dest)) skb->pkt_type = PACKET_HOST; - NF_HOOK(PF_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL, + NF_HOOK(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL, br_handle_frame_finish); break; default: drop: kfree_skb(skb); } - return NULL; + return RX_HANDLER_CONSUMED; } diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c index 2af6e4a9026..a9a4a1b7863 100644 --- a/net/bridge/br_ioctl.c +++ b/net/bridge/br_ioctl.c @@ -15,6 +15,7 @@ #include <linux/kernel.h> #include <linux/if_bridge.h> #include <linux/netdevice.h> +#include <linux/slab.h> #include <linux/times.h> #include <net/net_namespace.h> #include <asm/uaccess.h> @@ -84,13 +85,14 @@ static int get_fdb_entries(struct net_bridge *br, void __user *userbuf, /* called with RTNL */ static int add_del_if(struct net_bridge *br, int ifindex, int isadd) { + struct net *net = dev_net(br->dev); struct net_device *dev; int ret; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; - dev = __dev_get_by_index(dev_net(br->dev), ifindex); + dev = __dev_get_by_index(net, ifindex); if (dev == NULL) return -EINVAL; @@ -105,7 +107,7 @@ static int add_del_if(struct net_bridge *br, int ifindex, int isadd) /* * Legacy ioctl's through SIOCDEVPRIVATE * This interface is deprecated because it was too difficult to - * to do the translation for 32/64bit ioctl compatability. + * to do the translation for 32/64bit ioctl compatibility. */ static int old_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) { @@ -177,46 +179,25 @@ static int old_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) } case BRCTL_SET_BRIDGE_FORWARD_DELAY: - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; - spin_lock_bh(&br->lock); - br->bridge_forward_delay = clock_t_to_jiffies(args[1]); - if (br_is_root_bridge(br)) - br->forward_delay = br->bridge_forward_delay; - spin_unlock_bh(&br->lock); - return 0; + return br_set_forward_delay(br, args[1]); case BRCTL_SET_BRIDGE_HELLO_TIME: - { - unsigned long t = clock_t_to_jiffies(args[1]); - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; - if (t < HZ) - return -EINVAL; - - spin_lock_bh(&br->lock); - br->bridge_hello_time = t; - if (br_is_root_bridge(br)) - br->hello_time = br->bridge_hello_time; - spin_unlock_bh(&br->lock); - return 0; - } + return br_set_hello_time(br, args[1]); case BRCTL_SET_BRIDGE_MAX_AGE: - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; - spin_lock_bh(&br->lock); - br->bridge_max_age = clock_t_to_jiffies(args[1]); - if (br_is_root_bridge(br)) - br->max_age = br->bridge_max_age; - spin_unlock_bh(&br->lock); - return 0; + return br_set_max_age(br, args[1]); case BRCTL_SET_AGEING_TIME: - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; br->ageing_time = clock_t_to_jiffies(args[1]); @@ -256,14 +237,14 @@ static int old_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) } case BRCTL_SET_BRIDGE_STP_STATE: - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; br_stp_set_enabled(br, args[1]); return 0; case BRCTL_SET_BRIDGE_PRIORITY: - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; spin_lock_bh(&br->lock); @@ -274,19 +255,16 @@ static int old_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) case BRCTL_SET_PORT_PRIORITY: { struct net_bridge_port *p; - int ret = 0; + int ret; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; - if (args[2] >= (1<<(16-BR_PORT_BITS))) - return -ERANGE; - spin_lock_bh(&br->lock); if ((p = br_get_port(br, args[1])) == NULL) ret = -EINVAL; else - br_stp_set_port_priority(p, args[2]); + ret = br_stp_set_port_priority(p, args[2]); spin_unlock_bh(&br->lock); return ret; } @@ -294,15 +272,17 @@ static int old_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) case BRCTL_SET_PATH_COST: { struct net_bridge_port *p; - int ret = 0; + int ret; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; + spin_lock_bh(&br->lock); if ((p = br_get_port(br, args[1])) == NULL) ret = -EINVAL; else - br_stp_set_path_cost(p, args[2]); + ret = br_stp_set_path_cost(p, args[2]); + spin_unlock_bh(&br->lock); return ret; } @@ -351,7 +331,7 @@ static int old_deviceless(struct net *net, void __user *uarg) { char buf[IFNAMSIZ]; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (copy_from_user(buf, (void __user *)args[1], IFNAMSIZ)) @@ -381,7 +361,7 @@ int br_ioctl_deviceless_stub(struct net *net, unsigned int cmd, void __user *uar { char buf[IFNAMSIZ]; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (copy_from_user(buf, uarg, IFNAMSIZ)) @@ -401,7 +381,7 @@ int br_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) { struct net_bridge *br = netdev_priv(dev); - switch(cmd) { + switch (cmd) { case SIOCDEVPRIVATE: return old_dev_ioctl(dev, rq, cmd); @@ -411,6 +391,6 @@ int br_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) } - pr_debug("Bridge does not support ioctl 0x%x\n", cmd); + br_debug(br, "Bridge does not support ioctl 0x%x\n", cmd); return -EOPNOTSUPP; } diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c new file mode 100644 index 00000000000..5df05269d17 --- /dev/null +++ b/net/bridge/br_mdb.c @@ -0,0 +1,498 @@ +#include <linux/err.h> +#include <linux/igmp.h> +#include <linux/kernel.h> +#include <linux/netdevice.h> +#include <linux/rculist.h> +#include <linux/skbuff.h> +#include <linux/if_ether.h> +#include <net/ip.h> +#include <net/netlink.h> +#if IS_ENABLED(CONFIG_IPV6) +#include <net/ipv6.h> +#include <net/addrconf.h> +#endif + +#include "br_private.h" + +static int br_rports_fill_info(struct sk_buff *skb, struct netlink_callback *cb, + struct net_device *dev) +{ + struct net_bridge *br = netdev_priv(dev); + struct net_bridge_port *p; + struct nlattr *nest; + + if (!br->multicast_router || hlist_empty(&br->router_list)) + return 0; + + nest = nla_nest_start(skb, MDBA_ROUTER); + if (nest == NULL) + return -EMSGSIZE; + + hlist_for_each_entry_rcu(p, &br->router_list, rlist) { + if (p && nla_put_u32(skb, MDBA_ROUTER_PORT, p->dev->ifindex)) + goto fail; + } + + nla_nest_end(skb, nest); + return 0; +fail: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + +static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb, + struct net_device *dev) +{ + struct net_bridge *br = netdev_priv(dev); + struct net_bridge_mdb_htable *mdb; + struct nlattr *nest, *nest2; + int i, err = 0; + int idx = 0, s_idx = cb->args[1]; + + if (br->multicast_disabled) + return 0; + + mdb = rcu_dereference(br->mdb); + if (!mdb) + return 0; + + nest = nla_nest_start(skb, MDBA_MDB); + if (nest == NULL) + return -EMSGSIZE; + + for (i = 0; i < mdb->max; i++) { + struct net_bridge_mdb_entry *mp; + struct net_bridge_port_group *p; + struct net_bridge_port_group __rcu **pp; + struct net_bridge_port *port; + + hlist_for_each_entry_rcu(mp, &mdb->mhash[i], hlist[mdb->ver]) { + if (idx < s_idx) + goto skip; + + nest2 = nla_nest_start(skb, MDBA_MDB_ENTRY); + if (nest2 == NULL) { + err = -EMSGSIZE; + goto out; + } + + for (pp = &mp->ports; + (p = rcu_dereference(*pp)) != NULL; + pp = &p->next) { + port = p->port; + if (port) { + struct br_mdb_entry e; + memset(&e, 0, sizeof(e)); + e.ifindex = port->dev->ifindex; + e.state = p->state; + if (p->addr.proto == htons(ETH_P_IP)) + e.addr.u.ip4 = p->addr.u.ip4; +#if IS_ENABLED(CONFIG_IPV6) + if (p->addr.proto == htons(ETH_P_IPV6)) + e.addr.u.ip6 = p->addr.u.ip6; +#endif + e.addr.proto = p->addr.proto; + if (nla_put(skb, MDBA_MDB_ENTRY_INFO, sizeof(e), &e)) { + nla_nest_cancel(skb, nest2); + err = -EMSGSIZE; + goto out; + } + } + } + nla_nest_end(skb, nest2); + skip: + idx++; + } + } + +out: + cb->args[1] = idx; + nla_nest_end(skb, nest); + return err; +} + +static int br_mdb_dump(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct net_device *dev; + struct net *net = sock_net(skb->sk); + struct nlmsghdr *nlh = NULL; + int idx = 0, s_idx; + + s_idx = cb->args[0]; + + rcu_read_lock(); + + /* In theory this could be wrapped to 0... */ + cb->seq = net->dev_base_seq + br_mdb_rehash_seq; + + for_each_netdev_rcu(net, dev) { + if (dev->priv_flags & IFF_EBRIDGE) { + struct br_port_msg *bpm; + + if (idx < s_idx) + goto skip; + + nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, RTM_GETMDB, + sizeof(*bpm), NLM_F_MULTI); + if (nlh == NULL) + break; + + bpm = nlmsg_data(nlh); + memset(bpm, 0, sizeof(*bpm)); + bpm->ifindex = dev->ifindex; + if (br_mdb_fill_info(skb, cb, dev) < 0) + goto out; + if (br_rports_fill_info(skb, cb, dev) < 0) + goto out; + + cb->args[1] = 0; + nlmsg_end(skb, nlh); + skip: + idx++; + } + } + +out: + if (nlh) + nlmsg_end(skb, nlh); + rcu_read_unlock(); + cb->args[0] = idx; + return skb->len; +} + +static int nlmsg_populate_mdb_fill(struct sk_buff *skb, + struct net_device *dev, + struct br_mdb_entry *entry, u32 pid, + u32 seq, int type, unsigned int flags) +{ + struct nlmsghdr *nlh; + struct br_port_msg *bpm; + struct nlattr *nest, *nest2; + + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*bpm), NLM_F_MULTI); + if (!nlh) + return -EMSGSIZE; + + bpm = nlmsg_data(nlh); + memset(bpm, 0, sizeof(*bpm)); + bpm->family = AF_BRIDGE; + bpm->ifindex = dev->ifindex; + nest = nla_nest_start(skb, MDBA_MDB); + if (nest == NULL) + goto cancel; + nest2 = nla_nest_start(skb, MDBA_MDB_ENTRY); + if (nest2 == NULL) + goto end; + + if (nla_put(skb, MDBA_MDB_ENTRY_INFO, sizeof(*entry), entry)) + goto end; + + nla_nest_end(skb, nest2); + nla_nest_end(skb, nest); + return nlmsg_end(skb, nlh); + +end: + nla_nest_end(skb, nest); +cancel: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +static inline size_t rtnl_mdb_nlmsg_size(void) +{ + return NLMSG_ALIGN(sizeof(struct br_port_msg)) + + nla_total_size(sizeof(struct br_mdb_entry)); +} + +static void __br_mdb_notify(struct net_device *dev, struct br_mdb_entry *entry, + int type) +{ + struct net *net = dev_net(dev); + struct sk_buff *skb; + int err = -ENOBUFS; + + skb = nlmsg_new(rtnl_mdb_nlmsg_size(), GFP_ATOMIC); + if (!skb) + goto errout; + + err = nlmsg_populate_mdb_fill(skb, dev, entry, 0, 0, type, NTF_SELF); + if (err < 0) { + kfree_skb(skb); + goto errout; + } + + rtnl_notify(skb, net, 0, RTNLGRP_MDB, NULL, GFP_ATOMIC); + return; +errout: + rtnl_set_sk_err(net, RTNLGRP_MDB, err); +} + +void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port, + struct br_ip *group, int type) +{ + struct br_mdb_entry entry; + + memset(&entry, 0, sizeof(entry)); + entry.ifindex = port->dev->ifindex; + entry.addr.proto = group->proto; + entry.addr.u.ip4 = group->u.ip4; +#if IS_ENABLED(CONFIG_IPV6) + entry.addr.u.ip6 = group->u.ip6; +#endif + __br_mdb_notify(dev, &entry, type); +} + +static bool is_valid_mdb_entry(struct br_mdb_entry *entry) +{ + if (entry->ifindex == 0) + return false; + + if (entry->addr.proto == htons(ETH_P_IP)) { + if (!ipv4_is_multicast(entry->addr.u.ip4)) + return false; + if (ipv4_is_local_multicast(entry->addr.u.ip4)) + return false; +#if IS_ENABLED(CONFIG_IPV6) + } else if (entry->addr.proto == htons(ETH_P_IPV6)) { + if (ipv6_addr_is_ll_all_nodes(&entry->addr.u.ip6)) + return false; +#endif + } else + return false; + if (entry->state != MDB_PERMANENT && entry->state != MDB_TEMPORARY) + return false; + + return true; +} + +static int br_mdb_parse(struct sk_buff *skb, struct nlmsghdr *nlh, + struct net_device **pdev, struct br_mdb_entry **pentry) +{ + struct net *net = sock_net(skb->sk); + struct br_mdb_entry *entry; + struct br_port_msg *bpm; + struct nlattr *tb[MDBA_SET_ENTRY_MAX+1]; + struct net_device *dev; + int err; + + err = nlmsg_parse(nlh, sizeof(*bpm), tb, MDBA_SET_ENTRY, NULL); + if (err < 0) + return err; + + bpm = nlmsg_data(nlh); + if (bpm->ifindex == 0) { + pr_info("PF_BRIDGE: br_mdb_parse() with invalid ifindex\n"); + return -EINVAL; + } + + dev = __dev_get_by_index(net, bpm->ifindex); + if (dev == NULL) { + pr_info("PF_BRIDGE: br_mdb_parse() with unknown ifindex\n"); + return -ENODEV; + } + + if (!(dev->priv_flags & IFF_EBRIDGE)) { + pr_info("PF_BRIDGE: br_mdb_parse() with non-bridge\n"); + return -EOPNOTSUPP; + } + + *pdev = dev; + + if (!tb[MDBA_SET_ENTRY] || + nla_len(tb[MDBA_SET_ENTRY]) != sizeof(struct br_mdb_entry)) { + pr_info("PF_BRIDGE: br_mdb_parse() with invalid attr\n"); + return -EINVAL; + } + + entry = nla_data(tb[MDBA_SET_ENTRY]); + if (!is_valid_mdb_entry(entry)) { + pr_info("PF_BRIDGE: br_mdb_parse() with invalid entry\n"); + return -EINVAL; + } + + *pentry = entry; + return 0; +} + +static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, + struct br_ip *group, unsigned char state) +{ + struct net_bridge_mdb_entry *mp; + struct net_bridge_port_group *p; + struct net_bridge_port_group __rcu **pp; + struct net_bridge_mdb_htable *mdb; + int err; + + mdb = mlock_dereference(br->mdb, br); + mp = br_mdb_ip_get(mdb, group); + if (!mp) { + mp = br_multicast_new_group(br, port, group); + err = PTR_ERR(mp); + if (IS_ERR(mp)) + return err; + } + + for (pp = &mp->ports; + (p = mlock_dereference(*pp, br)) != NULL; + pp = &p->next) { + if (p->port == port) + return -EEXIST; + if ((unsigned long)p->port < (unsigned long)port) + break; + } + + p = br_multicast_new_port_group(port, group, *pp, state); + if (unlikely(!p)) + return -ENOMEM; + rcu_assign_pointer(*pp, p); + + br_mdb_notify(br->dev, port, group, RTM_NEWMDB); + return 0; +} + +static int __br_mdb_add(struct net *net, struct net_bridge *br, + struct br_mdb_entry *entry) +{ + struct br_ip ip; + struct net_device *dev; + struct net_bridge_port *p; + int ret; + + if (!netif_running(br->dev) || br->multicast_disabled) + return -EINVAL; + + dev = __dev_get_by_index(net, entry->ifindex); + if (!dev) + return -ENODEV; + + p = br_port_get_rtnl(dev); + if (!p || p->br != br || p->state == BR_STATE_DISABLED) + return -EINVAL; + + ip.proto = entry->addr.proto; + if (ip.proto == htons(ETH_P_IP)) + ip.u.ip4 = entry->addr.u.ip4; +#if IS_ENABLED(CONFIG_IPV6) + else + ip.u.ip6 = entry->addr.u.ip6; +#endif + + spin_lock_bh(&br->multicast_lock); + ret = br_mdb_add_group(br, p, &ip, entry->state); + spin_unlock_bh(&br->multicast_lock); + return ret; +} + +static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh) +{ + struct net *net = sock_net(skb->sk); + struct br_mdb_entry *entry; + struct net_device *dev; + struct net_bridge *br; + int err; + + err = br_mdb_parse(skb, nlh, &dev, &entry); + if (err < 0) + return err; + + br = netdev_priv(dev); + + err = __br_mdb_add(net, br, entry); + if (!err) + __br_mdb_notify(dev, entry, RTM_NEWMDB); + return err; +} + +static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry) +{ + struct net_bridge_mdb_htable *mdb; + struct net_bridge_mdb_entry *mp; + struct net_bridge_port_group *p; + struct net_bridge_port_group __rcu **pp; + struct br_ip ip; + int err = -EINVAL; + + if (!netif_running(br->dev) || br->multicast_disabled) + return -EINVAL; + + ip.proto = entry->addr.proto; + if (ip.proto == htons(ETH_P_IP)) { + if (timer_pending(&br->ip4_other_query.timer)) + return -EBUSY; + + ip.u.ip4 = entry->addr.u.ip4; +#if IS_ENABLED(CONFIG_IPV6) + } else { + if (timer_pending(&br->ip6_other_query.timer)) + return -EBUSY; + + ip.u.ip6 = entry->addr.u.ip6; +#endif + } + + spin_lock_bh(&br->multicast_lock); + mdb = mlock_dereference(br->mdb, br); + + mp = br_mdb_ip_get(mdb, &ip); + if (!mp) + goto unlock; + + for (pp = &mp->ports; + (p = mlock_dereference(*pp, br)) != NULL; + pp = &p->next) { + if (!p->port || p->port->dev->ifindex != entry->ifindex) + continue; + + if (p->port->state == BR_STATE_DISABLED) + goto unlock; + + rcu_assign_pointer(*pp, p->next); + hlist_del_init(&p->mglist); + del_timer(&p->timer); + call_rcu_bh(&p->rcu, br_multicast_free_pg); + err = 0; + + if (!mp->ports && !mp->mglist && + netif_running(br->dev)) + mod_timer(&mp->timer, jiffies); + break; + } + +unlock: + spin_unlock_bh(&br->multicast_lock); + return err; +} + +static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh) +{ + struct net_device *dev; + struct br_mdb_entry *entry; + struct net_bridge *br; + int err; + + err = br_mdb_parse(skb, nlh, &dev, &entry); + if (err < 0) + return err; + + br = netdev_priv(dev); + + err = __br_mdb_del(br, entry); + if (!err) + __br_mdb_notify(dev, entry, RTM_DELMDB); + return err; +} + +void br_mdb_init(void) +{ + rtnl_register(PF_BRIDGE, RTM_GETMDB, NULL, br_mdb_dump, NULL); + rtnl_register(PF_BRIDGE, RTM_NEWMDB, br_mdb_add, NULL, NULL); + rtnl_register(PF_BRIDGE, RTM_DELMDB, br_mdb_del, NULL, NULL); +} + +void br_mdb_uninit(void) +{ + rtnl_unregister(PF_BRIDGE, RTM_GETMDB); + rtnl_unregister(PF_BRIDGE, RTM_NEWMDB); + rtnl_unregister(PF_BRIDGE, RTM_DELMDB); +} diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c new file mode 100644 index 00000000000..abfa0b65a11 --- /dev/null +++ b/net/bridge/br_multicast.c @@ -0,0 +1,2265 @@ +/* + * Bridge multicast support. + * + * Copyright (c) 2010 Herbert Xu <herbert@gondor.apana.org.au> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + * + */ + +#include <linux/err.h> +#include <linux/export.h> +#include <linux/if_ether.h> +#include <linux/igmp.h> +#include <linux/jhash.h> +#include <linux/kernel.h> +#include <linux/log2.h> +#include <linux/netdevice.h> +#include <linux/netfilter_bridge.h> +#include <linux/random.h> +#include <linux/rculist.h> +#include <linux/skbuff.h> +#include <linux/slab.h> +#include <linux/timer.h> +#include <linux/inetdevice.h> +#include <net/ip.h> +#if IS_ENABLED(CONFIG_IPV6) +#include <net/ipv6.h> +#include <net/mld.h> +#include <net/ip6_checksum.h> +#include <net/addrconf.h> +#endif + +#include "br_private.h" + +static void br_multicast_start_querier(struct net_bridge *br, + struct bridge_mcast_own_query *query); +unsigned int br_mdb_rehash_seq; + +static inline int br_ip_equal(const struct br_ip *a, const struct br_ip *b) +{ + if (a->proto != b->proto) + return 0; + if (a->vid != b->vid) + return 0; + switch (a->proto) { + case htons(ETH_P_IP): + return a->u.ip4 == b->u.ip4; +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): + return ipv6_addr_equal(&a->u.ip6, &b->u.ip6); +#endif + } + return 0; +} + +static inline int __br_ip4_hash(struct net_bridge_mdb_htable *mdb, __be32 ip, + __u16 vid) +{ + return jhash_2words((__force u32)ip, vid, mdb->secret) & (mdb->max - 1); +} + +#if IS_ENABLED(CONFIG_IPV6) +static inline int __br_ip6_hash(struct net_bridge_mdb_htable *mdb, + const struct in6_addr *ip, + __u16 vid) +{ + return jhash_2words(ipv6_addr_hash(ip), vid, + mdb->secret) & (mdb->max - 1); +} +#endif + +static inline int br_ip_hash(struct net_bridge_mdb_htable *mdb, + struct br_ip *ip) +{ + switch (ip->proto) { + case htons(ETH_P_IP): + return __br_ip4_hash(mdb, ip->u.ip4, ip->vid); +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): + return __br_ip6_hash(mdb, &ip->u.ip6, ip->vid); +#endif + } + return 0; +} + +static struct net_bridge_mdb_entry *__br_mdb_ip_get( + struct net_bridge_mdb_htable *mdb, struct br_ip *dst, int hash) +{ + struct net_bridge_mdb_entry *mp; + + hlist_for_each_entry_rcu(mp, &mdb->mhash[hash], hlist[mdb->ver]) { + if (br_ip_equal(&mp->addr, dst)) + return mp; + } + + return NULL; +} + +struct net_bridge_mdb_entry *br_mdb_ip_get(struct net_bridge_mdb_htable *mdb, + struct br_ip *dst) +{ + if (!mdb) + return NULL; + + return __br_mdb_ip_get(mdb, dst, br_ip_hash(mdb, dst)); +} + +static struct net_bridge_mdb_entry *br_mdb_ip4_get( + struct net_bridge_mdb_htable *mdb, __be32 dst, __u16 vid) +{ + struct br_ip br_dst; + + br_dst.u.ip4 = dst; + br_dst.proto = htons(ETH_P_IP); + br_dst.vid = vid; + + return br_mdb_ip_get(mdb, &br_dst); +} + +#if IS_ENABLED(CONFIG_IPV6) +static struct net_bridge_mdb_entry *br_mdb_ip6_get( + struct net_bridge_mdb_htable *mdb, const struct in6_addr *dst, + __u16 vid) +{ + struct br_ip br_dst; + + br_dst.u.ip6 = *dst; + br_dst.proto = htons(ETH_P_IPV6); + br_dst.vid = vid; + + return br_mdb_ip_get(mdb, &br_dst); +} +#endif + +struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br, + struct sk_buff *skb, u16 vid) +{ + struct net_bridge_mdb_htable *mdb = rcu_dereference(br->mdb); + struct br_ip ip; + + if (br->multicast_disabled) + return NULL; + + if (BR_INPUT_SKB_CB(skb)->igmp) + return NULL; + + ip.proto = skb->protocol; + ip.vid = vid; + + switch (skb->protocol) { + case htons(ETH_P_IP): + ip.u.ip4 = ip_hdr(skb)->daddr; + break; +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): + ip.u.ip6 = ipv6_hdr(skb)->daddr; + break; +#endif + default: + return NULL; + } + + return br_mdb_ip_get(mdb, &ip); +} + +static void br_mdb_free(struct rcu_head *head) +{ + struct net_bridge_mdb_htable *mdb = + container_of(head, struct net_bridge_mdb_htable, rcu); + struct net_bridge_mdb_htable *old = mdb->old; + + mdb->old = NULL; + kfree(old->mhash); + kfree(old); +} + +static int br_mdb_copy(struct net_bridge_mdb_htable *new, + struct net_bridge_mdb_htable *old, + int elasticity) +{ + struct net_bridge_mdb_entry *mp; + int maxlen; + int len; + int i; + + for (i = 0; i < old->max; i++) + hlist_for_each_entry(mp, &old->mhash[i], hlist[old->ver]) + hlist_add_head(&mp->hlist[new->ver], + &new->mhash[br_ip_hash(new, &mp->addr)]); + + if (!elasticity) + return 0; + + maxlen = 0; + for (i = 0; i < new->max; i++) { + len = 0; + hlist_for_each_entry(mp, &new->mhash[i], hlist[new->ver]) + len++; + if (len > maxlen) + maxlen = len; + } + + return maxlen > elasticity ? -EINVAL : 0; +} + +void br_multicast_free_pg(struct rcu_head *head) +{ + struct net_bridge_port_group *p = + container_of(head, struct net_bridge_port_group, rcu); + + kfree(p); +} + +static void br_multicast_free_group(struct rcu_head *head) +{ + struct net_bridge_mdb_entry *mp = + container_of(head, struct net_bridge_mdb_entry, rcu); + + kfree(mp); +} + +static void br_multicast_group_expired(unsigned long data) +{ + struct net_bridge_mdb_entry *mp = (void *)data; + struct net_bridge *br = mp->br; + struct net_bridge_mdb_htable *mdb; + + spin_lock(&br->multicast_lock); + if (!netif_running(br->dev) || timer_pending(&mp->timer)) + goto out; + + mp->mglist = false; + + if (mp->ports) + goto out; + + mdb = mlock_dereference(br->mdb, br); + + hlist_del_rcu(&mp->hlist[mdb->ver]); + mdb->size--; + + call_rcu_bh(&mp->rcu, br_multicast_free_group); + +out: + spin_unlock(&br->multicast_lock); +} + +static void br_multicast_del_pg(struct net_bridge *br, + struct net_bridge_port_group *pg) +{ + struct net_bridge_mdb_htable *mdb; + struct net_bridge_mdb_entry *mp; + struct net_bridge_port_group *p; + struct net_bridge_port_group __rcu **pp; + + mdb = mlock_dereference(br->mdb, br); + + mp = br_mdb_ip_get(mdb, &pg->addr); + if (WARN_ON(!mp)) + return; + + for (pp = &mp->ports; + (p = mlock_dereference(*pp, br)) != NULL; + pp = &p->next) { + if (p != pg) + continue; + + rcu_assign_pointer(*pp, p->next); + hlist_del_init(&p->mglist); + del_timer(&p->timer); + call_rcu_bh(&p->rcu, br_multicast_free_pg); + + if (!mp->ports && !mp->mglist && + netif_running(br->dev)) + mod_timer(&mp->timer, jiffies); + + return; + } + + WARN_ON(1); +} + +static void br_multicast_port_group_expired(unsigned long data) +{ + struct net_bridge_port_group *pg = (void *)data; + struct net_bridge *br = pg->port->br; + + spin_lock(&br->multicast_lock); + if (!netif_running(br->dev) || timer_pending(&pg->timer) || + hlist_unhashed(&pg->mglist) || pg->state & MDB_PERMANENT) + goto out; + + br_multicast_del_pg(br, pg); + +out: + spin_unlock(&br->multicast_lock); +} + +static int br_mdb_rehash(struct net_bridge_mdb_htable __rcu **mdbp, int max, + int elasticity) +{ + struct net_bridge_mdb_htable *old = rcu_dereference_protected(*mdbp, 1); + struct net_bridge_mdb_htable *mdb; + int err; + + mdb = kmalloc(sizeof(*mdb), GFP_ATOMIC); + if (!mdb) + return -ENOMEM; + + mdb->max = max; + mdb->old = old; + + mdb->mhash = kzalloc(max * sizeof(*mdb->mhash), GFP_ATOMIC); + if (!mdb->mhash) { + kfree(mdb); + return -ENOMEM; + } + + mdb->size = old ? old->size : 0; + mdb->ver = old ? old->ver ^ 1 : 0; + + if (!old || elasticity) + get_random_bytes(&mdb->secret, sizeof(mdb->secret)); + else + mdb->secret = old->secret; + + if (!old) + goto out; + + err = br_mdb_copy(mdb, old, elasticity); + if (err) { + kfree(mdb->mhash); + kfree(mdb); + return err; + } + + br_mdb_rehash_seq++; + call_rcu_bh(&mdb->rcu, br_mdb_free); + +out: + rcu_assign_pointer(*mdbp, mdb); + + return 0; +} + +static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br, + __be32 group) +{ + struct sk_buff *skb; + struct igmphdr *ih; + struct ethhdr *eth; + struct iphdr *iph; + + skb = netdev_alloc_skb_ip_align(br->dev, sizeof(*eth) + sizeof(*iph) + + sizeof(*ih) + 4); + if (!skb) + goto out; + + skb->protocol = htons(ETH_P_IP); + + skb_reset_mac_header(skb); + eth = eth_hdr(skb); + + ether_addr_copy(eth->h_source, br->dev->dev_addr); + eth->h_dest[0] = 1; + eth->h_dest[1] = 0; + eth->h_dest[2] = 0x5e; + eth->h_dest[3] = 0; + eth->h_dest[4] = 0; + eth->h_dest[5] = 1; + eth->h_proto = htons(ETH_P_IP); + skb_put(skb, sizeof(*eth)); + + skb_set_network_header(skb, skb->len); + iph = ip_hdr(skb); + + iph->version = 4; + iph->ihl = 6; + iph->tos = 0xc0; + iph->tot_len = htons(sizeof(*iph) + sizeof(*ih) + 4); + iph->id = 0; + iph->frag_off = htons(IP_DF); + iph->ttl = 1; + iph->protocol = IPPROTO_IGMP; + iph->saddr = br->multicast_query_use_ifaddr ? + inet_select_addr(br->dev, 0, RT_SCOPE_LINK) : 0; + iph->daddr = htonl(INADDR_ALLHOSTS_GROUP); + ((u8 *)&iph[1])[0] = IPOPT_RA; + ((u8 *)&iph[1])[1] = 4; + ((u8 *)&iph[1])[2] = 0; + ((u8 *)&iph[1])[3] = 0; + ip_send_check(iph); + skb_put(skb, 24); + + skb_set_transport_header(skb, skb->len); + ih = igmp_hdr(skb); + ih->type = IGMP_HOST_MEMBERSHIP_QUERY; + ih->code = (group ? br->multicast_last_member_interval : + br->multicast_query_response_interval) / + (HZ / IGMP_TIMER_SCALE); + ih->group = group; + ih->csum = 0; + ih->csum = ip_compute_csum((void *)ih, sizeof(struct igmphdr)); + skb_put(skb, sizeof(*ih)); + + __skb_pull(skb, sizeof(*eth)); + +out: + return skb; +} + +#if IS_ENABLED(CONFIG_IPV6) +static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, + const struct in6_addr *group) +{ + struct sk_buff *skb; + struct ipv6hdr *ip6h; + struct mld_msg *mldq; + struct ethhdr *eth; + u8 *hopopt; + unsigned long interval; + + skb = netdev_alloc_skb_ip_align(br->dev, sizeof(*eth) + sizeof(*ip6h) + + 8 + sizeof(*mldq)); + if (!skb) + goto out; + + skb->protocol = htons(ETH_P_IPV6); + + /* Ethernet header */ + skb_reset_mac_header(skb); + eth = eth_hdr(skb); + + ether_addr_copy(eth->h_source, br->dev->dev_addr); + eth->h_proto = htons(ETH_P_IPV6); + skb_put(skb, sizeof(*eth)); + + /* IPv6 header + HbH option */ + skb_set_network_header(skb, skb->len); + ip6h = ipv6_hdr(skb); + + *(__force __be32 *)ip6h = htonl(0x60000000); + ip6h->payload_len = htons(8 + sizeof(*mldq)); + ip6h->nexthdr = IPPROTO_HOPOPTS; + ip6h->hop_limit = 1; + ipv6_addr_set(&ip6h->daddr, htonl(0xff020000), 0, 0, htonl(1)); + if (ipv6_dev_get_saddr(dev_net(br->dev), br->dev, &ip6h->daddr, 0, + &ip6h->saddr)) { + kfree_skb(skb); + return NULL; + } + ipv6_eth_mc_map(&ip6h->daddr, eth->h_dest); + + hopopt = (u8 *)(ip6h + 1); + hopopt[0] = IPPROTO_ICMPV6; /* next hdr */ + hopopt[1] = 0; /* length of HbH */ + hopopt[2] = IPV6_TLV_ROUTERALERT; /* Router Alert */ + hopopt[3] = 2; /* Length of RA Option */ + hopopt[4] = 0; /* Type = 0x0000 (MLD) */ + hopopt[5] = 0; + hopopt[6] = IPV6_TLV_PAD1; /* Pad1 */ + hopopt[7] = IPV6_TLV_PAD1; /* Pad1 */ + + skb_put(skb, sizeof(*ip6h) + 8); + + /* ICMPv6 */ + skb_set_transport_header(skb, skb->len); + mldq = (struct mld_msg *) icmp6_hdr(skb); + + interval = ipv6_addr_any(group) ? + br->multicast_query_response_interval : + br->multicast_last_member_interval; + + mldq->mld_type = ICMPV6_MGM_QUERY; + mldq->mld_code = 0; + mldq->mld_cksum = 0; + mldq->mld_maxdelay = htons((u16)jiffies_to_msecs(interval)); + mldq->mld_reserved = 0; + mldq->mld_mca = *group; + + /* checksum */ + mldq->mld_cksum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, + sizeof(*mldq), IPPROTO_ICMPV6, + csum_partial(mldq, + sizeof(*mldq), 0)); + skb_put(skb, sizeof(*mldq)); + + __skb_pull(skb, sizeof(*eth)); + +out: + return skb; +} +#endif + +static struct sk_buff *br_multicast_alloc_query(struct net_bridge *br, + struct br_ip *addr) +{ + switch (addr->proto) { + case htons(ETH_P_IP): + return br_ip4_multicast_alloc_query(br, addr->u.ip4); +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): + return br_ip6_multicast_alloc_query(br, &addr->u.ip6); +#endif + } + return NULL; +} + +static struct net_bridge_mdb_entry *br_multicast_get_group( + struct net_bridge *br, struct net_bridge_port *port, + struct br_ip *group, int hash) +{ + struct net_bridge_mdb_htable *mdb; + struct net_bridge_mdb_entry *mp; + unsigned int count = 0; + unsigned int max; + int elasticity; + int err; + + mdb = rcu_dereference_protected(br->mdb, 1); + hlist_for_each_entry(mp, &mdb->mhash[hash], hlist[mdb->ver]) { + count++; + if (unlikely(br_ip_equal(group, &mp->addr))) + return mp; + } + + elasticity = 0; + max = mdb->max; + + if (unlikely(count > br->hash_elasticity && count)) { + if (net_ratelimit()) + br_info(br, "Multicast hash table " + "chain limit reached: %s\n", + port ? port->dev->name : br->dev->name); + + elasticity = br->hash_elasticity; + } + + if (mdb->size >= max) { + max *= 2; + if (unlikely(max > br->hash_max)) { + br_warn(br, "Multicast hash table maximum of %d " + "reached, disabling snooping: %s\n", + br->hash_max, + port ? port->dev->name : br->dev->name); + err = -E2BIG; +disable: + br->multicast_disabled = 1; + goto err; + } + } + + if (max > mdb->max || elasticity) { + if (mdb->old) { + if (net_ratelimit()) + br_info(br, "Multicast hash table " + "on fire: %s\n", + port ? port->dev->name : br->dev->name); + err = -EEXIST; + goto err; + } + + err = br_mdb_rehash(&br->mdb, max, elasticity); + if (err) { + br_warn(br, "Cannot rehash multicast " + "hash table, disabling snooping: %s, %d, %d\n", + port ? port->dev->name : br->dev->name, + mdb->size, err); + goto disable; + } + + err = -EAGAIN; + goto err; + } + + return NULL; + +err: + mp = ERR_PTR(err); + return mp; +} + +struct net_bridge_mdb_entry *br_multicast_new_group(struct net_bridge *br, + struct net_bridge_port *port, struct br_ip *group) +{ + struct net_bridge_mdb_htable *mdb; + struct net_bridge_mdb_entry *mp; + int hash; + int err; + + mdb = rcu_dereference_protected(br->mdb, 1); + if (!mdb) { + err = br_mdb_rehash(&br->mdb, BR_HASH_SIZE, 0); + if (err) + return ERR_PTR(err); + goto rehash; + } + + hash = br_ip_hash(mdb, group); + mp = br_multicast_get_group(br, port, group, hash); + switch (PTR_ERR(mp)) { + case 0: + break; + + case -EAGAIN: +rehash: + mdb = rcu_dereference_protected(br->mdb, 1); + hash = br_ip_hash(mdb, group); + break; + + default: + goto out; + } + + mp = kzalloc(sizeof(*mp), GFP_ATOMIC); + if (unlikely(!mp)) + return ERR_PTR(-ENOMEM); + + mp->br = br; + mp->addr = *group; + setup_timer(&mp->timer, br_multicast_group_expired, + (unsigned long)mp); + + hlist_add_head_rcu(&mp->hlist[mdb->ver], &mdb->mhash[hash]); + mdb->size++; + +out: + return mp; +} + +struct net_bridge_port_group *br_multicast_new_port_group( + struct net_bridge_port *port, + struct br_ip *group, + struct net_bridge_port_group __rcu *next, + unsigned char state) +{ + struct net_bridge_port_group *p; + + p = kzalloc(sizeof(*p), GFP_ATOMIC); + if (unlikely(!p)) + return NULL; + + p->addr = *group; + p->port = port; + p->state = state; + rcu_assign_pointer(p->next, next); + hlist_add_head(&p->mglist, &port->mglist); + setup_timer(&p->timer, br_multicast_port_group_expired, + (unsigned long)p); + return p; +} + +static int br_multicast_add_group(struct net_bridge *br, + struct net_bridge_port *port, + struct br_ip *group) +{ + struct net_bridge_mdb_entry *mp; + struct net_bridge_port_group *p; + struct net_bridge_port_group __rcu **pp; + unsigned long now = jiffies; + int err; + + spin_lock(&br->multicast_lock); + if (!netif_running(br->dev) || + (port && port->state == BR_STATE_DISABLED)) + goto out; + + mp = br_multicast_new_group(br, port, group); + err = PTR_ERR(mp); + if (IS_ERR(mp)) + goto err; + + if (!port) { + mp->mglist = true; + mod_timer(&mp->timer, now + br->multicast_membership_interval); + goto out; + } + + for (pp = &mp->ports; + (p = mlock_dereference(*pp, br)) != NULL; + pp = &p->next) { + if (p->port == port) + goto found; + if ((unsigned long)p->port < (unsigned long)port) + break; + } + + p = br_multicast_new_port_group(port, group, *pp, MDB_TEMPORARY); + if (unlikely(!p)) + goto err; + rcu_assign_pointer(*pp, p); + br_mdb_notify(br->dev, port, group, RTM_NEWMDB); + +found: + mod_timer(&p->timer, now + br->multicast_membership_interval); +out: + err = 0; + +err: + spin_unlock(&br->multicast_lock); + return err; +} + +static int br_ip4_multicast_add_group(struct net_bridge *br, + struct net_bridge_port *port, + __be32 group, + __u16 vid) +{ + struct br_ip br_group; + + if (ipv4_is_local_multicast(group)) + return 0; + + br_group.u.ip4 = group; + br_group.proto = htons(ETH_P_IP); + br_group.vid = vid; + + return br_multicast_add_group(br, port, &br_group); +} + +#if IS_ENABLED(CONFIG_IPV6) +static int br_ip6_multicast_add_group(struct net_bridge *br, + struct net_bridge_port *port, + const struct in6_addr *group, + __u16 vid) +{ + struct br_ip br_group; + + if (ipv6_addr_is_ll_all_nodes(group)) + return 0; + + br_group.u.ip6 = *group; + br_group.proto = htons(ETH_P_IPV6); + br_group.vid = vid; + + return br_multicast_add_group(br, port, &br_group); +} +#endif + +static void br_multicast_router_expired(unsigned long data) +{ + struct net_bridge_port *port = (void *)data; + struct net_bridge *br = port->br; + + spin_lock(&br->multicast_lock); + if (port->multicast_router != 1 || + timer_pending(&port->multicast_router_timer) || + hlist_unhashed(&port->rlist)) + goto out; + + hlist_del_init_rcu(&port->rlist); + +out: + spin_unlock(&br->multicast_lock); +} + +static void br_multicast_local_router_expired(unsigned long data) +{ +} + +static void br_multicast_querier_expired(struct net_bridge *br, + struct bridge_mcast_own_query *query) +{ + spin_lock(&br->multicast_lock); + if (!netif_running(br->dev) || br->multicast_disabled) + goto out; + + br_multicast_start_querier(br, query); + +out: + spin_unlock(&br->multicast_lock); +} + +static void br_ip4_multicast_querier_expired(unsigned long data) +{ + struct net_bridge *br = (void *)data; + + br_multicast_querier_expired(br, &br->ip4_own_query); +} + +#if IS_ENABLED(CONFIG_IPV6) +static void br_ip6_multicast_querier_expired(unsigned long data) +{ + struct net_bridge *br = (void *)data; + + br_multicast_querier_expired(br, &br->ip6_own_query); +} +#endif + +static void br_multicast_select_own_querier(struct net_bridge *br, + struct br_ip *ip, + struct sk_buff *skb) +{ + if (ip->proto == htons(ETH_P_IP)) + br->ip4_querier.addr.u.ip4 = ip_hdr(skb)->saddr; +#if IS_ENABLED(CONFIG_IPV6) + else + br->ip6_querier.addr.u.ip6 = ipv6_hdr(skb)->saddr; +#endif +} + +static void __br_multicast_send_query(struct net_bridge *br, + struct net_bridge_port *port, + struct br_ip *ip) +{ + struct sk_buff *skb; + + skb = br_multicast_alloc_query(br, ip); + if (!skb) + return; + + if (port) { + __skb_push(skb, sizeof(struct ethhdr)); + skb->dev = port->dev; + NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, skb, NULL, skb->dev, + dev_queue_xmit); + } else { + br_multicast_select_own_querier(br, ip, skb); + netif_rx(skb); + } +} + +static void br_multicast_send_query(struct net_bridge *br, + struct net_bridge_port *port, + struct bridge_mcast_own_query *own_query) +{ + unsigned long time; + struct br_ip br_group; + struct bridge_mcast_other_query *other_query = NULL; + + if (!netif_running(br->dev) || br->multicast_disabled || + !br->multicast_querier) + return; + + memset(&br_group.u, 0, sizeof(br_group.u)); + + if (port ? (own_query == &port->ip4_own_query) : + (own_query == &br->ip4_own_query)) { + other_query = &br->ip4_other_query; + br_group.proto = htons(ETH_P_IP); +#if IS_ENABLED(CONFIG_IPV6) + } else { + other_query = &br->ip6_other_query; + br_group.proto = htons(ETH_P_IPV6); +#endif + } + + if (!other_query || timer_pending(&other_query->timer)) + return; + + __br_multicast_send_query(br, port, &br_group); + + time = jiffies; + time += own_query->startup_sent < br->multicast_startup_query_count ? + br->multicast_startup_query_interval : + br->multicast_query_interval; + mod_timer(&own_query->timer, time); +} + +static void +br_multicast_port_query_expired(struct net_bridge_port *port, + struct bridge_mcast_own_query *query) +{ + struct net_bridge *br = port->br; + + spin_lock(&br->multicast_lock); + if (port->state == BR_STATE_DISABLED || + port->state == BR_STATE_BLOCKING) + goto out; + + if (query->startup_sent < br->multicast_startup_query_count) + query->startup_sent++; + + br_multicast_send_query(port->br, port, query); + +out: + spin_unlock(&br->multicast_lock); +} + +static void br_ip4_multicast_port_query_expired(unsigned long data) +{ + struct net_bridge_port *port = (void *)data; + + br_multicast_port_query_expired(port, &port->ip4_own_query); +} + +#if IS_ENABLED(CONFIG_IPV6) +static void br_ip6_multicast_port_query_expired(unsigned long data) +{ + struct net_bridge_port *port = (void *)data; + + br_multicast_port_query_expired(port, &port->ip6_own_query); +} +#endif + +void br_multicast_add_port(struct net_bridge_port *port) +{ + port->multicast_router = 1; + + setup_timer(&port->multicast_router_timer, br_multicast_router_expired, + (unsigned long)port); + setup_timer(&port->ip4_own_query.timer, + br_ip4_multicast_port_query_expired, (unsigned long)port); +#if IS_ENABLED(CONFIG_IPV6) + setup_timer(&port->ip6_own_query.timer, + br_ip6_multicast_port_query_expired, (unsigned long)port); +#endif +} + +void br_multicast_del_port(struct net_bridge_port *port) +{ + del_timer_sync(&port->multicast_router_timer); +} + +static void br_multicast_enable(struct bridge_mcast_own_query *query) +{ + query->startup_sent = 0; + + if (try_to_del_timer_sync(&query->timer) >= 0 || + del_timer(&query->timer)) + mod_timer(&query->timer, jiffies); +} + +void br_multicast_enable_port(struct net_bridge_port *port) +{ + struct net_bridge *br = port->br; + + spin_lock(&br->multicast_lock); + if (br->multicast_disabled || !netif_running(br->dev)) + goto out; + + br_multicast_enable(&port->ip4_own_query); +#if IS_ENABLED(CONFIG_IPV6) + br_multicast_enable(&port->ip6_own_query); +#endif + +out: + spin_unlock(&br->multicast_lock); +} + +void br_multicast_disable_port(struct net_bridge_port *port) +{ + struct net_bridge *br = port->br; + struct net_bridge_port_group *pg; + struct hlist_node *n; + + spin_lock(&br->multicast_lock); + hlist_for_each_entry_safe(pg, n, &port->mglist, mglist) + br_multicast_del_pg(br, pg); + + if (!hlist_unhashed(&port->rlist)) + hlist_del_init_rcu(&port->rlist); + del_timer(&port->multicast_router_timer); + del_timer(&port->ip4_own_query.timer); +#if IS_ENABLED(CONFIG_IPV6) + del_timer(&port->ip6_own_query.timer); +#endif + spin_unlock(&br->multicast_lock); +} + +static int br_ip4_multicast_igmp3_report(struct net_bridge *br, + struct net_bridge_port *port, + struct sk_buff *skb, + u16 vid) +{ + struct igmpv3_report *ih; + struct igmpv3_grec *grec; + int i; + int len; + int num; + int type; + int err = 0; + __be32 group; + + if (!pskb_may_pull(skb, sizeof(*ih))) + return -EINVAL; + + ih = igmpv3_report_hdr(skb); + num = ntohs(ih->ngrec); + len = sizeof(*ih); + + for (i = 0; i < num; i++) { + len += sizeof(*grec); + if (!pskb_may_pull(skb, len)) + return -EINVAL; + + grec = (void *)(skb->data + len - sizeof(*grec)); + group = grec->grec_mca; + type = grec->grec_type; + + len += ntohs(grec->grec_nsrcs) * 4; + if (!pskb_may_pull(skb, len)) + return -EINVAL; + + /* We treat this as an IGMPv2 report for now. */ + switch (type) { + case IGMPV3_MODE_IS_INCLUDE: + case IGMPV3_MODE_IS_EXCLUDE: + case IGMPV3_CHANGE_TO_INCLUDE: + case IGMPV3_CHANGE_TO_EXCLUDE: + case IGMPV3_ALLOW_NEW_SOURCES: + case IGMPV3_BLOCK_OLD_SOURCES: + break; + + default: + continue; + } + + err = br_ip4_multicast_add_group(br, port, group, vid); + if (err) + break; + } + + return err; +} + +#if IS_ENABLED(CONFIG_IPV6) +static int br_ip6_multicast_mld2_report(struct net_bridge *br, + struct net_bridge_port *port, + struct sk_buff *skb, + u16 vid) +{ + struct icmp6hdr *icmp6h; + struct mld2_grec *grec; + int i; + int len; + int num; + int err = 0; + + if (!pskb_may_pull(skb, sizeof(*icmp6h))) + return -EINVAL; + + icmp6h = icmp6_hdr(skb); + num = ntohs(icmp6h->icmp6_dataun.un_data16[1]); + len = sizeof(*icmp6h); + + for (i = 0; i < num; i++) { + __be16 *nsrcs, _nsrcs; + + nsrcs = skb_header_pointer(skb, + len + offsetof(struct mld2_grec, + grec_nsrcs), + sizeof(_nsrcs), &_nsrcs); + if (!nsrcs) + return -EINVAL; + + if (!pskb_may_pull(skb, + len + sizeof(*grec) + + sizeof(struct in6_addr) * ntohs(*nsrcs))) + return -EINVAL; + + grec = (struct mld2_grec *)(skb->data + len); + len += sizeof(*grec) + + sizeof(struct in6_addr) * ntohs(*nsrcs); + + /* We treat these as MLDv1 reports for now. */ + switch (grec->grec_type) { + case MLD2_MODE_IS_INCLUDE: + case MLD2_MODE_IS_EXCLUDE: + case MLD2_CHANGE_TO_INCLUDE: + case MLD2_CHANGE_TO_EXCLUDE: + case MLD2_ALLOW_NEW_SOURCES: + case MLD2_BLOCK_OLD_SOURCES: + break; + + default: + continue; + } + + err = br_ip6_multicast_add_group(br, port, &grec->grec_mca, + vid); + if (!err) + break; + } + + return err; +} +#endif + +static bool br_ip4_multicast_select_querier(struct net_bridge *br, + struct net_bridge_port *port, + __be32 saddr) +{ + if (!timer_pending(&br->ip4_own_query.timer) && + !timer_pending(&br->ip4_other_query.timer)) + goto update; + + if (!br->ip4_querier.addr.u.ip4) + goto update; + + if (ntohl(saddr) <= ntohl(br->ip4_querier.addr.u.ip4)) + goto update; + + return false; + +update: + br->ip4_querier.addr.u.ip4 = saddr; + + /* update protected by general multicast_lock by caller */ + rcu_assign_pointer(br->ip4_querier.port, port); + + return true; +} + +#if IS_ENABLED(CONFIG_IPV6) +static bool br_ip6_multicast_select_querier(struct net_bridge *br, + struct net_bridge_port *port, + struct in6_addr *saddr) +{ + if (!timer_pending(&br->ip6_own_query.timer) && + !timer_pending(&br->ip6_other_query.timer)) + goto update; + + if (ipv6_addr_cmp(saddr, &br->ip6_querier.addr.u.ip6) <= 0) + goto update; + + return false; + +update: + br->ip6_querier.addr.u.ip6 = *saddr; + + /* update protected by general multicast_lock by caller */ + rcu_assign_pointer(br->ip6_querier.port, port); + + return true; +} +#endif + +static bool br_multicast_select_querier(struct net_bridge *br, + struct net_bridge_port *port, + struct br_ip *saddr) +{ + switch (saddr->proto) { + case htons(ETH_P_IP): + return br_ip4_multicast_select_querier(br, port, saddr->u.ip4); +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): + return br_ip6_multicast_select_querier(br, port, &saddr->u.ip6); +#endif + } + + return false; +} + +static void +br_multicast_update_query_timer(struct net_bridge *br, + struct bridge_mcast_other_query *query, + unsigned long max_delay) +{ + if (!timer_pending(&query->timer)) + query->delay_time = jiffies + max_delay; + + mod_timer(&query->timer, jiffies + br->multicast_querier_interval); +} + +/* + * Add port to router_list + * list is maintained ordered by pointer value + * and locked by br->multicast_lock and RCU + */ +static void br_multicast_add_router(struct net_bridge *br, + struct net_bridge_port *port) +{ + struct net_bridge_port *p; + struct hlist_node *slot = NULL; + + hlist_for_each_entry(p, &br->router_list, rlist) { + if ((unsigned long) port >= (unsigned long) p) + break; + slot = &p->rlist; + } + + if (slot) + hlist_add_after_rcu(slot, &port->rlist); + else + hlist_add_head_rcu(&port->rlist, &br->router_list); +} + +static void br_multicast_mark_router(struct net_bridge *br, + struct net_bridge_port *port) +{ + unsigned long now = jiffies; + + if (!port) { + if (br->multicast_router == 1) + mod_timer(&br->multicast_router_timer, + now + br->multicast_querier_interval); + return; + } + + if (port->multicast_router != 1) + return; + + if (!hlist_unhashed(&port->rlist)) + goto timer; + + br_multicast_add_router(br, port); + +timer: + mod_timer(&port->multicast_router_timer, + now + br->multicast_querier_interval); +} + +static void br_multicast_query_received(struct net_bridge *br, + struct net_bridge_port *port, + struct bridge_mcast_other_query *query, + struct br_ip *saddr, + unsigned long max_delay) +{ + if (!br_multicast_select_querier(br, port, saddr)) + return; + + br_multicast_update_query_timer(br, query, max_delay); + br_multicast_mark_router(br, port); +} + +static int br_ip4_multicast_query(struct net_bridge *br, + struct net_bridge_port *port, + struct sk_buff *skb, + u16 vid) +{ + const struct iphdr *iph = ip_hdr(skb); + struct igmphdr *ih = igmp_hdr(skb); + struct net_bridge_mdb_entry *mp; + struct igmpv3_query *ih3; + struct net_bridge_port_group *p; + struct net_bridge_port_group __rcu **pp; + struct br_ip saddr; + unsigned long max_delay; + unsigned long now = jiffies; + __be32 group; + int err = 0; + + spin_lock(&br->multicast_lock); + if (!netif_running(br->dev) || + (port && port->state == BR_STATE_DISABLED)) + goto out; + + group = ih->group; + + if (skb->len == sizeof(*ih)) { + max_delay = ih->code * (HZ / IGMP_TIMER_SCALE); + + if (!max_delay) { + max_delay = 10 * HZ; + group = 0; + } + } else { + if (!pskb_may_pull(skb, sizeof(struct igmpv3_query))) { + err = -EINVAL; + goto out; + } + + ih3 = igmpv3_query_hdr(skb); + if (ih3->nsrcs) + goto out; + + max_delay = ih3->code ? + IGMPV3_MRC(ih3->code) * (HZ / IGMP_TIMER_SCALE) : 1; + } + + /* RFC2236+RFC3376 (IGMPv2+IGMPv3) require the multicast link layer + * all-systems destination addresses (224.0.0.1) for general queries + */ + if (!group && iph->daddr != htonl(INADDR_ALLHOSTS_GROUP)) { + err = -EINVAL; + goto out; + } + + if (!group) { + saddr.proto = htons(ETH_P_IP); + saddr.u.ip4 = iph->saddr; + + br_multicast_query_received(br, port, &br->ip4_other_query, + &saddr, max_delay); + goto out; + } + + mp = br_mdb_ip4_get(mlock_dereference(br->mdb, br), group, vid); + if (!mp) + goto out; + + max_delay *= br->multicast_last_member_count; + + if (mp->mglist && + (timer_pending(&mp->timer) ? + time_after(mp->timer.expires, now + max_delay) : + try_to_del_timer_sync(&mp->timer) >= 0)) + mod_timer(&mp->timer, now + max_delay); + + for (pp = &mp->ports; + (p = mlock_dereference(*pp, br)) != NULL; + pp = &p->next) { + if (timer_pending(&p->timer) ? + time_after(p->timer.expires, now + max_delay) : + try_to_del_timer_sync(&p->timer) >= 0) + mod_timer(&p->timer, now + max_delay); + } + +out: + spin_unlock(&br->multicast_lock); + return err; +} + +#if IS_ENABLED(CONFIG_IPV6) +static int br_ip6_multicast_query(struct net_bridge *br, + struct net_bridge_port *port, + struct sk_buff *skb, + u16 vid) +{ + const struct ipv6hdr *ip6h = ipv6_hdr(skb); + struct mld_msg *mld; + struct net_bridge_mdb_entry *mp; + struct mld2_query *mld2q; + struct net_bridge_port_group *p; + struct net_bridge_port_group __rcu **pp; + struct br_ip saddr; + unsigned long max_delay; + unsigned long now = jiffies; + const struct in6_addr *group = NULL; + bool is_general_query; + int err = 0; + + spin_lock(&br->multicast_lock); + if (!netif_running(br->dev) || + (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; + goto out; + } + mld = (struct mld_msg *) icmp6_hdr(skb); + max_delay = msecs_to_jiffies(ntohs(mld->mld_maxdelay)); + if (max_delay) + group = &mld->mld_mca; + } else { + if (!pskb_may_pull(skb, sizeof(*mld2q))) { + err = -EINVAL; + goto out; + } + mld2q = (struct mld2_query *)icmp6_hdr(skb); + if (!mld2q->mld2q_nsrcs) + group = &mld2q->mld2q_mca; + + max_delay = max(msecs_to_jiffies(mldv2_mrc(mld2q)), 1UL); + } + + is_general_query = group && ipv6_addr_any(group); + + /* RFC2710+RFC3810 (MLDv1+MLDv2) require the multicast link layer + * all-nodes destination address (ff02::1) for general queries + */ + if (is_general_query && !ipv6_addr_is_ll_all_nodes(&ip6h->daddr)) { + err = -EINVAL; + goto out; + } + + if (is_general_query) { + saddr.proto = htons(ETH_P_IPV6); + saddr.u.ip6 = ip6h->saddr; + + br_multicast_query_received(br, port, &br->ip6_other_query, + &saddr, max_delay); + goto out; + } else if (!group) { + goto out; + } + + mp = br_mdb_ip6_get(mlock_dereference(br->mdb, br), group, vid); + if (!mp) + goto out; + + max_delay *= br->multicast_last_member_count; + if (mp->mglist && + (timer_pending(&mp->timer) ? + time_after(mp->timer.expires, now + max_delay) : + try_to_del_timer_sync(&mp->timer) >= 0)) + mod_timer(&mp->timer, now + max_delay); + + for (pp = &mp->ports; + (p = mlock_dereference(*pp, br)) != NULL; + pp = &p->next) { + if (timer_pending(&p->timer) ? + time_after(p->timer.expires, now + max_delay) : + try_to_del_timer_sync(&p->timer) >= 0) + mod_timer(&p->timer, now + max_delay); + } + +out: + spin_unlock(&br->multicast_lock); + return err; +} +#endif + +static void +br_multicast_leave_group(struct net_bridge *br, + struct net_bridge_port *port, + struct br_ip *group, + struct bridge_mcast_other_query *other_query, + struct bridge_mcast_own_query *own_query) +{ + struct net_bridge_mdb_htable *mdb; + struct net_bridge_mdb_entry *mp; + struct net_bridge_port_group *p; + unsigned long now; + unsigned long time; + + spin_lock(&br->multicast_lock); + if (!netif_running(br->dev) || + (port && port->state == BR_STATE_DISABLED) || + timer_pending(&other_query->timer)) + goto out; + + mdb = mlock_dereference(br->mdb, br); + mp = br_mdb_ip_get(mdb, group); + if (!mp) + goto out; + + if (br->multicast_querier) { + __br_multicast_send_query(br, port, &mp->addr); + + time = jiffies + br->multicast_last_member_count * + br->multicast_last_member_interval; + + mod_timer(&own_query->timer, time); + + for (p = mlock_dereference(mp->ports, br); + p != NULL; + p = mlock_dereference(p->next, br)) { + if (p->port != port) + continue; + + if (!hlist_unhashed(&p->mglist) && + (timer_pending(&p->timer) ? + time_after(p->timer.expires, time) : + try_to_del_timer_sync(&p->timer) >= 0)) { + mod_timer(&p->timer, time); + } + + break; + } + } + + if (port && (port->flags & BR_MULTICAST_FAST_LEAVE)) { + struct net_bridge_port_group __rcu **pp; + + for (pp = &mp->ports; + (p = mlock_dereference(*pp, br)) != NULL; + pp = &p->next) { + if (p->port != port) + continue; + + rcu_assign_pointer(*pp, p->next); + hlist_del_init(&p->mglist); + del_timer(&p->timer); + call_rcu_bh(&p->rcu, br_multicast_free_pg); + br_mdb_notify(br->dev, port, group, RTM_DELMDB); + + if (!mp->ports && !mp->mglist && + netif_running(br->dev)) + mod_timer(&mp->timer, jiffies); + } + goto out; + } + + now = jiffies; + time = now + br->multicast_last_member_count * + br->multicast_last_member_interval; + + if (!port) { + if (mp->mglist && + (timer_pending(&mp->timer) ? + time_after(mp->timer.expires, time) : + try_to_del_timer_sync(&mp->timer) >= 0)) { + mod_timer(&mp->timer, time); + } + + goto out; + } + + for (p = mlock_dereference(mp->ports, br); + p != NULL; + p = mlock_dereference(p->next, br)) { + if (p->port != port) + continue; + + if (!hlist_unhashed(&p->mglist) && + (timer_pending(&p->timer) ? + time_after(p->timer.expires, time) : + try_to_del_timer_sync(&p->timer) >= 0)) { + mod_timer(&p->timer, time); + } + + break; + } +out: + spin_unlock(&br->multicast_lock); +} + +static void br_ip4_multicast_leave_group(struct net_bridge *br, + struct net_bridge_port *port, + __be32 group, + __u16 vid) +{ + struct br_ip br_group; + struct bridge_mcast_own_query *own_query; + + if (ipv4_is_local_multicast(group)) + return; + + own_query = port ? &port->ip4_own_query : &br->ip4_own_query; + + br_group.u.ip4 = group; + br_group.proto = htons(ETH_P_IP); + br_group.vid = vid; + + br_multicast_leave_group(br, port, &br_group, &br->ip4_other_query, + own_query); +} + +#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) +{ + struct br_ip br_group; + struct bridge_mcast_own_query *own_query; + + if (ipv6_addr_is_ll_all_nodes(group)) + return; + + own_query = port ? &port->ip6_own_query : &br->ip6_own_query; + + br_group.u.ip6 = *group; + br_group.proto = htons(ETH_P_IPV6); + br_group.vid = vid; + + br_multicast_leave_group(br, port, &br_group, &br->ip6_other_query, + own_query); +} +#endif + +static int br_multicast_ipv4_rcv(struct net_bridge *br, + struct net_bridge_port *port, + struct sk_buff *skb, + u16 vid) +{ + struct sk_buff *skb2 = skb; + const struct iphdr *iph; + 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; + + if (iph->protocol != IPPROTO_IGMP) { + if (!ipv4_is_local_multicast(iph->daddr)) + BR_INPUT_SKB_CB(skb)->mrouters_only = 1; + return 0; + } + + len = ntohs(iph->tot_len); + if (skb->len < len || len < ip_hdrlen(skb)) + return -EINVAL; + + if (skb->len > len) { + skb2 = skb_clone(skb, GFP_ATOMIC); + if (!skb2) + return -ENOMEM; + + err = pskb_trim_rcsum(skb2, len); + if (err) + goto err_out; + } + + len -= ip_hdrlen(skb2); + offset = skb_network_offset(skb2) + ip_hdrlen(skb2); + __skb_pull(skb2, offset); + skb_reset_transport_header(skb2); + + err = -EINVAL; + if (!pskb_may_pull(skb2, sizeof(*ih))) + goto out; + + switch (skb2->ip_summed) { + case CHECKSUM_COMPLETE: + if (!csum_fold(skb2->csum)) + break; + /* fall through */ + case CHECKSUM_NONE: + skb2->csum = 0; + if (skb_checksum_complete(skb2)) + goto out; + } + + err = 0; + + BR_INPUT_SKB_CB(skb)->igmp = 1; + ih = igmp_hdr(skb2); + + switch (ih->type) { + case IGMP_HOST_MEMBERSHIP_REPORT: + case IGMPV2_HOST_MEMBERSHIP_REPORT: + BR_INPUT_SKB_CB(skb)->mrouters_only = 1; + err = br_ip4_multicast_add_group(br, port, ih->group, vid); + break; + case IGMPV3_HOST_MEMBERSHIP_REPORT: + err = br_ip4_multicast_igmp3_report(br, port, skb2, vid); + break; + case IGMP_HOST_MEMBERSHIP_QUERY: + err = br_ip4_multicast_query(br, port, skb2, 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); + return err; +} + +#if IS_ENABLED(CONFIG_IPV6) +static int br_multicast_ipv6_rcv(struct net_bridge *br, + struct net_bridge_port *port, + struct sk_buff *skb, + u16 vid) +{ + struct sk_buff *skb2; + const struct ipv6hdr *ip6h; + u8 icmp6_type; + u8 nexthdr; + __be16 frag_off; + unsigned int len; + int offset; + int err; + + if (!pskb_may_pull(skb, sizeof(*ip6h))) + return -EINVAL; + + ip6h = ipv6_hdr(skb); + + /* + * We're interested in MLD messages only. + * - Version is 6 + * - MLD has always Router Alert hop-by-hop option + * - But we do not support jumbrograms. + */ + if (ip6h->version != 6) + 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); + + if (offset < 0 || nexthdr != IPPROTO_ICMPV6) + return 0; + + /* Okay, we found ICMPv6 header */ + skb2 = skb_clone(skb, GFP_ATOMIC); + if (!skb2) + return -ENOMEM; + + err = -EINVAL; + if (!pskb_may_pull(skb2, offset + sizeof(struct icmp6hdr))) + goto out; + + len -= offset - skb_network_offset(skb2); + + __skb_pull(skb2, offset); + skb_reset_transport_header(skb2); + skb_postpull_rcsum(skb2, skb_network_header(skb2), + skb_network_header_len(skb2)); + + icmp6_type = icmp6_hdr(skb2)->icmp6_type; + + switch (icmp6_type) { + case ICMPV6_MGM_QUERY: + case ICMPV6_MGM_REPORT: + case ICMPV6_MGM_REDUCTION: + case ICMPV6_MLD2_REPORT: + break; + default: + err = 0; + goto out; + } + + /* Okay, we found MLD message. Check further. */ + if (skb2->len > len) { + err = pskb_trim_rcsum(skb2, len); + if (err) + goto out; + err = -EINVAL; + } + + ip6h = ipv6_hdr(skb2); + + switch (skb2->ip_summed) { + case CHECKSUM_COMPLETE: + if (!csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, skb2->len, + IPPROTO_ICMPV6, skb2->csum)) + break; + /*FALLTHROUGH*/ + case CHECKSUM_NONE: + skb2->csum = ~csum_unfold(csum_ipv6_magic(&ip6h->saddr, + &ip6h->daddr, + skb2->len, + IPPROTO_ICMPV6, 0)); + if (__skb_checksum_complete(skb2)) + goto out; + } + + err = 0; + + BR_INPUT_SKB_CB(skb)->igmp = 1; + + switch (icmp6_type) { + case ICMPV6_MGM_REPORT: + { + struct mld_msg *mld; + if (!pskb_may_pull(skb2, sizeof(*mld))) { + err = -EINVAL; + goto out; + } + mld = (struct mld_msg *)skb_transport_header(skb2); + BR_INPUT_SKB_CB(skb)->mrouters_only = 1; + err = br_ip6_multicast_add_group(br, port, &mld->mld_mca, vid); + break; + } + case ICMPV6_MLD2_REPORT: + err = br_ip6_multicast_mld2_report(br, port, skb2, vid); + break; + case ICMPV6_MGM_QUERY: + err = br_ip6_multicast_query(br, port, skb2, 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); + } + } + +out: + kfree_skb(skb2); + return err; +} +#endif + +int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port, + struct sk_buff *skb, u16 vid) +{ + BR_INPUT_SKB_CB(skb)->igmp = 0; + BR_INPUT_SKB_CB(skb)->mrouters_only = 0; + + if (br->multicast_disabled) + return 0; + + switch (skb->protocol) { + case htons(ETH_P_IP): + return br_multicast_ipv4_rcv(br, port, skb, vid); +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): + return br_multicast_ipv6_rcv(br, port, skb, vid); +#endif + } + + return 0; +} + +static void br_multicast_query_expired(struct net_bridge *br, + struct bridge_mcast_own_query *query, + struct bridge_mcast_querier *querier) +{ + spin_lock(&br->multicast_lock); + if (query->startup_sent < br->multicast_startup_query_count) + query->startup_sent++; + + rcu_assign_pointer(querier, NULL); + br_multicast_send_query(br, NULL, query); + spin_unlock(&br->multicast_lock); +} + +static void br_ip4_multicast_query_expired(unsigned long data) +{ + struct net_bridge *br = (void *)data; + + br_multicast_query_expired(br, &br->ip4_own_query, &br->ip4_querier); +} + +#if IS_ENABLED(CONFIG_IPV6) +static void br_ip6_multicast_query_expired(unsigned long data) +{ + struct net_bridge *br = (void *)data; + + br_multicast_query_expired(br, &br->ip6_own_query, &br->ip6_querier); +} +#endif + +void br_multicast_init(struct net_bridge *br) +{ + br->hash_elasticity = 4; + br->hash_max = 512; + + br->multicast_router = 1; + br->multicast_querier = 0; + br->multicast_query_use_ifaddr = 0; + br->multicast_last_member_count = 2; + br->multicast_startup_query_count = 2; + + br->multicast_last_member_interval = HZ; + br->multicast_query_response_interval = 10 * HZ; + br->multicast_startup_query_interval = 125 * HZ / 4; + br->multicast_query_interval = 125 * HZ; + br->multicast_querier_interval = 255 * HZ; + br->multicast_membership_interval = 260 * HZ; + + br->ip4_other_query.delay_time = 0; + br->ip4_querier.port = NULL; +#if IS_ENABLED(CONFIG_IPV6) + br->ip6_other_query.delay_time = 0; + br->ip6_querier.port = NULL; +#endif + + spin_lock_init(&br->multicast_lock); + setup_timer(&br->multicast_router_timer, + br_multicast_local_router_expired, 0); + setup_timer(&br->ip4_other_query.timer, + br_ip4_multicast_querier_expired, (unsigned long)br); + setup_timer(&br->ip4_own_query.timer, br_ip4_multicast_query_expired, + (unsigned long)br); +#if IS_ENABLED(CONFIG_IPV6) + setup_timer(&br->ip6_other_query.timer, + br_ip6_multicast_querier_expired, (unsigned long)br); + setup_timer(&br->ip6_own_query.timer, br_ip6_multicast_query_expired, + (unsigned long)br); +#endif +} + +static void __br_multicast_open(struct net_bridge *br, + struct bridge_mcast_own_query *query) +{ + query->startup_sent = 0; + + if (br->multicast_disabled) + return; + + mod_timer(&query->timer, jiffies); +} + +void br_multicast_open(struct net_bridge *br) +{ + __br_multicast_open(br, &br->ip4_own_query); +#if IS_ENABLED(CONFIG_IPV6) + __br_multicast_open(br, &br->ip6_own_query); +#endif +} + +void br_multicast_stop(struct net_bridge *br) +{ + struct net_bridge_mdb_htable *mdb; + struct net_bridge_mdb_entry *mp; + struct hlist_node *n; + u32 ver; + int i; + + del_timer_sync(&br->multicast_router_timer); + del_timer_sync(&br->ip4_other_query.timer); + del_timer_sync(&br->ip4_own_query.timer); +#if IS_ENABLED(CONFIG_IPV6) + del_timer_sync(&br->ip6_other_query.timer); + del_timer_sync(&br->ip6_own_query.timer); +#endif + + spin_lock_bh(&br->multicast_lock); + mdb = mlock_dereference(br->mdb, br); + if (!mdb) + goto out; + + br->mdb = NULL; + + ver = mdb->ver; + for (i = 0; i < mdb->max; i++) { + hlist_for_each_entry_safe(mp, n, &mdb->mhash[i], + hlist[ver]) { + del_timer(&mp->timer); + call_rcu_bh(&mp->rcu, br_multicast_free_group); + } + } + + if (mdb->old) { + spin_unlock_bh(&br->multicast_lock); + rcu_barrier_bh(); + spin_lock_bh(&br->multicast_lock); + WARN_ON(mdb->old); + } + + mdb->old = mdb; + call_rcu_bh(&mdb->rcu, br_mdb_free); + +out: + spin_unlock_bh(&br->multicast_lock); +} + +int br_multicast_set_router(struct net_bridge *br, unsigned long val) +{ + int err = -ENOENT; + + spin_lock_bh(&br->multicast_lock); + if (!netif_running(br->dev)) + goto unlock; + + switch (val) { + case 0: + case 2: + del_timer(&br->multicast_router_timer); + /* fall through */ + case 1: + br->multicast_router = val; + err = 0; + break; + + default: + err = -EINVAL; + break; + } + +unlock: + spin_unlock_bh(&br->multicast_lock); + + return err; +} + +int br_multicast_set_port_router(struct net_bridge_port *p, unsigned long val) +{ + struct net_bridge *br = p->br; + int err = -ENOENT; + + spin_lock(&br->multicast_lock); + if (!netif_running(br->dev) || p->state == BR_STATE_DISABLED) + goto unlock; + + switch (val) { + case 0: + case 1: + case 2: + p->multicast_router = val; + err = 0; + + if (val < 2 && !hlist_unhashed(&p->rlist)) + hlist_del_init_rcu(&p->rlist); + + if (val == 1) + break; + + del_timer(&p->multicast_router_timer); + + if (val == 0) + break; + + br_multicast_add_router(br, p); + break; + + default: + err = -EINVAL; + break; + } + +unlock: + spin_unlock(&br->multicast_lock); + + return err; +} + +static void br_multicast_start_querier(struct net_bridge *br, + struct bridge_mcast_own_query *query) +{ + struct net_bridge_port *port; + + __br_multicast_open(br, query); + + list_for_each_entry(port, &br->port_list, list) { + if (port->state == BR_STATE_DISABLED || + port->state == BR_STATE_BLOCKING) + continue; + + if (query == &br->ip4_own_query) + br_multicast_enable(&port->ip4_own_query); +#if IS_ENABLED(CONFIG_IPV6) + else + br_multicast_enable(&port->ip6_own_query); +#endif + } +} + +int br_multicast_toggle(struct net_bridge *br, unsigned long val) +{ + int err = 0; + struct net_bridge_mdb_htable *mdb; + + spin_lock_bh(&br->multicast_lock); + if (br->multicast_disabled == !val) + goto unlock; + + br->multicast_disabled = !val; + if (br->multicast_disabled) + goto unlock; + + if (!netif_running(br->dev)) + goto unlock; + + mdb = mlock_dereference(br->mdb, br); + if (mdb) { + if (mdb->old) { + err = -EEXIST; +rollback: + br->multicast_disabled = !!val; + goto unlock; + } + + err = br_mdb_rehash(&br->mdb, mdb->max, + br->hash_elasticity); + if (err) + goto rollback; + } + + br_multicast_start_querier(br, &br->ip4_own_query); +#if IS_ENABLED(CONFIG_IPV6) + br_multicast_start_querier(br, &br->ip6_own_query); +#endif + +unlock: + spin_unlock_bh(&br->multicast_lock); + + return err; +} + +int br_multicast_set_querier(struct net_bridge *br, unsigned long val) +{ + unsigned long max_delay; + + val = !!val; + + spin_lock_bh(&br->multicast_lock); + if (br->multicast_querier == val) + goto unlock; + + br->multicast_querier = val; + if (!val) + goto unlock; + + max_delay = br->multicast_query_response_interval; + + if (!timer_pending(&br->ip4_other_query.timer)) + br->ip4_other_query.delay_time = jiffies + max_delay; + + br_multicast_start_querier(br, &br->ip4_own_query); + +#if IS_ENABLED(CONFIG_IPV6) + if (!timer_pending(&br->ip6_other_query.timer)) + br->ip6_other_query.delay_time = jiffies + max_delay; + + br_multicast_start_querier(br, &br->ip6_own_query); +#endif + +unlock: + spin_unlock_bh(&br->multicast_lock); + + return 0; +} + +int br_multicast_set_hash_max(struct net_bridge *br, unsigned long val) +{ + int err = -ENOENT; + u32 old; + struct net_bridge_mdb_htable *mdb; + + spin_lock_bh(&br->multicast_lock); + if (!netif_running(br->dev)) + goto unlock; + + err = -EINVAL; + if (!is_power_of_2(val)) + goto unlock; + + mdb = mlock_dereference(br->mdb, br); + if (mdb && val < mdb->size) + goto unlock; + + err = 0; + + old = br->hash_max; + br->hash_max = val; + + if (mdb) { + if (mdb->old) { + err = -EEXIST; +rollback: + br->hash_max = old; + goto unlock; + } + + err = br_mdb_rehash(&br->mdb, br->hash_max, + br->hash_elasticity); + if (err) + goto rollback; + } + +unlock: + spin_unlock_bh(&br->multicast_lock); + + return err; +} + +/** + * br_multicast_list_adjacent - Returns snooped multicast addresses + * @dev: The bridge port adjacent to which to retrieve addresses + * @br_ip_list: The list to store found, snooped multicast IP addresses in + * + * Creates a list of IP addresses (struct br_ip_list) sensed by the multicast + * snooping feature on all bridge ports of dev's bridge device, excluding + * the addresses from dev itself. + * + * Returns the number of items added to br_ip_list. + * + * Notes: + * - br_ip_list needs to be initialized by caller + * - br_ip_list might contain duplicates in the end + * (needs to be taken care of by caller) + * - br_ip_list needs to be freed by caller + */ +int br_multicast_list_adjacent(struct net_device *dev, + struct list_head *br_ip_list) +{ + struct net_bridge *br; + struct net_bridge_port *port; + struct net_bridge_port_group *group; + struct br_ip_list *entry; + int count = 0; + + rcu_read_lock(); + if (!br_ip_list || !br_port_exists(dev)) + goto unlock; + + port = br_port_get_rcu(dev); + if (!port || !port->br) + goto unlock; + + br = port->br; + + list_for_each_entry_rcu(port, &br->port_list, list) { + if (!port->dev || port->dev == dev) + continue; + + hlist_for_each_entry_rcu(group, &port->mglist, mglist) { + entry = kmalloc(sizeof(*entry), GFP_ATOMIC); + if (!entry) + goto unlock; + + entry->addr = group->addr; + list_add(&entry->list, br_ip_list); + count++; + } + } + +unlock: + rcu_read_unlock(); + return count; +} +EXPORT_SYMBOL_GPL(br_multicast_list_adjacent); + +/** + * br_multicast_has_querier_adjacent - Checks for a querier behind a bridge port + * @dev: The bridge port adjacent to which to check for a querier + * @proto: The protocol family to check for: IGMP -> ETH_P_IP, MLD -> ETH_P_IPV6 + * + * Checks whether the given interface has a bridge on top and if so returns + * true if a selected querier is behind one of the other ports of this + * bridge. Otherwise returns false. + */ +bool br_multicast_has_querier_adjacent(struct net_device *dev, int proto) +{ + struct net_bridge *br; + struct net_bridge_port *port; + bool ret = false; + + rcu_read_lock(); + if (!br_port_exists(dev)) + goto unlock; + + port = br_port_get_rcu(dev); + if (!port || !port->br) + goto unlock; + + br = port->br; + + switch (proto) { + case ETH_P_IP: + if (!timer_pending(&br->ip4_other_query.timer) || + rcu_dereference(br->ip4_querier.port) == port) + goto unlock; + break; +#if IS_ENABLED(CONFIG_IPV6) + case ETH_P_IPV6: + if (!timer_pending(&br->ip6_other_query.timer) || + rcu_dereference(br->ip6_querier.port) == port) + goto unlock; + break; +#endif + default: + goto unlock; + } + + ret = true; +unlock: + rcu_read_unlock(); + return ret; +} +EXPORT_SYMBOL_GPL(br_multicast_has_querier_adjacent); diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index 268e2e72588..a615264cf01 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -3,15 +3,8 @@ * Linux ethernet bridge * * Authors: - * Lennert Buytenhek <buytenh@gnu.org> - * Bart De Schuymer (maintainer) <bdschuym@pandora.be> - * - * Changes: - * Apr 29 2003: physdev module support (bdschuym) - * Jun 19 2003: let arptables see bridged ARP traffic (bdschuym) - * Oct 06 2003: filter encapsulated IP/ARP VLAN traffic on untagged bridge - * (bdschuym) - * Sep 01 2004: add IPv6 filtering (bdschuym) + * 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 @@ -23,6 +16,7 @@ #include <linux/module.h> #include <linux/kernel.h> +#include <linux/slab.h> #include <linux/ip.h> #include <linux/netdevice.h> #include <linux/skbuff.h> @@ -60,29 +54,45 @@ static int brnf_call_ip6tables __read_mostly = 1; static int brnf_call_arptables __read_mostly = 1; static int brnf_filter_vlan_tagged __read_mostly = 0; static int brnf_filter_pppoe_tagged __read_mostly = 0; +static int brnf_pass_vlan_indev __read_mostly = 0; #else +#define brnf_call_iptables 1 +#define brnf_call_ip6tables 1 +#define brnf_call_arptables 1 #define brnf_filter_vlan_tagged 0 #define brnf_filter_pppoe_tagged 0 +#define brnf_pass_vlan_indev 0 #endif +#define IS_IP(skb) \ + (!vlan_tx_tag_present(skb) && skb->protocol == htons(ETH_P_IP)) + +#define IS_IPV6(skb) \ + (!vlan_tx_tag_present(skb) && skb->protocol == htons(ETH_P_IPV6)) + +#define IS_ARP(skb) \ + (!vlan_tx_tag_present(skb) && skb->protocol == htons(ETH_P_ARP)) + static inline __be16 vlan_proto(const struct sk_buff *skb) { - return vlan_eth_hdr(skb)->h_vlan_encapsulated_proto; + if (vlan_tx_tag_present(skb)) + return skb->protocol; + else if (skb->protocol == htons(ETH_P_8021Q)) + return vlan_eth_hdr(skb)->h_vlan_encapsulated_proto; + else + return 0; } #define IS_VLAN_IP(skb) \ - (skb->protocol == htons(ETH_P_8021Q) && \ - vlan_proto(skb) == htons(ETH_P_IP) && \ + (vlan_proto(skb) == htons(ETH_P_IP) && \ brnf_filter_vlan_tagged) #define IS_VLAN_IPV6(skb) \ - (skb->protocol == htons(ETH_P_8021Q) && \ - vlan_proto(skb) == htons(ETH_P_IPV6) &&\ + (vlan_proto(skb) == htons(ETH_P_IPV6) && \ brnf_filter_vlan_tagged) #define IS_VLAN_ARP(skb) \ - (skb->protocol == htons(ETH_P_8021Q) && \ - vlan_proto(skb) == htons(ETH_P_ARP) && \ + (vlan_proto(skb) == htons(ETH_P_ARP) && \ brnf_filter_vlan_tagged) static inline __be16 pppoe_proto(const struct sk_buff *skb) @@ -101,15 +111,41 @@ static inline __be16 pppoe_proto(const struct sk_buff *skb) pppoe_proto(skb) == htons(PPP_IPV6) && \ brnf_filter_pppoe_tagged) -static void fake_update_pmtu(struct dst_entry *dst, u32 mtu) +static void fake_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu) +{ +} + +static void fake_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb) +{ +} + +static u32 *fake_cow_metrics(struct dst_entry *dst, unsigned long old) +{ + return NULL; +} + +static struct neighbour *fake_neigh_lookup(const struct dst_entry *dst, + struct sk_buff *skb, + const void *daddr) { + return NULL; +} + +static unsigned int fake_mtu(const struct dst_entry *dst) +{ + return dst->dev->mtu; } static struct dst_ops fake_dst_ops = { .family = AF_INET, .protocol = cpu_to_be16(ETH_P_IP), .update_pmtu = fake_update_pmtu, - .entries = ATOMIC_INIT(0), + .redirect = fake_redirect, + .cow_metrics = fake_cow_metrics, + .neigh_lookup = fake_neigh_lookup, + .mtu = fake_mtu, }; /* @@ -119,29 +155,35 @@ static struct dst_ops fake_dst_ops = { * ipt_REJECT needs it. Future netfilter modules might * require us to fill additional fields. */ +static const u32 br_dst_default_metrics[RTAX_MAX] = { + [RTAX_MTU - 1] = 1500, +}; + void br_netfilter_rtable_init(struct net_bridge *br) { struct rtable *rt = &br->fake_rtable; - atomic_set(&rt->u.dst.__refcnt, 1); - rt->u.dst.dev = br->dev; - rt->u.dst.path = &rt->u.dst; - rt->u.dst.metrics[RTAX_MTU - 1] = 1500; - rt->u.dst.flags = DST_NOXFRM; - rt->u.dst.ops = &fake_dst_ops; + atomic_set(&rt->dst.__refcnt, 1); + rt->dst.dev = br->dev; + rt->dst.path = &rt->dst; + dst_init_metrics(&rt->dst, br_dst_default_metrics, true); + rt->dst.flags = DST_NOXFRM | DST_FAKE_RTABLE; + rt->dst.ops = &fake_dst_ops; } static inline struct rtable *bridge_parent_rtable(const struct net_device *dev) { - struct net_bridge_port *port = rcu_dereference(dev->br_port); + struct net_bridge_port *port; + port = br_port_get_rcu(dev); return port ? &port->br->fake_rtable : NULL; } static inline struct net_device *bridge_parent(const struct net_device *dev) { - struct net_bridge_port *port = rcu_dereference(dev->br_port); + struct net_bridge_port *port; + port = br_port_get_rcu(dev); return port ? port->br->dev : NULL; } @@ -164,8 +206,8 @@ static inline struct nf_bridge_info *nf_bridge_unshare(struct sk_buff *skb) if (tmp) { memcpy(tmp, nf_bridge, sizeof(struct nf_bridge_info)); atomic_set(&tmp->use, 1); - nf_bridge_put(nf_bridge); } + nf_bridge_put(nf_bridge); nf_bridge = tmp; } return nf_bridge; @@ -203,15 +245,91 @@ static inline void nf_bridge_save_header(struct sk_buff *skb) skb->nf_bridge->data, header_size); } -/* - * When forwarding bridge frames, we save a copy of the original - * header before processing. +static inline void nf_bridge_update_protocol(struct sk_buff *skb) +{ + if (skb->nf_bridge->mask & BRNF_8021Q) + skb->protocol = htons(ETH_P_8021Q); + else if (skb->nf_bridge->mask & BRNF_PPPoE) + skb->protocol = htons(ETH_P_PPP_SES); +} + +/* When handing a packet over to the IP layer + * check whether we have a skb that is in the + * expected format + */ + +static int br_parse_ip_options(struct sk_buff *skb) +{ + struct ip_options *opt; + const struct iphdr *iph; + struct net_device *dev = skb->dev; + u32 len; + + if (!pskb_may_pull(skb, sizeof(struct iphdr))) + goto inhdr_error; + + iph = ip_hdr(skb); + opt = &(IPCB(skb)->opt); + + /* Basic sanity checks */ + if (iph->ihl < 5 || iph->version != 4) + goto inhdr_error; + + if (!pskb_may_pull(skb, iph->ihl*4)) + goto inhdr_error; + + iph = ip_hdr(skb); + if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl))) + goto inhdr_error; + + len = ntohs(iph->tot_len); + if (skb->len < len) { + IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INTRUNCATEDPKTS); + goto drop; + } else if (len < (iph->ihl*4)) + goto inhdr_error; + + if (pskb_trim_rcsum(skb, len)) { + IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INDISCARDS); + goto drop; + } + + memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); + if (iph->ihl == 5) + return 0; + + opt->optlen = iph->ihl*4 - sizeof(struct iphdr); + if (ip_options_compile(dev_net(dev), opt, skb)) + goto inhdr_error; + + /* Check correct handling of SRR option */ + if (unlikely(opt->srr)) { + struct in_device *in_dev = __in_dev_get_rcu(dev); + if (in_dev && !IN_DEV_SOURCE_ROUTE(in_dev)) + goto drop; + + if (ip_options_rcv_srr(skb)) + goto drop; + } + + return 0; + +inhdr_error: + IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INHDRERRORS); +drop: + return -1; +} + +/* Fill in the header for fragmented IP packets handled by + * the IPv4 connection tracking code. */ int nf_bridge_copy_header(struct sk_buff *skb) { int err; - int header_size = ETH_HLEN + nf_bridge_encap_header_len(skb); + unsigned int header_size; + nf_bridge_update_protocol(skb); + header_size = ETH_HLEN + nf_bridge_encap_header_len(skb); err = skb_cow_head(skb, header_size); if (err) return err; @@ -241,31 +359,63 @@ static int br_nf_pre_routing_finish_ipv6(struct sk_buff *skb) kfree_skb(skb); return 0; } - dst_hold(&rt->u.dst); - skb_dst_set(skb, &rt->u.dst); + 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(PF_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL, + NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL, br_handle_frame_finish, 1); return 0; } -static void __br_dnat_complain(void) +/* 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 sk_buff *skb) { - static unsigned long last_complaint; + struct nf_bridge_info *nf_bridge = skb->nf_bridge; + struct neighbour *neigh; + struct dst_entry *dst; - if (jiffies - last_complaint >= 5 * HZ) { - printk(KERN_WARNING "Performing cross-bridge DNAT requires IP " - "forwarding to be enabled\n"); - last_complaint = jiffies; + skb->dev = bridge_parent(skb->dev); + if (!skb->dev) + goto free_skb; + dst = skb_dst(skb); + neigh = dst_neigh_lookup_skb(dst, skb); + if (neigh) { + int ret; + + if (neigh->hh.hh_len) { + neigh_hh_bridge(&neigh->hh, skb); + skb->dev = nf_bridge->physindev; + ret = br_handle_frame_finish(skb); + } else { + /* the neighbour function below overwrites the complete + * MAC header, so we save the Ethernet source address and + * protocol number. + */ + skb_copy_from_linear_data_offset(skb, + -(ETH_HLEN-ETH_ALEN), + skb->nf_bridge->data, + ETH_HLEN-ETH_ALEN); + /* tell br_dev_xmit to continue with forwarding */ + nf_bridge->mask |= BRNF_BRIDGED_DNAT; + ret = neigh->output(neigh, skb); + } + neigh_release(neigh); + return ret; } +free_skb: + kfree_skb(skb); + return 0; } /* This requires some explaining. If DNAT has taken place, - * we will need to fix up the destination Ethernet address, - * and this is a tricky process. + * we will need to fix up the destination Ethernet address. * * There are two cases to consider: * 1. The packet was DNAT'ed to a device in the same bridge @@ -279,62 +429,29 @@ static void __br_dnat_complain(void) * call ip_route_input() and to look at skb->dst->dev, which is * changed to the destination device if ip_route_input() succeeds. * - * Let us first consider the case that ip_route_input() succeeds: - * - * If skb->dst->dev equals the logical bridge device the packet - * came in on, we can consider this bridging. The packet is passed - * through the neighbour output function to build a new destination - * MAC address, which will make the packet enter br_nf_local_out() - * not much later. In that function it is assured that the iptables - * FORWARD chain is traversed for the packet. + * Let's first consider the case that ip_route_input() succeeds: * + * If the output device equals the logical bridge device the packet + * came in on, we can consider this bridging. The corresponding MAC + * address will be obtained in br_nf_pre_routing_finish_bridge. * Otherwise, the packet is considered to be routed and we just * change the destination MAC address so that the packet will * later be passed up to the IP stack to be routed. For a redirected * packet, ip_route_input() will give back the localhost as output device, * which differs from the bridge device. * - * Let us now consider the case that ip_route_input() fails: + * Let's now consider the case that ip_route_input() fails: * * This can be because the destination address is martian, in which case * the packet will be dropped. - * After a "echo '0' > /proc/sys/net/ipv4/ip_forward" ip_route_input() - * will fail, while __ip_route_output_key() will return success. The source - * address for __ip_route_output_key() is set to zero, so __ip_route_output_key + * If IP forwarding is disabled, ip_route_input() will fail, while + * ip_route_output_key() can return success. The source + * address for ip_route_output_key() is set to zero, so ip_route_output_key() * thinks we're handling a locally generated packet and won't care - * if IP forwarding is allowed. We send a warning message to the users's - * log telling her to put IP forwarding on. - * - * ip_route_input() will also fail if there is no route available. - * In that case we just drop the packet. - * - * --Lennert, 20020411 - * --Bart, 20020416 (updated) - * --Bart, 20021007 (updated) - * --Bart, 20062711 (updated) */ -static int br_nf_pre_routing_finish_bridge(struct sk_buff *skb) -{ - if (skb->pkt_type == PACKET_OTHERHOST) { - skb->pkt_type = PACKET_HOST; - skb->nf_bridge->mask |= BRNF_PKT_TYPE; - } - skb->nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING; - - skb->dev = bridge_parent(skb->dev); - if (skb->dev) { - struct dst_entry *dst = skb_dst(skb); - - nf_bridge_pull_encap_header(skb); - - if (dst->hh) - return neigh_hh_output(dst->hh, skb); - else if (dst->neighbour) - return dst->neighbour->output(skb); - } - kfree_skb(skb); - return 0; -} - + * if IP forwarding is enabled. If the output device equals the logical bridge + * device, we proceed as if ip_route_input() succeeded. If it differs from the + * logical bridge port or if ip_route_output_key() fails we drop the packet. + */ static int br_nf_pre_routing_finish(struct sk_buff *skb) { struct net_device *dev = skb->dev; @@ -350,15 +467,6 @@ static int br_nf_pre_routing_finish(struct sk_buff *skb) nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING; if (dnat_took_place(skb)) { if ((err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev))) { - struct flowi fl = { - .nl_u = { - .ip4_u = { - .daddr = iph->daddr, - .saddr = 0, - .tos = RT_TOS(iph->tos) }, - }, - .proto = 0, - }; struct in_device *in_dev = __in_dev_get_rcu(dev); /* If err equals -EHOSTUNREACH the error is due to a @@ -371,19 +479,16 @@ static int br_nf_pre_routing_finish(struct sk_buff *skb) if (err != -EHOSTUNREACH || !in_dev || IN_DEV_FORWARD(in_dev)) goto free_skb; - if (!ip_route_output_key(dev_net(dev), &rt, &fl)) { + rt = ip_route_output(dev_net(dev), iph->daddr, 0, + RT_TOS(iph->tos), 0); + if (!IS_ERR(rt)) { /* - Bridged-and-DNAT'ed traffic doesn't * require ip_forwarding. */ - if (((struct dst_entry *)rt)->dev == dev) { - skb_dst_set(skb, (struct dst_entry *)rt); + if (rt->dst.dev == dev) { + skb_dst_set(skb, &rt->dst); goto bridged_dnat; } - /* we are sure that forwarding is disabled, so printing - * this message is no problem. Note that the packet could - * still have a martian destination address, in which case - * the packet could be dropped even if forwarding were enabled */ - __br_dnat_complain(); - dst_release((struct dst_entry *)rt); + ip_rt_put(rt); } free_skb: kfree_skb(skb); @@ -391,18 +496,17 @@ free_skb: } else { if (skb_dst(skb)->dev == dev) { bridged_dnat: - /* Tell br_nf_local_out this is a - * bridged frame */ - nf_bridge->mask |= BRNF_BRIDGED_DNAT; skb->dev = nf_bridge->physindev; + nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); - NF_HOOK_THRESH(PF_BRIDGE, NF_BR_PRE_ROUTING, + NF_HOOK_THRESH(NFPROTO_BRIDGE, + NF_BR_PRE_ROUTING, skb, skb->dev, NULL, br_nf_pre_routing_finish_bridge, 1); return 0; } - memcpy(eth_hdr(skb)->h_dest, dev->dev_addr, ETH_ALEN); + ether_addr_copy(eth_hdr(skb)->h_dest, dev->dev_addr); skb->pkt_type = PACKET_HOST; } } else { @@ -411,18 +515,32 @@ bridged_dnat: kfree_skb(skb); return 0; } - dst_hold(&rt->u.dst); - skb_dst_set(skb, &rt->u.dst); + 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(PF_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL, + NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL, br_handle_frame_finish, 1); return 0; } +static struct net_device *brnf_get_logical_dev(struct sk_buff *skb, const struct net_device *dev) +{ + struct net_device *vlan, *br; + + br = bridge_parent(dev); + if (brnf_pass_vlan_indev == 0 || !vlan_tx_tag_present(skb)) + return br; + + vlan = __vlan_find_dev_deep_rcu(br, skb->vlan_proto, + vlan_tx_tag_get(skb) & VLAN_VID_MASK); + + return vlan ? vlan : br; +} + /* Some common code for IPv4/IPv6 */ static struct net_device *setup_pre_routing(struct sk_buff *skb) { @@ -435,8 +553,14 @@ static struct net_device *setup_pre_routing(struct sk_buff *skb) nf_bridge->mask |= BRNF_NF_BRIDGE_PREROUTING; nf_bridge->physindev = skb->dev; - skb->dev = bridge_parent(skb->dev); - + skb->dev = brnf_get_logical_dev(skb, skb->dev); + if (skb->protocol == htons(ETH_P_8021Q)) + nf_bridge->mask |= BRNF_8021Q; + else if (skb->protocol == htons(ETH_P_PPP_SES)) + nf_bridge->mask |= BRNF_PPPoE; + + /* Must drop socket now because of tproxy. */ + skb_orphan(skb); return skb->dev; } @@ -459,7 +583,7 @@ static int check_hbh_len(struct sk_buff *skb) int optlen = nh[off + 1] + 2; switch (nh[off]) { - case IPV6_TLV_PAD0: + case IPV6_TLV_PAD1: optlen = 1; break; @@ -497,36 +621,36 @@ bad: /* 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(unsigned int hook, +static unsigned int br_nf_pre_routing_ipv6(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - struct ipv6hdr *hdr; + const struct ipv6hdr *hdr; u32 pkt_len; if (skb->len < sizeof(struct ipv6hdr)) - goto inhdr_error; + return NF_DROP; if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) - goto inhdr_error; + return NF_DROP; hdr = ipv6_hdr(skb); if (hdr->version != 6) - goto inhdr_error; + return NF_DROP; pkt_len = ntohs(hdr->payload_len); if (pkt_len || hdr->nexthdr != NEXTHDR_HOP) { if (pkt_len + sizeof(struct ipv6hdr) > skb->len) - goto inhdr_error; + return NF_DROP; if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr))) - goto inhdr_error; + return NF_DROP; } if (hdr->nexthdr == NEXTHDR_HOP && check_hbh_len(skb)) - goto inhdr_error; + return NF_DROP; nf_bridge_put(skb->nf_bridge); if (!nf_bridge_alloc(skb)) @@ -534,13 +658,11 @@ static unsigned int br_nf_pre_routing_ipv6(unsigned int hook, if (!setup_pre_routing(skb)) return NF_DROP; - NF_HOOK(PF_INET6, NF_INET_PRE_ROUTING, skb, skb->dev, NULL, + skb->protocol = htons(ETH_P_IPV6); + NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, skb, skb->dev, NULL, br_nf_pre_routing_finish_ipv6); return NF_STOLEN; - -inhdr_error: - return NF_DROP; } /* Direct IPv6 traffic to br_nf_pre_routing_ipv6. @@ -549,56 +671,42 @@ inhdr_error: * receiving device) to make netfilter happy, the REDIRECT * target in particular. Save the original destination IP * address to be able to detect DNAT afterwards. */ -static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff *skb, +static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops, + struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - struct iphdr *iph; + struct net_bridge_port *p; + struct net_bridge *br; __u32 len = nf_bridge_encap_header_len(skb); if (unlikely(!pskb_may_pull(skb, len))) - goto out; + return NF_DROP; - if (skb->protocol == htons(ETH_P_IPV6) || IS_VLAN_IPV6(skb) || - IS_PPPOE_IPV6(skb)) { -#ifdef CONFIG_SYSCTL - if (!brnf_call_ip6tables) + p = br_port_get_rcu(in); + if (p == NULL) + return NF_DROP; + br = p->br; + + if (IS_IPV6(skb) || IS_VLAN_IPV6(skb) || IS_PPPOE_IPV6(skb)) { + if (!brnf_call_ip6tables && !br->nf_call_ip6tables) return NF_ACCEPT; -#endif + nf_bridge_pull_encap_header_rcsum(skb); - return br_nf_pre_routing_ipv6(hook, skb, in, out, okfn); + return br_nf_pre_routing_ipv6(ops, skb, in, out, okfn); } -#ifdef CONFIG_SYSCTL - if (!brnf_call_iptables) + + if (!brnf_call_iptables && !br->nf_call_iptables) return NF_ACCEPT; -#endif - if (skb->protocol != htons(ETH_P_IP) && !IS_VLAN_IP(skb) && - !IS_PPPOE_IP(skb)) + if (!IS_IP(skb) && !IS_VLAN_IP(skb) && !IS_PPPOE_IP(skb)) return NF_ACCEPT; nf_bridge_pull_encap_header_rcsum(skb); - if (!pskb_may_pull(skb, sizeof(struct iphdr))) - goto inhdr_error; - - iph = ip_hdr(skb); - if (iph->ihl < 5 || iph->version != 4) - goto inhdr_error; - - if (!pskb_may_pull(skb, 4 * iph->ihl)) - goto inhdr_error; - - iph = ip_hdr(skb); - if (ip_fast_csum((__u8 *) iph, iph->ihl) != 0) - goto inhdr_error; - - len = ntohs(iph->tot_len); - if (skb->len < len || len < 4 * iph->ihl) - goto inhdr_error; - - pskb_trim_rcsum(skb, len); + if (br_parse_ip_options(skb)) + return NF_DROP; nf_bridge_put(skb->nf_bridge); if (!nf_bridge_alloc(skb)) @@ -606,16 +714,12 @@ static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff *skb, if (!setup_pre_routing(skb)) return NF_DROP; store_orig_dstaddr(skb); + skb->protocol = htons(ETH_P_IP); - NF_HOOK(PF_INET, NF_INET_PRE_ROUTING, skb, skb->dev, NULL, + NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, skb, skb->dev, NULL, br_nf_pre_routing_finish); return NF_STOLEN; - -inhdr_error: -// IP_INC_STATS_BH(IpInHdrErrors); -out: - return NF_DROP; } @@ -626,16 +730,13 @@ out: * took place when the packet entered the bridge), but we * register an IPv4 PRE_ROUTING 'sabotage' hook that will * prevent this from happening. */ -static unsigned int br_nf_local_in(unsigned int hook, struct sk_buff *skb, +static unsigned int br_nf_local_in(const struct nf_hook_ops *ops, + struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - struct rtable *rt = skb_rtable(skb); - - if (rt && rt == bridge_parent_rtable(in)) - skb_dst_drop(skb); - + br_drop_fake_rtable(skb); return NF_ACCEPT; } @@ -645,27 +746,31 @@ static int br_nf_forward_finish(struct sk_buff *skb) struct nf_bridge_info *nf_bridge = skb->nf_bridge; struct net_device *in; - if (skb->protocol != htons(ETH_P_ARP) && !IS_VLAN_ARP(skb)) { + if (!IS_ARP(skb) && !IS_VLAN_ARP(skb)) { in = nf_bridge->physindev; if (nf_bridge->mask & BRNF_PKT_TYPE) { skb->pkt_type = PACKET_OTHERHOST; nf_bridge->mask ^= BRNF_PKT_TYPE; } + nf_bridge_update_protocol(skb); } else { in = *((struct net_device **)(skb->cb)); } nf_bridge_push_encap_header(skb); - NF_HOOK_THRESH(PF_BRIDGE, NF_BR_FORWARD, skb, in, + + NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_FORWARD, skb, in, skb->dev, br_forward_finish, 1); return 0; } + /* This is the 'purely bridged' case. For IP, we pass the packet to * netfilter with indev and outdev set to the bridge device, * but we are still able to filter on the 'real' indev/outdev * because of the physdev module. For ARP, indev and outdev are the * bridge ports. */ -static unsigned int br_nf_forward_ip(unsigned int hook, struct sk_buff *skb, +static unsigned int br_nf_forward_ip(const struct nf_hook_ops *ops, + struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) @@ -686,12 +791,10 @@ static unsigned int br_nf_forward_ip(unsigned int hook, struct sk_buff *skb, if (!parent) return NF_DROP; - if (skb->protocol == htons(ETH_P_IP) || IS_VLAN_IP(skb) || - IS_PPPOE_IP(skb)) - pf = PF_INET; - else if (skb->protocol == htons(ETH_P_IPV6) || IS_VLAN_IPV6(skb) || - IS_PPPOE_IPV6(skb)) - pf = PF_INET6; + if (IS_IP(skb) || IS_VLAN_IP(skb) || IS_PPPOE_IP(skb)) + pf = NFPROTO_IPV4; + else if (IS_IPV6(skb) || IS_VLAN_IPV6(skb) || IS_PPPOE_IPV6(skb)) + pf = NFPROTO_IPV6; else return NF_ACCEPT; @@ -703,29 +806,42 @@ static unsigned int br_nf_forward_ip(unsigned int hook, struct sk_buff *skb, nf_bridge->mask |= BRNF_PKT_TYPE; } + if (pf == NFPROTO_IPV4 && br_parse_ip_options(skb)) + return NF_DROP; + /* The physdev module checks on this */ nf_bridge->mask |= BRNF_BRIDGED; nf_bridge->physoutdev = skb->dev; + if (pf == NFPROTO_IPV4) + skb->protocol = htons(ETH_P_IP); + else + skb->protocol = htons(ETH_P_IPV6); - NF_HOOK(pf, NF_INET_FORWARD, skb, bridge_parent(in), parent, + NF_HOOK(pf, NF_INET_FORWARD, skb, brnf_get_logical_dev(skb, in), parent, br_nf_forward_finish); return NF_STOLEN; } -static unsigned int br_nf_forward_arp(unsigned int hook, struct sk_buff *skb, +static unsigned int br_nf_forward_arp(const struct nf_hook_ops *ops, + struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { + struct net_bridge_port *p; + struct net_bridge *br; struct net_device **d = (struct net_device **)(skb->cb); -#ifdef CONFIG_SYSCTL - if (!brnf_call_arptables) + p = br_port_get_rcu(out); + if (p == NULL) + return NF_ACCEPT; + br = p->br; + + if (!brnf_call_arptables && !br->nf_call_arptables) return NF_ACCEPT; -#endif - if (skb->protocol != htons(ETH_P_ARP)) { + if (!IS_ARP(skb)) { if (!IS_VLAN_ARP(skb)) return NF_ACCEPT; nf_bridge_pull_encap_header(skb); @@ -743,64 +859,22 @@ static unsigned int br_nf_forward_arp(unsigned int hook, struct sk_buff *skb, return NF_STOLEN; } -/* PF_BRIDGE/LOCAL_OUT *********************************************** - * - * This function sees both locally originated IP packets and forwarded - * IP packets (in both cases the destination device is a bridge - * device). It also sees bridged-and-DNAT'ed packets. - * - * If (nf_bridge->mask & BRNF_BRIDGED_DNAT) then the packet is bridged - * and we fake the PF_BRIDGE/FORWARD hook. The function br_nf_forward() - * will then fake the PF_INET/FORWARD hook. br_nf_local_out() has priority - * NF_BR_PRI_FIRST, so no relevant PF_BRIDGE/INPUT functions have been nor - * will be executed. - */ -static unsigned int br_nf_local_out(unsigned int hook, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) +#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) +static int br_nf_dev_queue_xmit(struct sk_buff *skb) { - struct net_device *realindev; - struct nf_bridge_info *nf_bridge; - - if (!skb->nf_bridge) - return NF_ACCEPT; - - /* Need exclusive nf_bridge_info since we might have multiple - * different physoutdevs. */ - if (!nf_bridge_unshare(skb)) - return NF_DROP; - - nf_bridge = skb->nf_bridge; - if (!(nf_bridge->mask & BRNF_BRIDGED_DNAT)) - return NF_ACCEPT; - - /* Bridged, take PF_BRIDGE/FORWARD. - * (see big note in front of br_nf_pre_routing_finish) */ - nf_bridge->physoutdev = skb->dev; - realindev = nf_bridge->physindev; - - if (nf_bridge->mask & BRNF_PKT_TYPE) { - skb->pkt_type = PACKET_OTHERHOST; - nf_bridge->mask ^= BRNF_PKT_TYPE; - } - nf_bridge_push_encap_header(skb); + int ret; - NF_HOOK(PF_BRIDGE, NF_BR_FORWARD, skb, realindev, skb->dev, - br_forward_finish); - return NF_STOLEN; -} + if (skb->protocol == htons(ETH_P_IP) && + skb->len + nf_bridge_mtu_reduction(skb) > skb->dev->mtu && + !skb_is_gso(skb)) { + if (br_parse_ip_options(skb)) + /* Drop invalid packet */ + return NF_DROP; + ret = ip_fragment(skb, br_dev_queue_push_xmit); + } else + ret = br_dev_queue_push_xmit(skb); -#if defined(CONFIG_NF_CONNTRACK_IPV4) || defined(CONFIG_NF_CONNTRACK_IPV4_MODULE) -static int br_nf_dev_queue_xmit(struct sk_buff *skb) -{ - if (skb->nfct != NULL && - (skb->protocol == htons(ETH_P_IP) || IS_VLAN_IP(skb)) && - skb->len > skb->dev->mtu && - !skb_is_gso(skb)) - return ip_fragment(skb, br_dev_queue_push_xmit); - else - return br_dev_queue_push_xmit(skb); + return ret; } #else static int br_nf_dev_queue_xmit(struct sk_buff *skb) @@ -810,7 +884,8 @@ static int br_nf_dev_queue_xmit(struct sk_buff *skb) #endif /* PF_BRIDGE/POST_ROUTING ********************************************/ -static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff *skb, +static unsigned int br_nf_post_routing(const struct nf_hook_ops *ops, + struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) @@ -819,42 +894,19 @@ static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff *skb, struct net_device *realoutdev = bridge_parent(skb->dev); u_int8_t pf; -#ifdef CONFIG_NETFILTER_DEBUG - /* Be very paranoid. This probably won't happen anymore, but let's - * keep the check just to be sure... */ - if (skb_mac_header(skb) < skb->head || - skb_mac_header(skb) + ETH_HLEN > skb->data) { - printk(KERN_CRIT "br_netfilter: Argh!! br_nf_post_routing: " - "bad mac.raw pointer.\n"); - goto print_error; - } -#endif - - if (!nf_bridge) - return NF_ACCEPT; - - if (!(nf_bridge->mask & (BRNF_BRIDGED | BRNF_BRIDGED_DNAT))) + if (!nf_bridge || !(nf_bridge->mask & BRNF_BRIDGED)) return NF_ACCEPT; if (!realoutdev) return NF_DROP; - if (skb->protocol == htons(ETH_P_IP) || IS_VLAN_IP(skb) || - IS_PPPOE_IP(skb)) - pf = PF_INET; - else if (skb->protocol == htons(ETH_P_IPV6) || IS_VLAN_IPV6(skb) || - IS_PPPOE_IPV6(skb)) - pf = PF_INET6; + if (IS_IP(skb) || IS_VLAN_IP(skb) || IS_PPPOE_IP(skb)) + pf = NFPROTO_IPV4; + else if (IS_IPV6(skb) || IS_VLAN_IPV6(skb) || IS_PPPOE_IPV6(skb)) + pf = NFPROTO_IPV6; else return NF_ACCEPT; -#ifdef CONFIG_NETFILTER_DEBUG - if (skb_dst(skb) == NULL) { - printk(KERN_INFO "br_netfilter post_routing: skb->dst == NULL\n"); - goto print_error; - } -#endif - /* We assume any code from br_dev_queue_push_xmit onwards doesn't care * about the value of skb->pkt_type. */ if (skb->pkt_type == PACKET_OTHERHOST) { @@ -864,30 +916,22 @@ static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff *skb, nf_bridge_pull_encap_header(skb); nf_bridge_save_header(skb); + if (pf == NFPROTO_IPV4) + skb->protocol = htons(ETH_P_IP); + else + skb->protocol = htons(ETH_P_IPV6); NF_HOOK(pf, NF_INET_POST_ROUTING, skb, NULL, realoutdev, br_nf_dev_queue_xmit); return NF_STOLEN; - -#ifdef CONFIG_NETFILTER_DEBUG -print_error: - if (skb->dev != NULL) { - printk("[%s]", skb->dev->name); - if (realoutdev) - printk("[%s]", realoutdev->name); - } - printk(" head:%p, raw:%p, data:%p\n", skb->head, skb_mac_header(skb), - skb->data); - dump_stack(); - return NF_ACCEPT; -#endif } /* IP/SABOTAGE *****************************************************/ /* Don't hand locally destined packets to PF_INET(6)/PRE_ROUTING * for the second time. */ -static unsigned int ip_sabotage_in(unsigned int hook, struct sk_buff *skb, +static unsigned int ip_sabotage_in(const struct nf_hook_ops *ops, + struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) @@ -900,64 +944,55 @@ static unsigned int ip_sabotage_in(unsigned int hook, struct sk_buff *skb, return NF_ACCEPT; } -/* For br_nf_local_out we need (prio = NF_BR_PRI_FIRST), to insure that innocent - * PF_BRIDGE/NF_BR_LOCAL_OUT functions don't get bridged traffic as input. - * For br_nf_post_routing, we need (prio = NF_BR_PRI_LAST), because - * ip_refrag() can return NF_STOLEN. */ +/* For br_nf_post_routing, we need (prio = NF_BR_PRI_LAST), because + * br_dev_queue_push_xmit is called afterwards */ static struct nf_hook_ops br_nf_ops[] __read_mostly = { { .hook = br_nf_pre_routing, .owner = THIS_MODULE, - .pf = PF_BRIDGE, + .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_PRE_ROUTING, .priority = NF_BR_PRI_BRNF, }, { .hook = br_nf_local_in, .owner = THIS_MODULE, - .pf = PF_BRIDGE, + .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_LOCAL_IN, .priority = NF_BR_PRI_BRNF, }, { .hook = br_nf_forward_ip, .owner = THIS_MODULE, - .pf = PF_BRIDGE, + .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_FORWARD, .priority = NF_BR_PRI_BRNF - 1, }, { .hook = br_nf_forward_arp, .owner = THIS_MODULE, - .pf = PF_BRIDGE, + .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_FORWARD, .priority = NF_BR_PRI_BRNF, }, { - .hook = br_nf_local_out, - .owner = THIS_MODULE, - .pf = PF_BRIDGE, - .hooknum = NF_BR_LOCAL_OUT, - .priority = NF_BR_PRI_FIRST, - }, - { .hook = br_nf_post_routing, .owner = THIS_MODULE, - .pf = PF_BRIDGE, + .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_POST_ROUTING, .priority = NF_BR_PRI_LAST, }, { .hook = ip_sabotage_in, .owner = THIS_MODULE, - .pf = PF_INET, + .pf = NFPROTO_IPV4, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP_PRI_FIRST, }, { .hook = ip_sabotage_in, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP6_PRI_FIRST, }, @@ -965,8 +1000,8 @@ static struct nf_hook_ops br_nf_ops[] __read_mostly = { #ifdef CONFIG_SYSCTL static -int brnf_sysctl_call_tables(ctl_table * ctl, int write, - void __user * buffer, size_t * lenp, loff_t * ppos) +int brnf_sysctl_call_tables(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) { int ret; @@ -977,7 +1012,7 @@ int brnf_sysctl_call_tables(ctl_table * ctl, int write, return ret; } -static ctl_table brnf_table[] = { +static struct ctl_table brnf_table[] = { { .procname = "bridge-nf-call-arptables", .data = &brnf_call_arptables, @@ -1013,12 +1048,13 @@ static ctl_table brnf_table[] = { .mode = 0644, .proc_handler = brnf_sysctl_call_tables, }, - { } -}; - -static struct ctl_path brnf_path[] = { - { .procname = "net", }, - { .procname = "bridge", }, + { + .procname = "bridge-nf-pass-vlan-input-dev", + .data = &brnf_pass_vlan_indev, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = brnf_sysctl_call_tables, + }, { } }; #endif @@ -1027,15 +1063,22 @@ int __init br_netfilter_init(void) { int ret; - ret = nf_register_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops)); + ret = dst_entries_init(&fake_dst_ops); if (ret < 0) return ret; + + ret = nf_register_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops)); + if (ret < 0) { + dst_entries_destroy(&fake_dst_ops); + return ret; + } #ifdef CONFIG_SYSCTL - brnf_sysctl_header = register_sysctl_paths(brnf_path, brnf_table); + brnf_sysctl_header = register_net_sysctl(&init_net, "net/bridge", brnf_table); if (brnf_sysctl_header == NULL) { printk(KERN_WARNING "br_netfilter: can't register to sysctl.\n"); nf_unregister_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops)); + dst_entries_destroy(&fake_dst_ops); return -ENOMEM; } #endif @@ -1047,6 +1090,7 @@ void br_netfilter_fini(void) { nf_unregister_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops)); #ifdef CONFIG_SYSCTL - unregister_sysctl_table(brnf_sysctl_header); + unregister_net_sysctl_table(brnf_sysctl_header); #endif + dst_entries_destroy(&fake_dst_ops); } diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index fcffb3fb117..26edb518b83 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -11,38 +11,82 @@ */ #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 "br_private.h" +#include "br_private_stp.h" + +static inline size_t br_port_info_size(void) +{ + return nla_total_size(1) /* IFLA_BRPORT_STATE */ + + nla_total_size(2) /* IFLA_BRPORT_PRIORITY */ + + nla_total_size(4) /* IFLA_BRPORT_COST */ + + nla_total_size(1) /* IFLA_BRPORT_MODE */ + + 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_LEARNING */ + + nla_total_size(1) /* IFLA_BRPORT_UNICAST_FLOOD */ + + 0; +} static inline size_t br_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct ifinfomsg)) - + nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */ - + nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */ - + nla_total_size(4) /* IFLA_MASTER */ - + nla_total_size(4) /* IFLA_MTU */ - + nla_total_size(4) /* IFLA_LINK */ - + nla_total_size(1) /* IFLA_OPERSTATE */ - + nla_total_size(1); /* IFLA_PROTINFO */ + + nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */ + + nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */ + + nla_total_size(4) /* IFLA_MASTER */ + + nla_total_size(4) /* IFLA_MTU */ + + nla_total_size(4) /* IFLA_LINK */ + + nla_total_size(1) /* IFLA_OPERSTATE */ + + nla_total_size(br_port_info_size()); /* IFLA_PROTINFO */ +} + +static int br_port_fill_attrs(struct sk_buff *skb, + const struct net_bridge_port *p) +{ + u8 mode = !!(p->flags & BR_HAIRPIN_MODE); + + if (nla_put_u8(skb, IFLA_BRPORT_STATE, p->state) || + nla_put_u16(skb, IFLA_BRPORT_PRIORITY, p->priority) || + nla_put_u32(skb, IFLA_BRPORT_COST, p->path_cost) || + nla_put_u8(skb, IFLA_BRPORT_MODE, mode) || + nla_put_u8(skb, IFLA_BRPORT_GUARD, !!(p->flags & BR_BPDU_GUARD)) || + nla_put_u8(skb, IFLA_BRPORT_PROTECT, !!(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_LEARNING, !!(p->flags & BR_LEARNING)) || + nla_put_u8(skb, IFLA_BRPORT_UNICAST_FLOOD, !!(p->flags & BR_FLOOD))) + return -EMSGSIZE; + + return 0; } /* * Create one netlink message for one interface * Contains port and master info as well as carrier and bridge state. */ -static int br_fill_ifinfo(struct sk_buff *skb, const struct net_bridge_port *port, - u32 pid, u32 seq, int event, unsigned int flags) +static int br_fill_ifinfo(struct sk_buff *skb, + const struct net_bridge_port *port, + u32 pid, u32 seq, int event, unsigned int flags, + u32 filter_mask, const struct net_device *dev) { - const struct net_bridge *br = port->br; - const struct net_device *dev = port->dev; + const struct net_bridge *br; struct ifinfomsg *hdr; struct nlmsghdr *nlh; u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN; - pr_debug("br_fill_info event %d port %s master %s\n", - event, dev->name, br->dev->name); + if (port) + br = port->br; + else + br = netdev_priv(dev); + + br_debug(br, "br_fill_info event %d port %s master %s\n", + event, dev->name, br->dev->name); nlh = nlmsg_put(skb, pid, seq, event, sizeof(*hdr), flags); if (nlh == NULL) @@ -56,20 +100,64 @@ static int br_fill_ifinfo(struct sk_buff *skb, const struct net_bridge_port *por hdr->ifi_flags = dev_get_flags(dev); hdr->ifi_change = 0; - NLA_PUT_STRING(skb, IFLA_IFNAME, dev->name); - NLA_PUT_U32(skb, IFLA_MASTER, br->dev->ifindex); - NLA_PUT_U32(skb, IFLA_MTU, dev->mtu); - NLA_PUT_U8(skb, IFLA_OPERSTATE, operstate); - - if (dev->addr_len) - NLA_PUT(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr); - - if (dev->ifindex != dev->iflink) - NLA_PUT_U32(skb, IFLA_LINK, dev->iflink); + if (nla_put_string(skb, IFLA_IFNAME, dev->name) || + nla_put_u32(skb, IFLA_MASTER, br->dev->ifindex) || + nla_put_u32(skb, IFLA_MTU, dev->mtu) || + nla_put_u8(skb, IFLA_OPERSTATE, operstate) || + (dev->addr_len && + nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) || + (dev->ifindex != dev->iflink && + nla_put_u32(skb, IFLA_LINK, dev->iflink))) + goto nla_put_failure; + + if (event == RTM_NEWLINK && port) { + struct nlattr *nest + = nla_nest_start(skb, IFLA_PROTINFO | NLA_F_NESTED); + + if (nest == NULL || br_port_fill_attrs(skb, port) < 0) + goto nla_put_failure; + nla_nest_end(skb, nest); + } - if (event == RTM_NEWLINK) - NLA_PUT_U8(skb, IFLA_PROTINFO, port->state); + /* Check if the VID information is requested */ + if (filter_mask & RTEXT_FILTER_BRVLAN) { + struct nlattr *af; + const struct net_port_vlans *pv; + struct bridge_vlan_info vinfo; + u16 vid; + u16 pvid; + + if (port) + pv = nbp_get_vlan_info(port); + else + pv = br_get_vlan_info(br); + + if (!pv || bitmap_empty(pv->vlan_bitmap, VLAN_N_VID)) + goto done; + + af = nla_nest_start(skb, IFLA_AF_SPEC); + if (!af) + goto nla_put_failure; + + pvid = br_get_pvid(pv); + for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { + vinfo.vid = vid; + vinfo.flags = 0; + if (vid == pvid) + vinfo.flags |= BRIDGE_VLAN_INFO_PVID; + + if (test_bit(vid, pv->untagged_bitmap)) + vinfo.flags |= BRIDGE_VLAN_INFO_UNTAGGED; + + if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, + sizeof(vinfo), &vinfo)) + goto nla_put_failure; + } + + nla_nest_end(skb, af); + } +done: return nlmsg_end(skb, nlh); nla_put_failure: @@ -82,16 +170,22 @@ nla_put_failure: */ void br_ifinfo_notify(int event, struct net_bridge_port *port) { - struct net *net = dev_net(port->dev); + struct net *net; struct sk_buff *skb; int err = -ENOBUFS; - pr_debug("bridge notify event=%d\n", event); + if (!port) + return; + + net = dev_net(port->dev); + br_debug(port->br, "port %u(%s) event %d\n", + (unsigned int)port->port_no, port->dev->name, event); + skb = nlmsg_new(br_nlmsg_size(), GFP_ATOMIC); if (skb == NULL) goto errout; - err = br_fill_ifinfo(skb, port, 0, 0, event, 0); + err = br_fill_ifinfo(skb, port, 0, 0, event, 0, 0, port->dev); if (err < 0) { /* -EMSGSIZE implies BUG in br_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); @@ -101,101 +195,327 @@ void br_ifinfo_notify(int event, struct net_bridge_port *port) rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC); return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_LINK, err); + rtnl_set_sk_err(net, RTNLGRP_LINK, err); } + /* * Dump information about all ports, in response to GETLINK */ -static int br_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) +int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, + struct net_device *dev, u32 filter_mask) { - struct net *net = sock_net(skb->sk); - struct net_device *dev; - int idx; + int err = 0; + struct net_bridge_port *port = br_port_get_rtnl(dev); + + /* not a bridge port and */ + if (!port && !(filter_mask & RTEXT_FILTER_BRVLAN)) + goto out; + + err = br_fill_ifinfo(skb, port, pid, seq, RTM_NEWLINK, NLM_F_MULTI, + filter_mask, dev); +out: + return err; +} + +static const struct nla_policy ifla_br_policy[IFLA_MAX+1] = { + [IFLA_BRIDGE_FLAGS] = { .type = NLA_U16 }, + [IFLA_BRIDGE_MODE] = { .type = NLA_U16 }, + [IFLA_BRIDGE_VLAN_INFO] = { .type = NLA_BINARY, + .len = sizeof(struct bridge_vlan_info), }, +}; + +static int br_afspec(struct net_bridge *br, + struct net_bridge_port *p, + struct nlattr *af_spec, + int cmd) +{ + struct nlattr *tb[IFLA_BRIDGE_MAX+1]; + int err = 0; + + err = nla_parse_nested(tb, IFLA_BRIDGE_MAX, af_spec, ifla_br_policy); + if (err) + return err; - idx = 0; - for_each_netdev(net, dev) { - /* not a bridge port */ - if (dev->br_port == NULL || idx < cb->args[0]) - goto skip; + if (tb[IFLA_BRIDGE_VLAN_INFO]) { + struct bridge_vlan_info *vinfo; - if (br_fill_ifinfo(skb, dev->br_port, NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, RTM_NEWLINK, - NLM_F_MULTI) < 0) + vinfo = nla_data(tb[IFLA_BRIDGE_VLAN_INFO]); + + if (!vinfo->vid || vinfo->vid >= VLAN_VID_MASK) + return -EINVAL; + + switch (cmd) { + case RTM_SETLINK: + if (p) { + err = nbp_vlan_add(p, vinfo->vid, vinfo->flags); + if (err) + break; + + if (vinfo->flags & BRIDGE_VLAN_INFO_MASTER) + err = br_vlan_add(p->br, vinfo->vid, + vinfo->flags); + } else + err = br_vlan_add(br, vinfo->vid, vinfo->flags); + + if (err) + break; + + break; + + case RTM_DELLINK: + if (p) { + nbp_vlan_delete(p, vinfo->vid); + if (vinfo->flags & BRIDGE_VLAN_INFO_MASTER) + br_vlan_delete(p->br, vinfo->vid); + } else + br_vlan_delete(br, vinfo->vid); break; -skip: - ++idx; + } } - cb->args[0] = idx; + return err; +} + +static const struct nla_policy ifla_brport_policy[IFLA_BRPORT_MAX + 1] = { + [IFLA_BRPORT_STATE] = { .type = NLA_U8 }, + [IFLA_BRPORT_COST] = { .type = NLA_U32 }, + [IFLA_BRPORT_PRIORITY] = { .type = NLA_U16 }, + [IFLA_BRPORT_MODE] = { .type = NLA_U8 }, + [IFLA_BRPORT_GUARD] = { .type = NLA_U8 }, + [IFLA_BRPORT_PROTECT] = { .type = NLA_U8 }, + [IFLA_BRPORT_LEARNING] = { .type = NLA_U8 }, + [IFLA_BRPORT_UNICAST_FLOOD] = { .type = NLA_U8 }, +}; + +/* Change the state of the port and notify spanning tree */ +static int br_set_port_state(struct net_bridge_port *p, u8 state) +{ + if (state > BR_STATE_BLOCKING) + return -EINVAL; - return skb->len; + /* if kernel STP is running, don't allow changes */ + if (p->br->stp_enabled == BR_KERNEL_STP) + return -EBUSY; + + /* if device is not up, change is not allowed + * if link is not present, only allowable state is disabled + */ + if (!netif_running(p->dev) || + (!netif_oper_up(p->dev) && state != BR_STATE_DISABLED)) + return -ENETDOWN; + + p->state = state; + br_log_state(p); + br_port_state_selection(p->br); + return 0; } -/* - * Change state of port (ie from forwarding to blocking etc) - * Used by spanning tree in user space. - */ -static int br_rtm_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +/* Set/clear or port flags based on attribute */ +static void br_set_port_flag(struct net_bridge_port *p, struct nlattr *tb[], + int attrtype, unsigned long mask) +{ + if (tb[attrtype]) { + u8 flag = nla_get_u8(tb[attrtype]); + if (flag) + p->flags |= mask; + else + p->flags &= ~mask; + } +} + +/* 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; + + br_set_port_flag(p, tb, IFLA_BRPORT_MODE, BR_HAIRPIN_MODE); + br_set_port_flag(p, tb, IFLA_BRPORT_GUARD, BR_BPDU_GUARD); + br_set_port_flag(p, tb, IFLA_BRPORT_FAST_LEAVE, BR_MULTICAST_FAST_LEAVE); + br_set_port_flag(p, tb, IFLA_BRPORT_PROTECT, BR_ROOT_BLOCK); + br_set_port_flag(p, tb, IFLA_BRPORT_LEARNING, BR_LEARNING); + br_set_port_flag(p, tb, IFLA_BRPORT_UNICAST_FLOOD, BR_FLOOD); + + if (tb[IFLA_BRPORT_COST]) { + err = br_stp_set_path_cost(p, nla_get_u32(tb[IFLA_BRPORT_COST])); + if (err) + return err; + } + + if (tb[IFLA_BRPORT_PRIORITY]) { + err = br_stp_set_port_priority(p, nla_get_u16(tb[IFLA_BRPORT_PRIORITY])); + if (err) + return err; + } + + if (tb[IFLA_BRPORT_STATE]) { + err = br_set_port_state(p, nla_get_u8(tb[IFLA_BRPORT_STATE])); + if (err) + return err; + } + + br_port_flags_change(p, old_flags ^ p->flags); + return 0; +} + +/* Change state and parameters on port. */ +int br_setlink(struct net_device *dev, struct nlmsghdr *nlh) { - struct net *net = sock_net(skb->sk); - struct ifinfomsg *ifm; struct nlattr *protinfo; - struct net_device *dev; + struct nlattr *afspec; struct net_bridge_port *p; - u8 new_state; - - if (nlmsg_len(nlh) < sizeof(*ifm)) + struct nlattr *tb[IFLA_BRPORT_MAX + 1]; + int err = 0; + + protinfo = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_PROTINFO); + afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); + if (!protinfo && !afspec) + return 0; + + p = br_port_get_rtnl(dev); + /* We want to accept dev as bridge itself if the AF_SPEC + * is set to see if someone is setting vlan info on the bridge + */ + if (!p && !afspec) return -EINVAL; - ifm = nlmsg_data(nlh); - if (ifm->ifi_family != AF_BRIDGE) - return -EPFNOSUPPORT; + if (p && protinfo) { + if (protinfo->nla_type & NLA_F_NESTED) { + err = nla_parse_nested(tb, IFLA_BRPORT_MAX, + protinfo, ifla_brport_policy); + if (err) + return err; + + spin_lock_bh(&p->br->lock); + err = br_setport(p, tb); + spin_unlock_bh(&p->br->lock); + } else { + /* Binary compatibility with old RSTP */ + if (nla_len(protinfo) < sizeof(u8)) + return -EINVAL; + + spin_lock_bh(&p->br->lock); + err = br_set_port_state(p, nla_get_u8(protinfo)); + spin_unlock_bh(&p->br->lock); + } + if (err) + goto out; + } - protinfo = nlmsg_find_attr(nlh, sizeof(*ifm), IFLA_PROTINFO); - if (!protinfo || nla_len(protinfo) < sizeof(u8)) - return -EINVAL; + if (afspec) { + err = br_afspec((struct net_bridge *)netdev_priv(dev), p, + afspec, RTM_SETLINK); + } - new_state = nla_get_u8(protinfo); - if (new_state > BR_STATE_BLOCKING) - return -EINVAL; + if (err == 0) + br_ifinfo_notify(RTM_NEWLINK, p); - dev = __dev_get_by_index(net, ifm->ifi_index); - if (!dev) - return -ENODEV; +out: + return err; +} - p = dev->br_port; - if (!p) +/* Delete port information */ +int br_dellink(struct net_device *dev, struct nlmsghdr *nlh) +{ + struct nlattr *afspec; + struct net_bridge_port *p; + int err; + + afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); + if (!afspec) + return 0; + + p = br_port_get_rtnl(dev); + /* We want to accept dev as bridge itself as well */ + if (!p && !(dev->priv_flags & IFF_EBRIDGE)) return -EINVAL; - /* if kernel STP is running, don't allow changes */ - if (p->br->stp_enabled == BR_KERNEL_STP) - return -EBUSY; + err = br_afspec((struct net_bridge *)netdev_priv(dev), p, + afspec, RTM_DELLINK); - if (!netif_running(dev) || - (!netif_carrier_ok(dev) && new_state != BR_STATE_DISABLED)) - return -ENETDOWN; + return err; +} +static int br_validate(struct nlattr *tb[], struct nlattr *data[]) +{ + if (tb[IFLA_ADDRESS]) { + if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) + return -EINVAL; + if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) + return -EADDRNOTAVAIL; + } - p->state = new_state; - br_log_state(p); return 0; } +static int br_dev_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[]) +{ + struct net_bridge *br = netdev_priv(dev); + + if (tb[IFLA_ADDRESS]) { + spin_lock_bh(&br->lock); + br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS])); + spin_unlock_bh(&br->lock); + } + + return register_netdevice(dev); +} + +static size_t br_get_link_af_size(const struct net_device *dev) +{ + struct net_port_vlans *pv; + + if (br_port_exists(dev)) + pv = nbp_get_vlan_info(br_port_get_rtnl(dev)); + else if (dev->priv_flags & IFF_EBRIDGE) + pv = br_get_vlan_info((struct net_bridge *)netdev_priv(dev)); + else + return 0; + + if (!pv) + return 0; + + /* Each VLAN is returned in bridge_vlan_info along with flags */ + return pv->num_vlans * nla_total_size(sizeof(struct bridge_vlan_info)); +} + +static struct rtnl_af_ops br_af_ops = { + .family = AF_BRIDGE, + .get_link_af_size = br_get_link_af_size, +}; + +struct rtnl_link_ops br_link_ops __read_mostly = { + .kind = "bridge", + .priv_size = sizeof(struct net_bridge), + .setup = br_dev_setup, + .validate = br_validate, + .newlink = br_dev_newlink, + .dellink = br_dev_delete, +}; int __init br_netlink_init(void) { - if (__rtnl_register(PF_BRIDGE, RTM_GETLINK, NULL, br_dump_ifinfo)) - return -ENOBUFS; + int err; + + br_mdb_init(); + rtnl_af_register(&br_af_ops); - /* Only the first call to __rtnl_register can fail */ - __rtnl_register(PF_BRIDGE, RTM_SETLINK, br_rtm_setlink, NULL); + err = rtnl_link_register(&br_link_ops); + if (err) + goto out_af; return 0; + +out_af: + rtnl_af_unregister(&br_af_ops); + br_mdb_uninit(); + return err; } void __exit br_netlink_fini(void) { - rtnl_unregister_all(PF_BRIDGE); + br_mdb_uninit(); + rtnl_af_unregister(&br_af_ops); + rtnl_link_unregister(&br_link_ops); } - diff --git a/net/bridge/br_notify.c b/net/bridge/br_notify.c deleted file mode 100644 index 763a3ec292e..00000000000 --- a/net/bridge/br_notify.c +++ /dev/null @@ -1,93 +0,0 @@ -/* - * Device event handling - * Linux ethernet bridge - * - * Authors: - * Lennert Buytenhek <buytenh@gnu.org> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include <linux/kernel.h> -#include <linux/rtnetlink.h> -#include <net/net_namespace.h> - -#include "br_private.h" - -static int br_device_event(struct notifier_block *unused, unsigned long event, void *ptr); - -struct notifier_block br_device_notifier = { - .notifier_call = br_device_event -}; - -/* - * Handle changes in state of network devices enslaved to a bridge. - * - * Note: don't care about up/down if bridge itself is down, because - * port state is checked when bridge is brought up. - */ -static int br_device_event(struct notifier_block *unused, unsigned long event, void *ptr) -{ - struct net_device *dev = ptr; - struct net_bridge_port *p = dev->br_port; - struct net_bridge *br; - - /* not a port of a bridge */ - if (p == NULL) - return NOTIFY_DONE; - - br = p->br; - - switch (event) { - case NETDEV_CHANGEMTU: - dev_set_mtu(br->dev, br_min_mtu(br)); - break; - - case NETDEV_CHANGEADDR: - spin_lock_bh(&br->lock); - br_fdb_changeaddr(p, dev->dev_addr); - br_stp_recalculate_bridge_id(br); - spin_unlock_bh(&br->lock); - break; - - case NETDEV_CHANGE: - br_port_carrier_check(p); - break; - - case NETDEV_FEAT_CHANGE: - spin_lock_bh(&br->lock); - if (netif_running(br->dev)) - br_features_recompute(br); - spin_unlock_bh(&br->lock); - break; - - case NETDEV_DOWN: - spin_lock_bh(&br->lock); - if (br->dev->flags & IFF_UP) - br_stp_disable_port(p); - spin_unlock_bh(&br->lock); - break; - - case NETDEV_UP: - if (netif_carrier_ok(dev) && (br->dev->flags & IFF_UP)) { - spin_lock_bh(&br->lock); - br_stp_enable_port(p); - spin_unlock_bh(&br->lock); - } - break; - - case NETDEV_UNREGISTER: - br_del_if(br, dev); - break; - } - - /* Events that may cause spanning tree to refresh */ - if (event == NETDEV_CHANGEADDR || event == NETDEV_UP || - event == NETDEV_CHANGE || event == NETDEV_DOWN) - br_ifinfo_notify(RTM_NEWLINK, p); - - return NOTIFY_DONE; -} diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 2114e45682e..23caf5b0309 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -15,7 +15,10 @@ #include <linux/netdevice.h> #include <linux/if_bridge.h> +#include <linux/netpoll.h> +#include <linux/u64_stats_sync.h> #include <net/route.h> +#include <linux/if_vlan.h> #define BR_HASH_BITS 8 #define BR_HASH_SIZE (1 << BR_HASH_BITS) @@ -24,9 +27,17 @@ #define BR_PORT_BITS 10 #define BR_MAX_PORTS (1<<BR_PORT_BITS) +#define BR_VLAN_BITMAP_LEN BITS_TO_LONGS(VLAN_N_VID) #define BR_VERSION "2.3" +/* 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 +/* The Nearest Customer Bridge Group Address, 01-80-C2-00-00-[00,0B,0C,0D,0F] */ +#define BR_GROUPFWD_8021AD 0xB801u + /* Path to usermode spanning tree program */ #define BR_STP_PROG "/sbin/bridge-stp" @@ -37,12 +48,45 @@ typedef __u16 port_id; struct bridge_id { unsigned char prio[2]; - unsigned char addr[6]; + unsigned char addr[ETH_ALEN]; }; struct mac_addr { - unsigned char addr[6]; + unsigned char addr[ETH_ALEN]; +}; + +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING +/* our own querier */ +struct bridge_mcast_own_query { + struct timer_list timer; + u32 startup_sent; +}; + +/* other querier */ +struct bridge_mcast_other_query { + struct timer_list timer; + unsigned long delay_time; +}; + +/* selected querier */ +struct bridge_mcast_querier { + struct br_ip addr; + struct net_bridge_port __rcu *port; +}; +#endif + +struct net_port_vlans { + u16 port_idx; + u16 pvid; + union { + struct net_bridge_port *port; + struct net_bridge *br; + } parent; + struct rcu_head rcu; + unsigned long vlan_bitmap[BR_VLAN_BITMAP_LEN]; + unsigned long untagged_bitmap[BR_VLAN_BITMAP_LEN]; + u16 num_vlans; }; struct net_bridge_fdb_entry @@ -51,10 +95,45 @@ struct net_bridge_fdb_entry struct net_bridge_port *dst; struct rcu_head rcu; - unsigned long ageing_timer; + unsigned long updated; + unsigned long used; mac_addr addr; unsigned char is_local; unsigned char is_static; + unsigned char added_by_user; + __u16 vlan_id; +}; + +struct net_bridge_port_group { + struct net_bridge_port *port; + struct net_bridge_port_group __rcu *next; + struct hlist_node mglist; + struct rcu_head rcu; + struct timer_list timer; + struct br_ip addr; + unsigned char state; +}; + +struct net_bridge_mdb_entry +{ + struct hlist_node hlist[2]; + struct net_bridge *br; + struct net_bridge_port_group __rcu *ports; + struct rcu_head rcu; + struct timer_list timer; + struct br_ip addr; + bool mglist; +}; + +struct net_bridge_mdb_htable +{ + struct hlist_head *mhash; + struct rcu_head rcu; + struct net_bridge_mdb_htable *old; + u32 size; + u32 max; + u32 secret; + u32 ver; }; struct net_bridge_port @@ -75,6 +154,7 @@ struct net_bridge_port bridge_id designated_bridge; u32 path_cost; u32 designated_cost; + unsigned long designated_age; struct timer_list forward_delay_timer; struct timer_list hold_timer; @@ -84,22 +164,71 @@ struct net_bridge_port unsigned long flags; #define BR_HAIRPIN_MODE 0x00000001 +#define BR_BPDU_GUARD 0x00000002 +#define BR_ROOT_BLOCK 0x00000004 +#define BR_MULTICAST_FAST_LEAVE 0x00000008 +#define BR_ADMIN_COST 0x00000010 +#define BR_LEARNING 0x00000020 +#define BR_FLOOD 0x00000040 +#define BR_AUTO_MASK (BR_FLOOD | BR_LEARNING) +#define BR_PROMISC 0x00000080 + +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + struct bridge_mcast_own_query ip4_own_query; +#if IS_ENABLED(CONFIG_IPV6) + struct bridge_mcast_own_query ip6_own_query; +#endif /* IS_ENABLED(CONFIG_IPV6) */ + unsigned char multicast_router; + struct timer_list multicast_router_timer; + struct hlist_head mglist; + struct hlist_node rlist; +#endif + +#ifdef CONFIG_SYSFS + char sysfs_name[IFNAMSIZ]; +#endif + +#ifdef CONFIG_NET_POLL_CONTROLLER + struct netpoll *np; +#endif +#ifdef CONFIG_BRIDGE_VLAN_FILTERING + struct net_port_vlans __rcu *vlan_info; +#endif }; +#define br_auto_port(p) ((p)->flags & BR_AUTO_MASK) +#define br_promisc_port(p) ((p)->flags & BR_PROMISC) + +#define br_port_exists(dev) (dev->priv_flags & IFF_BRIDGE_PORT) + +static inline struct net_bridge_port *br_port_get_rcu(const struct net_device *dev) +{ + return rcu_dereference(dev->rx_handler_data); +} + +static inline struct net_bridge_port *br_port_get_rtnl(const struct net_device *dev) +{ + return br_port_exists(dev) ? + rtnl_dereference(dev->rx_handler_data) : NULL; +} + struct net_bridge { spinlock_t lock; struct list_head port_list; struct net_device *dev; + + struct pcpu_sw_netstats __percpu *stats; spinlock_t hash_lock; struct hlist_head hash[BR_HASH_SIZE]; - struct list_head age_list; - unsigned long feature_mask; #ifdef CONFIG_BRIDGE_NETFILTER struct rtable fake_rtable; + bool nf_call_iptables; + bool nf_call_ip6tables; + bool nf_call_arptables; #endif - unsigned long flags; -#define BR_SET_MAC_ADDR 0x00000001 + u16 group_fwd_mask; + u16 group_fwd_mask_required; /* STP */ bridge_id designated_root; @@ -114,6 +243,7 @@ struct net_bridge unsigned long bridge_forward_delay; u8 group_addr[ETH_ALEN]; + bool group_addr_set; u16 root_port; enum { @@ -125,15 +255,84 @@ struct net_bridge unsigned char topology_change; unsigned char topology_change_detected; +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + unsigned char multicast_router; + + u8 multicast_disabled:1; + u8 multicast_querier:1; + u8 multicast_query_use_ifaddr:1; + + u32 hash_elasticity; + u32 hash_max; + + u32 multicast_last_member_count; + u32 multicast_startup_query_count; + + unsigned long multicast_last_member_interval; + unsigned long multicast_membership_interval; + unsigned long multicast_querier_interval; + unsigned long multicast_query_interval; + unsigned long multicast_query_response_interval; + unsigned long multicast_startup_query_interval; + + spinlock_t multicast_lock; + struct net_bridge_mdb_htable __rcu *mdb; + struct hlist_head router_list; + + struct timer_list multicast_router_timer; + struct bridge_mcast_other_query ip4_other_query; + struct bridge_mcast_own_query ip4_own_query; + struct bridge_mcast_querier ip4_querier; +#if IS_ENABLED(CONFIG_IPV6) + struct bridge_mcast_other_query ip6_other_query; + struct bridge_mcast_own_query ip6_own_query; + struct bridge_mcast_querier ip6_querier; +#endif /* IS_ENABLED(CONFIG_IPV6) */ +#endif + struct timer_list hello_timer; struct timer_list tcn_timer; struct timer_list topology_change_timer; struct timer_list gc_timer; struct kobject *ifobj; + u32 auto_cnt; +#ifdef CONFIG_BRIDGE_VLAN_FILTERING + u8 vlan_enabled; + __be16 vlan_proto; + struct net_port_vlans __rcu *vlan_info; +#endif +}; + +struct br_input_skb_cb { + struct net_device *brdev; +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + int igmp; + int mrouters_only; +#endif }; -extern struct notifier_block br_device_notifier; -extern const u8 br_group_address[ETH_ALEN]; +#define BR_INPUT_SKB_CB(__skb) ((struct br_input_skb_cb *)(__skb)->cb) + +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING +# define BR_INPUT_SKB_CB_MROUTERS_ONLY(__skb) (BR_INPUT_SKB_CB(__skb)->mrouters_only) +#else +# define BR_INPUT_SKB_CB_MROUTERS_ONLY(__skb) (0) +#endif + +#define br_printk(level, br, format, args...) \ + printk(level "%s: " format, (br)->dev->name, ##args) + +#define br_err(__br, format, args...) \ + br_printk(KERN_ERR, __br, format, ##args) +#define br_warn(__br, format, args...) \ + br_printk(KERN_WARNING, __br, format, ##args) +#define br_notice(__br, format, args...) \ + br_printk(KERN_NOTICE, __br, format, ##args) +#define br_info(__br, format, args...) \ + br_printk(KERN_INFO, __br, format, ##args) + +#define br_debug(br, format, args...) \ + pr_debug("%s: " format, (br)->dev->name, ##args) /* called under bridge lock */ static inline int br_is_root_bridge(const struct net_bridge *br) @@ -142,130 +341,492 @@ static inline int br_is_root_bridge(const struct net_bridge *br) } /* br_device.c */ -extern void br_dev_setup(struct net_device *dev); -extern netdev_tx_t br_dev_xmit(struct sk_buff *skb, - struct net_device *dev); +void br_dev_setup(struct net_device *dev); +void br_dev_delete(struct net_device *dev, struct list_head *list); +netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev); +#ifdef CONFIG_NET_POLL_CONTROLLER +static inline void br_netpoll_send_skb(const struct net_bridge_port *p, + struct sk_buff *skb) +{ + struct netpoll *np = p->np; + + if (np) + netpoll_send_skb(np, skb); +} + +int br_netpoll_enable(struct net_bridge_port *p); +void br_netpoll_disable(struct net_bridge_port *p); +#else +static inline void br_netpoll_send_skb(const struct net_bridge_port *p, + struct sk_buff *skb) +{ +} + +static inline int br_netpoll_enable(struct net_bridge_port *p) +{ + return 0; +} + +static inline void br_netpoll_disable(struct net_bridge_port *p) +{ +} +#endif /* br_fdb.c */ -extern int br_fdb_init(void); -extern void br_fdb_fini(void); -extern void br_fdb_flush(struct net_bridge *br); -extern void br_fdb_changeaddr(struct net_bridge_port *p, - const unsigned char *newaddr); -extern void br_fdb_cleanup(unsigned long arg); -extern void br_fdb_delete_by_port(struct net_bridge *br, - const struct net_bridge_port *p, int do_all); -extern struct net_bridge_fdb_entry *__br_fdb_get(struct net_bridge *br, - const unsigned char *addr); -extern int br_fdb_test_addr(struct net_device *dev, unsigned char *addr); -extern int br_fdb_fillbuf(struct net_bridge *br, void *buf, - unsigned long count, unsigned long off); -extern int br_fdb_insert(struct net_bridge *br, - struct net_bridge_port *source, - const unsigned char *addr); -extern void br_fdb_update(struct net_bridge *br, - struct net_bridge_port *source, - const unsigned char *addr); +int br_fdb_init(void); +void br_fdb_fini(void); +void br_fdb_flush(struct net_bridge *br); +void br_fdb_find_delete_local(struct net_bridge *br, + const struct net_bridge_port *p, + 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_delete_by_port(struct net_bridge *br, + const struct net_bridge_port *p, 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); +int br_fdb_fillbuf(struct net_bridge *br, void *buf, unsigned long count, + unsigned long off); +int br_fdb_insert(struct net_bridge *br, struct net_bridge_port *source, + const unsigned char *addr, u16 vid); +void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, + const unsigned char *addr, u16 vid, bool added_by_user); + +int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], + struct net_device *dev, const unsigned char *addr); +int br_fdb_add(struct ndmsg *nlh, struct nlattr *tb[], struct net_device *dev, + const unsigned char *addr, u16 nlh_flags); +int br_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, + struct net_device *dev, int idx); +int br_fdb_sync_static(struct net_bridge *br, struct net_bridge_port *p); +void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p); /* br_forward.c */ -extern void br_deliver(const struct net_bridge_port *to, - struct sk_buff *skb); -extern int br_dev_queue_push_xmit(struct sk_buff *skb); -extern void br_forward(const struct net_bridge_port *to, - struct sk_buff *skb); -extern int br_forward_finish(struct sk_buff *skb); -extern void br_flood_deliver(struct net_bridge *br, struct sk_buff *skb); -extern void br_flood_forward(struct net_bridge *br, struct sk_buff *skb); +void br_deliver(const struct net_bridge_port *to, struct sk_buff *skb); +int br_dev_queue_push_xmit(struct sk_buff *skb); +void br_forward(const struct net_bridge_port *to, + struct sk_buff *skb, struct sk_buff *skb0); +int br_forward_finish(struct sk_buff *skb); +void br_flood_deliver(struct net_bridge *br, struct sk_buff *skb, bool unicast); +void br_flood_forward(struct net_bridge *br, struct sk_buff *skb, + struct sk_buff *skb2, bool unicast); /* br_if.c */ -extern void br_port_carrier_check(struct net_bridge_port *p); -extern int br_add_bridge(struct net *net, const char *name); -extern int br_del_bridge(struct net *net, const char *name); -extern void br_net_exit(struct net *net); -extern int br_add_if(struct net_bridge *br, - struct net_device *dev); -extern int br_del_if(struct net_bridge *br, - struct net_device *dev); -extern int br_min_mtu(const struct net_bridge *br); -extern void br_features_recompute(struct net_bridge *br); +void br_port_carrier_check(struct net_bridge_port *p); +int br_add_bridge(struct net *net, const char *name); +int br_del_bridge(struct net *net, const char *name); +int br_add_if(struct net_bridge *br, struct net_device *dev); +int br_del_if(struct net_bridge *br, struct net_device *dev); +int br_min_mtu(const struct net_bridge *br); +netdev_features_t br_features_recompute(struct net_bridge *br, + netdev_features_t features); +void br_port_flags_change(struct net_bridge_port *port, unsigned long mask); +void br_manage_promisc(struct net_bridge *br); /* br_input.c */ -extern int br_handle_frame_finish(struct sk_buff *skb); -extern struct sk_buff *br_handle_frame(struct net_bridge_port *p, - struct sk_buff *skb); +int br_handle_frame_finish(struct sk_buff *skb); +rx_handler_result_t br_handle_frame(struct sk_buff **pskb); + +static inline bool br_rx_handler_check_rcu(const struct net_device *dev) +{ + return rcu_dereference(dev->rx_handler) == br_handle_frame; +} + +static inline struct net_bridge_port *br_port_get_check_rcu(const struct net_device *dev) +{ + return br_rx_handler_check_rcu(dev) ? br_port_get_rcu(dev) : NULL; +} /* br_ioctl.c */ -extern int br_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd); -extern int br_ioctl_deviceless_stub(struct net *net, unsigned int cmd, void __user *arg); +int br_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd); +int br_ioctl_deviceless_stub(struct net *net, unsigned int cmd, + void __user *arg); + +/* br_multicast.c */ +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING +extern unsigned int br_mdb_rehash_seq; +int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port, + struct sk_buff *skb, u16 vid); +struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br, + struct sk_buff *skb, u16 vid); +void br_multicast_add_port(struct net_bridge_port *port); +void br_multicast_del_port(struct net_bridge_port *port); +void br_multicast_enable_port(struct net_bridge_port *port); +void br_multicast_disable_port(struct net_bridge_port *port); +void br_multicast_init(struct net_bridge *br); +void br_multicast_open(struct net_bridge *br); +void br_multicast_stop(struct net_bridge *br); +void br_multicast_deliver(struct net_bridge_mdb_entry *mdst, + struct sk_buff *skb); +void br_multicast_forward(struct net_bridge_mdb_entry *mdst, + struct sk_buff *skb, struct sk_buff *skb2); +int br_multicast_set_router(struct net_bridge *br, unsigned long val); +int br_multicast_set_port_router(struct net_bridge_port *p, unsigned long val); +int br_multicast_toggle(struct net_bridge *br, unsigned long val); +int br_multicast_set_querier(struct net_bridge *br, unsigned long val); +int br_multicast_set_hash_max(struct net_bridge *br, unsigned long val); +struct net_bridge_mdb_entry * +br_mdb_ip_get(struct net_bridge_mdb_htable *mdb, struct br_ip *dst); +struct net_bridge_mdb_entry * +br_multicast_new_group(struct net_bridge *br, struct net_bridge_port *port, + struct br_ip *group); +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 state); +void br_mdb_init(void); +void br_mdb_uninit(void); +void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port, + struct br_ip *group, int type); + +#define mlock_dereference(X, br) \ + rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock)) + +static inline bool br_multicast_is_router(struct net_bridge *br) +{ + return br->multicast_router == 2 || + (br->multicast_router == 1 && + timer_pending(&br->multicast_router_timer)); +} + +static inline bool +__br_multicast_querier_exists(struct net_bridge *br, + struct bridge_mcast_other_query *querier) +{ + return time_is_before_jiffies(querier->delay_time) && + (br->multicast_querier || timer_pending(&querier->timer)); +} + +static inline bool br_multicast_querier_exists(struct net_bridge *br, + struct ethhdr *eth) +{ + switch (eth->h_proto) { + case (htons(ETH_P_IP)): + return __br_multicast_querier_exists(br, &br->ip4_other_query); +#if IS_ENABLED(CONFIG_IPV6) + case (htons(ETH_P_IPV6)): + return __br_multicast_querier_exists(br, &br->ip6_other_query); +#endif + default: + return false; + } +} +#else +static inline int br_multicast_rcv(struct net_bridge *br, + struct net_bridge_port *port, + struct sk_buff *skb, + u16 vid) +{ + return 0; +} + +static inline struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br, + struct sk_buff *skb, u16 vid) +{ + return NULL; +} + +static inline void br_multicast_add_port(struct net_bridge_port *port) +{ +} + +static inline void br_multicast_del_port(struct net_bridge_port *port) +{ +} + +static inline void br_multicast_enable_port(struct net_bridge_port *port) +{ +} + +static inline void br_multicast_disable_port(struct net_bridge_port *port) +{ +} + +static inline void br_multicast_init(struct net_bridge *br) +{ +} + +static inline void br_multicast_open(struct net_bridge *br) +{ +} + +static inline void br_multicast_stop(struct net_bridge *br) +{ +} + +static inline void br_multicast_deliver(struct net_bridge_mdb_entry *mdst, + struct sk_buff *skb) +{ +} + +static inline void br_multicast_forward(struct net_bridge_mdb_entry *mdst, + struct sk_buff *skb, + struct sk_buff *skb2) +{ +} +static inline bool br_multicast_is_router(struct net_bridge *br) +{ + return 0; +} +static inline bool br_multicast_querier_exists(struct net_bridge *br, + struct ethhdr *eth) +{ + return false; +} +static inline void br_mdb_init(void) +{ +} +static inline void br_mdb_uninit(void) +{ +} +#endif + +/* br_vlan.c */ +#ifdef CONFIG_BRIDGE_VLAN_FILTERING +bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, + struct sk_buff *skb, u16 *vid); +bool br_allowed_egress(struct net_bridge *br, const struct net_port_vlans *v, + 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_port_vlans *v, + struct sk_buff *skb); +int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags); +int br_vlan_delete(struct net_bridge *br, u16 vid); +void br_vlan_flush(struct net_bridge *br); +bool br_vlan_find(struct net_bridge *br, u16 vid); +void br_recalculate_fwd_mask(struct net_bridge *br); +int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val); +int br_vlan_set_proto(struct net_bridge *br, unsigned long val); +void br_vlan_init(struct net_bridge *br); +int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags); +int nbp_vlan_delete(struct net_bridge_port *port, u16 vid); +void nbp_vlan_flush(struct net_bridge_port *port); +bool nbp_vlan_find(struct net_bridge_port *port, u16 vid); + +static inline struct net_port_vlans *br_get_vlan_info( + const struct net_bridge *br) +{ + return rcu_dereference_rtnl(br->vlan_info); +} + +static inline struct net_port_vlans *nbp_get_vlan_info( + const struct net_bridge_port *p) +{ + return rcu_dereference_rtnl(p->vlan_info); +} + +/* Since bridge now depends on 8021Q module, but the time bridge sees the + * skb, the vlan tag will always be present if the frame was tagged. + */ +static inline int br_vlan_get_tag(const struct sk_buff *skb, u16 *vid) +{ + int err = 0; + + if (vlan_tx_tag_present(skb)) + *vid = vlan_tx_tag_get(skb) & VLAN_VID_MASK; + else { + *vid = 0; + err = -EINVAL; + } + + return err; +} + +static inline u16 br_get_pvid(const struct net_port_vlans *v) +{ + /* Return just the VID if it is set, or VLAN_N_VID (invalid vid) if + * vid wasn't set + */ + smp_rmb(); + return v->pvid ?: VLAN_N_VID; +} + +static inline int br_vlan_enabled(struct net_bridge *br) +{ + return br->vlan_enabled; +} +#else +static inline bool br_allowed_ingress(struct net_bridge *br, + struct net_port_vlans *v, + struct sk_buff *skb, + u16 *vid) +{ + return true; +} + +static inline bool br_allowed_egress(struct net_bridge *br, + const struct net_port_vlans *v, + const struct sk_buff *skb) +{ + return true; +} + +static inline bool br_should_learn(struct net_bridge_port *p, + struct sk_buff *skb, u16 *vid) +{ + return true; +} + +static inline struct sk_buff *br_handle_vlan(struct net_bridge *br, + const struct net_port_vlans *v, + struct sk_buff *skb) +{ + return skb; +} + +static inline int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags) +{ + return -EOPNOTSUPP; +} + +static inline int br_vlan_delete(struct net_bridge *br, u16 vid) +{ + return -EOPNOTSUPP; +} + +static inline void br_vlan_flush(struct net_bridge *br) +{ +} + +static inline bool br_vlan_find(struct net_bridge *br, u16 vid) +{ + return false; +} + +static inline void br_recalculate_fwd_mask(struct net_bridge *br) +{ +} + +static inline void br_vlan_init(struct net_bridge *br) +{ +} + +static inline int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags) +{ + return -EOPNOTSUPP; +} + +static inline int nbp_vlan_delete(struct net_bridge_port *port, u16 vid) +{ + return -EOPNOTSUPP; +} + +static inline void nbp_vlan_flush(struct net_bridge_port *port) +{ +} + +static inline struct net_port_vlans *br_get_vlan_info( + const struct net_bridge *br) +{ + return NULL; +} +static inline struct net_port_vlans *nbp_get_vlan_info( + const struct net_bridge_port *p) +{ + return NULL; +} + +static inline bool nbp_vlan_find(struct net_bridge_port *port, u16 vid) +{ + return false; +} + +static inline u16 br_vlan_get_tag(const struct sk_buff *skb, u16 *tag) +{ + return 0; +} +static inline u16 br_get_pvid(const struct net_port_vlans *v) +{ + return VLAN_N_VID; /* Returns invalid vid */ +} + +static inline int br_vlan_enabled(struct net_bridge *br) +{ + return 0; +} +#endif /* br_netfilter.c */ #ifdef CONFIG_BRIDGE_NETFILTER -extern int br_netfilter_init(void); -extern void br_netfilter_fini(void); -extern void br_netfilter_rtable_init(struct net_bridge *); +int br_netfilter_init(void); +void br_netfilter_fini(void); +void br_netfilter_rtable_init(struct net_bridge *); #else #define br_netfilter_init() (0) -#define br_netfilter_fini() do { } while(0) +#define br_netfilter_fini() do { } while (0) #define br_netfilter_rtable_init(x) #endif /* br_stp.c */ -extern void br_log_state(const struct net_bridge_port *p); -extern struct net_bridge_port *br_get_port(struct net_bridge *br, - u16 port_no); -extern void br_init_port(struct net_bridge_port *p); -extern void br_become_designated_port(struct net_bridge_port *p); +void br_log_state(const struct net_bridge_port *p); +struct net_bridge_port *br_get_port(struct net_bridge *br, u16 port_no); +void br_init_port(struct net_bridge_port *p); +void br_become_designated_port(struct net_bridge_port *p); + +void __br_set_forward_delay(struct net_bridge *br, unsigned long t); +int br_set_forward_delay(struct net_bridge *br, unsigned long x); +int br_set_hello_time(struct net_bridge *br, unsigned long x); +int br_set_max_age(struct net_bridge *br, unsigned long x); + /* br_stp_if.c */ -extern void br_stp_enable_bridge(struct net_bridge *br); -extern void br_stp_disable_bridge(struct net_bridge *br); -extern void br_stp_set_enabled(struct net_bridge *br, unsigned long val); -extern void br_stp_enable_port(struct net_bridge_port *p); -extern void br_stp_disable_port(struct net_bridge_port *p); -extern void br_stp_recalculate_bridge_id(struct net_bridge *br); -extern void br_stp_change_bridge_id(struct net_bridge *br, const unsigned char *a); -extern void br_stp_set_bridge_priority(struct net_bridge *br, - u16 newprio); -extern void br_stp_set_port_priority(struct net_bridge_port *p, - u8 newprio); -extern void br_stp_set_path_cost(struct net_bridge_port *p, - u32 path_cost); -extern ssize_t br_show_bridge_id(char *buf, const struct bridge_id *id); +void br_stp_enable_bridge(struct net_bridge *br); +void br_stp_disable_bridge(struct net_bridge *br); +void br_stp_set_enabled(struct net_bridge *br, unsigned long val); +void br_stp_enable_port(struct net_bridge_port *p); +void br_stp_disable_port(struct net_bridge_port *p); +bool br_stp_recalculate_bridge_id(struct net_bridge *br); +void br_stp_change_bridge_id(struct net_bridge *br, const unsigned char *a); +void br_stp_set_bridge_priority(struct net_bridge *br, u16 newprio); +int br_stp_set_port_priority(struct net_bridge_port *p, unsigned long newprio); +int br_stp_set_path_cost(struct net_bridge_port *p, unsigned long path_cost); +ssize_t br_show_bridge_id(char *buf, const struct bridge_id *id); /* br_stp_bpdu.c */ struct stp_proto; -extern void br_stp_rcv(const struct stp_proto *proto, struct sk_buff *skb, - struct net_device *dev); +void br_stp_rcv(const struct stp_proto *proto, struct sk_buff *skb, + struct net_device *dev); /* br_stp_timer.c */ -extern void br_stp_timer_init(struct net_bridge *br); -extern void br_stp_port_timer_init(struct net_bridge_port *p); -extern unsigned long br_timer_value(const struct timer_list *timer); +void br_stp_timer_init(struct net_bridge *br); +void br_stp_port_timer_init(struct net_bridge_port *p); +unsigned long br_timer_value(const struct timer_list *timer); /* br.c */ -#if defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE) +#if IS_ENABLED(CONFIG_ATM_LANE) extern int (*br_fdb_test_addr_hook)(struct net_device *dev, unsigned char *addr); #endif /* br_netlink.c */ -extern int br_netlink_init(void); -extern void br_netlink_fini(void); -extern void br_ifinfo_notify(int event, struct net_bridge_port *port); +extern struct rtnl_link_ops br_link_ops; +int br_netlink_init(void); +void br_netlink_fini(void); +void br_ifinfo_notify(int event, struct net_bridge_port *port); +int br_setlink(struct net_device *dev, struct nlmsghdr *nlmsg); +int br_dellink(struct net_device *dev, struct nlmsghdr *nlmsg); +int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, + u32 filter_mask); #ifdef CONFIG_SYSFS /* br_sysfs_if.c */ -extern struct sysfs_ops brport_sysfs_ops; -extern int br_sysfs_addif(struct net_bridge_port *p); +extern const struct sysfs_ops brport_sysfs_ops; +int br_sysfs_addif(struct net_bridge_port *p); +int br_sysfs_renameif(struct net_bridge_port *p); /* br_sysfs_br.c */ -extern int br_sysfs_addbr(struct net_device *dev); -extern void br_sysfs_delbr(struct net_device *dev); +int br_sysfs_addbr(struct net_device *dev); +void br_sysfs_delbr(struct net_device *dev); #else -#define br_sysfs_addif(p) (0) -#define br_sysfs_addbr(dev) (0) -#define br_sysfs_delbr(dev) do { } while(0) +static inline int br_sysfs_addif(struct net_bridge_port *p) { return 0; } +static inline int br_sysfs_renameif(struct net_bridge_port *p) { return 0; } +static inline int br_sysfs_addbr(struct net_device *dev) { return 0; } +static inline void br_sysfs_delbr(struct net_device *dev) { return; } #endif /* CONFIG_SYSFS */ #endif diff --git a/net/bridge/br_private_stp.h b/net/bridge/br_private_stp.h index 8b650f7fbfa..2fe910c4e17 100644 --- a/net/bridge/br_private_stp.h +++ b/net/bridge/br_private_stp.h @@ -16,10 +16,22 @@ #define BPDU_TYPE_CONFIG 0 #define BPDU_TYPE_TCN 0x80 -struct br_config_bpdu -{ - unsigned topology_change:1; - unsigned topology_change_ack:1; +/* IEEE 802.1D-1998 timer values */ +#define BR_MIN_HELLO_TIME (1*HZ) +#define BR_MAX_HELLO_TIME (10*HZ) + +#define BR_MIN_FORWARD_DELAY (2*HZ) +#define BR_MAX_FORWARD_DELAY (30*HZ) + +#define BR_MIN_MAX_AGE (6*HZ) +#define BR_MAX_MAX_AGE (40*HZ) + +#define BR_MIN_PATH_COST 1 +#define BR_MAX_PATH_COST 65535 + +struct br_config_bpdu { + unsigned int topology_change:1; + unsigned int topology_change_ack:1; bridge_id root; int root_path_cost; bridge_id bridge_id; @@ -39,18 +51,19 @@ static inline int br_is_designated_port(const struct net_bridge_port *p) /* br_stp.c */ -extern void br_become_root_bridge(struct net_bridge *br); -extern void br_config_bpdu_generation(struct net_bridge *); -extern void br_configuration_update(struct net_bridge *); -extern void br_port_state_selection(struct net_bridge *); -extern void br_received_config_bpdu(struct net_bridge_port *p, struct br_config_bpdu *bpdu); -extern void br_received_tcn_bpdu(struct net_bridge_port *p); -extern void br_transmit_config(struct net_bridge_port *p); -extern void br_transmit_tcn(struct net_bridge *br); -extern void br_topology_change_detection(struct net_bridge *br); +void br_become_root_bridge(struct net_bridge *br); +void br_config_bpdu_generation(struct net_bridge *); +void br_configuration_update(struct net_bridge *); +void br_port_state_selection(struct net_bridge *); +void br_received_config_bpdu(struct net_bridge_port *p, + const struct br_config_bpdu *bpdu); +void br_received_tcn_bpdu(struct net_bridge_port *p); +void br_transmit_config(struct net_bridge_port *p); +void br_transmit_tcn(struct net_bridge *br); +void br_topology_change_detection(struct net_bridge *br); /* br_stp_bpdu.c */ -extern void br_send_config_bpdu(struct net_bridge_port *, struct br_config_bpdu *); -extern void br_send_tcn_bpdu(struct net_bridge_port *); +void br_send_config_bpdu(struct net_bridge_port *, struct br_config_bpdu *); +void br_send_tcn_bpdu(struct net_bridge_port *); #endif diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index fd3f8d6c099..3c86f0538cb 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -17,9 +17,9 @@ #include "br_private_stp.h" /* since time values in bpdu are in jiffies and then scaled (1/256) - * before sending, make sure that is at least one. + * before sending, make sure that is at least one STP tick. */ -#define MESSAGE_AGE_INCR ((HZ < 256) ? 1 : (HZ/256)) +#define MESSAGE_AGE_INCR ((HZ / 256) + 1) static const char *const br_port_state_names[] = { [BR_STATE_DISABLED] = "disabled", @@ -31,10 +31,9 @@ static const char *const br_port_state_names[] = { void br_log_state(const struct net_bridge_port *p) { - pr_info("%s: port %d(%s) entering %s state\n", - p->br->dev->name, p->port_no, p->dev->name, + br_info(p->br, "port %u(%s) entered %s state\n", + (unsigned int) p->port_no, p->dev->name, br_port_state_names[p->state]); - } /* called under bridge lock */ @@ -101,6 +100,21 @@ static int br_should_become_root_port(const struct net_bridge_port *p, return 0; } +static void br_root_port_block(const struct net_bridge *br, + struct net_bridge_port *p) +{ + + br_notice(br, "port %u(%s) tried to become root port (blocked)", + (unsigned int) p->port_no, p->dev->name); + + p->state = BR_STATE_LISTENING; + br_log_state(p); + br_ifinfo_notify(RTM_NEWLINK, p); + + if (br->forward_delay > 0) + mod_timer(&p->forward_delay_timer, jiffies + br->forward_delay); +} + /* called under bridge lock */ static void br_root_selection(struct net_bridge *br) { @@ -108,9 +122,13 @@ static void br_root_selection(struct net_bridge *br) u16 root_port = 0; list_for_each_entry(p, &br->port_list, list) { - if (br_should_become_root_port(p, root_port)) - root_port = p->port_no; + if (!br_should_become_root_port(p, root_port)) + continue; + if (p->flags & BR_ROOT_BLOCK) + br_root_port_block(br, p); + else + root_port = p->port_no; } br->root_port = root_port; @@ -146,7 +164,6 @@ void br_transmit_config(struct net_bridge_port *p) struct br_config_bpdu bpdu; struct net_bridge *br; - if (timer_pending(&p->hold_timer)) { p->config_pending = 1; return; @@ -165,8 +182,7 @@ void br_transmit_config(struct net_bridge_port *p) else { struct net_bridge_port *root = br_get_port(br, br->root_port); - bpdu.message_age = br->max_age - - (root->message_age_timer.expires - jiffies) + bpdu.message_age = (jiffies - root->designated_age) + MESSAGE_AGE_INCR; } bpdu.max_age = br->max_age; @@ -183,20 +199,21 @@ void br_transmit_config(struct net_bridge_port *p) } /* called under bridge lock */ -static inline void br_record_config_information(struct net_bridge_port *p, - const struct br_config_bpdu *bpdu) +static void br_record_config_information(struct net_bridge_port *p, + const struct br_config_bpdu *bpdu) { p->designated_root = bpdu->root; p->designated_cost = bpdu->root_path_cost; p->designated_bridge = bpdu->bridge_id; p->designated_port = bpdu->port_id; + p->designated_age = jiffies - bpdu->message_age; mod_timer(&p->message_age_timer, jiffies - + (p->br->max_age - bpdu->message_age)); + + (bpdu->max_age - bpdu->message_age)); } /* called under bridge lock */ -static inline void br_record_config_timeout_values(struct net_bridge *br, +static void br_record_config_timeout_values(struct net_bridge *br, const struct br_config_bpdu *bpdu) { br->max_age = bpdu->max_age; @@ -208,7 +225,14 @@ static inline void br_record_config_timeout_values(struct net_bridge *br, /* called under bridge lock */ void br_transmit_tcn(struct net_bridge *br) { - br_send_tcn_bpdu(br_get_port(br, br->root_port)); + struct net_bridge_port *p; + + p = br_get_port(br, br->root_port); + if (p) + br_send_tcn_bpdu(p); + else + br_notice(br, "root port %u not found for topology notice\n", + br->root_port); } /* called under bridge lock */ @@ -255,7 +279,8 @@ static void br_designated_port_selection(struct net_bridge *br) } /* called under bridge lock */ -static int br_supersedes_port_info(struct net_bridge_port *p, struct br_config_bpdu *bpdu) +static int br_supersedes_port_info(const struct net_bridge_port *p, + const struct br_config_bpdu *bpdu) { int t; @@ -286,7 +311,7 @@ static int br_supersedes_port_info(struct net_bridge_port *p, struct br_config_b } /* called under bridge lock */ -static inline void br_topology_change_acknowledged(struct net_bridge *br) +static void br_topology_change_acknowledged(struct net_bridge *br) { br->topology_change_detected = 0; del_timer(&br->tcn_timer); @@ -300,7 +325,7 @@ void br_topology_change_detection(struct net_bridge *br) if (br->stp_enabled != BR_KERNEL_STP) return; - pr_info("%s: topology change detected, %s\n", br->dev->name, + br_info(br, "topology change detected, %s\n", isroot ? "propagating" : "sending tcn bpdu"); if (isroot) { @@ -328,7 +353,7 @@ void br_config_bpdu_generation(struct net_bridge *br) } /* called under bridge lock */ -static inline void br_reply(struct net_bridge_port *p) +static void br_reply(struct net_bridge_port *p) { br_transmit_config(p); } @@ -364,6 +389,8 @@ static void br_make_blocking(struct net_bridge_port *p) p->state = BR_STATE_BLOCKING; br_log_state(p); + br_ifinfo_notify(RTM_NEWLINK, p); + del_timer(&p->forward_delay_timer); } } @@ -376,17 +403,18 @@ static void br_make_forwarding(struct net_bridge_port *p) if (p->state != BR_STATE_BLOCKING) return; - if (br->forward_delay == 0) { + if (br->stp_enabled == BR_NO_STP || br->forward_delay == 0) { p->state = BR_STATE_FORWARDING; br_topology_change_detection(br); del_timer(&p->forward_delay_timer); - } - else if (p->br->stp_enabled == BR_KERNEL_STP) + } else if (br->stp_enabled == BR_KERNEL_STP) p->state = BR_STATE_LISTENING; else p->state = BR_STATE_LEARNING; + br_multicast_enable_port(p); br_log_state(p); + br_ifinfo_notify(RTM_NEWLINK, p); if (br->forward_delay != 0) mod_timer(&p->forward_delay_timer, jiffies + br->forward_delay); @@ -396,13 +424,14 @@ static void br_make_forwarding(struct net_bridge_port *p) void br_port_state_selection(struct net_bridge *br) { struct net_bridge_port *p; - - /* Don't change port states if userspace is handling STP */ - if (br->stp_enabled == BR_USER_STP) - return; + unsigned int liveports = 0; list_for_each_entry(p, &br->port_list, list) { - if (p->state != BR_STATE_DISABLED) { + if (p->state == BR_STATE_DISABLED) + continue; + + /* Don't change port states if userspace is handling STP */ + if (br->stp_enabled != BR_USER_STP) { if (p->port_no == br->root_port) { p->config_pending = 0; p->topology_change_ack = 0; @@ -417,18 +446,26 @@ void br_port_state_selection(struct net_bridge *br) } } + if (p->state == BR_STATE_FORWARDING) + ++liveports; } + + if (liveports == 0) + netif_carrier_off(br->dev); + else + netif_carrier_on(br->dev); } /* called under bridge lock */ -static inline void br_topology_change_acknowledge(struct net_bridge_port *p) +static void br_topology_change_acknowledge(struct net_bridge_port *p) { p->topology_change_ack = 1; br_transmit_config(p); } /* called under bridge lock */ -void br_received_config_bpdu(struct net_bridge_port *p, struct br_config_bpdu *bpdu) +void br_received_config_bpdu(struct net_bridge_port *p, + const struct br_config_bpdu *bpdu) { struct net_bridge *br; int was_root; @@ -467,10 +504,67 @@ void br_received_config_bpdu(struct net_bridge_port *p, struct br_config_bpdu *b void br_received_tcn_bpdu(struct net_bridge_port *p) { if (br_is_designated_port(p)) { - pr_info("%s: received tcn bpdu on port %i(%s)\n", - p->br->dev->name, p->port_no, p->dev->name); + br_info(p->br, "port %u(%s) received tcn bpdu\n", + (unsigned int) p->port_no, p->dev->name); br_topology_change_detection(p->br); br_topology_change_acknowledge(p); } } + +/* Change bridge STP parameter */ +int br_set_hello_time(struct net_bridge *br, unsigned long val) +{ + unsigned long t = clock_t_to_jiffies(val); + + if (t < BR_MIN_HELLO_TIME || t > BR_MAX_HELLO_TIME) + return -ERANGE; + + spin_lock_bh(&br->lock); + br->bridge_hello_time = t; + if (br_is_root_bridge(br)) + br->hello_time = br->bridge_hello_time; + spin_unlock_bh(&br->lock); + return 0; +} + +int br_set_max_age(struct net_bridge *br, unsigned long val) +{ + unsigned long t = clock_t_to_jiffies(val); + + if (t < BR_MIN_MAX_AGE || t > BR_MAX_MAX_AGE) + return -ERANGE; + + spin_lock_bh(&br->lock); + br->bridge_max_age = t; + if (br_is_root_bridge(br)) + br->max_age = br->bridge_max_age; + spin_unlock_bh(&br->lock); + return 0; + +} + +void __br_set_forward_delay(struct net_bridge *br, unsigned long t) +{ + br->bridge_forward_delay = t; + if (br_is_root_bridge(br)) + br->forward_delay = br->bridge_forward_delay; +} + +int br_set_forward_delay(struct net_bridge *br, unsigned long val) +{ + unsigned long t = clock_t_to_jiffies(val); + int err = -ERANGE; + + spin_lock_bh(&br->lock); + if (br->stp_enabled != BR_NO_STP && + (t < BR_MIN_FORWARD_DELAY || t > BR_MAX_FORWARD_DELAY)) + goto unlock; + + __br_set_forward_delay(br, t); + err = 0; + +unlock: + spin_unlock_bh(&br->lock); + return err; +} diff --git a/net/bridge/br_stp_bpdu.c b/net/bridge/br_stp_bpdu.c index 81ae40b3f65..bdb459d21ad 100644 --- a/net/bridge/br_stp_bpdu.c +++ b/net/bridge/br_stp_bpdu.c @@ -15,6 +15,8 @@ #include <linux/netfilter_bridge.h> #include <linux/etherdevice.h> #include <linux/llc.h> +#include <linux/slab.h> +#include <linux/pkt_sched.h> #include <net/net_namespace.h> #include <net/llc.h> #include <net/llc_pdu.h> @@ -39,6 +41,7 @@ static void br_send_bpdu(struct net_bridge_port *p, skb->dev = p->dev; skb->protocol = htons(ETH_P_802_2); + skb->priority = TC_PRIO_CONTROL; skb_reserve(skb, LLC_RESERVE); memcpy(__skb_put(skb, length), data, length); @@ -49,7 +52,9 @@ static void br_send_bpdu(struct net_bridge_port *p, llc_mac_hdr_init(skb, p->dev->dev_addr, p->br->group_addr); - NF_HOOK(PF_BRIDGE, NF_BR_LOCAL_OUT, skb, NULL, skb->dev, + skb_reset_mac_header(skb); + + NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, skb, NULL, skb->dev, dev_queue_xmit); } @@ -130,19 +135,16 @@ void br_send_tcn_bpdu(struct net_bridge_port *p) /* * Called from llc. * - * NO locks, but rcu_read_lock (preempt_disabled) + * NO locks, but rcu_read_lock */ void br_stp_rcv(const struct stp_proto *proto, struct sk_buff *skb, struct net_device *dev) { const unsigned char *dest = eth_hdr(skb)->h_dest; - struct net_bridge_port *p = rcu_dereference(dev->br_port); + struct net_bridge_port *p; struct net_bridge *br; const unsigned char *buf; - if (!p) - goto err; - if (!pskb_may_pull(skb, 4)) goto err; @@ -151,6 +153,10 @@ void br_stp_rcv(const struct stp_proto *proto, struct sk_buff *skb, if (buf[0] != 0 || buf[1] != 0 || buf[2] != 0) goto err; + p = br_port_get_check_rcu(dev); + if (!p) + goto err; + br = p->br; spin_lock(&br->lock); @@ -163,9 +169,16 @@ void br_stp_rcv(const struct stp_proto *proto, struct sk_buff *skb, if (p->state == BR_STATE_DISABLED) goto out; - if (compare_ether_addr(dest, br->group_addr) != 0) + if (!ether_addr_equal(dest, br->group_addr)) goto out; + if (p->flags & BR_BPDU_GUARD) { + br_notice(br, "BPDU received on blocked port %u(%s)\n", + (unsigned int) p->port_no, p->dev->name); + br_stp_disable_port(p); + goto out; + } + buf = skb_pull(skb, 3); if (buf[0] == BPDU_TYPE_CONFIG) { @@ -206,10 +219,19 @@ void br_stp_rcv(const struct stp_proto *proto, struct sk_buff *skb, bpdu.hello_time = br_get_ticks(buf+28); bpdu.forward_delay = br_get_ticks(buf+30); - br_received_config_bpdu(p, &bpdu); - } + if (bpdu.message_age > bpdu.max_age) { + if (net_ratelimit()) + br_notice(p->br, + "port %u config from %pM" + " (message_age %ul > max_age %ul)\n", + p->port_no, + eth_hdr(skb)->h_source, + bpdu.message_age, bpdu.max_age); + goto out; + } - else if (buf[0] == BPDU_TYPE_TCN) { + br_received_config_bpdu(p, &bpdu); + } else if (buf[0] == BPDU_TYPE_TCN) { br_received_tcn_bpdu(p); } out: diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index 9a52ac5b452..189ba1e7d85 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -12,6 +12,7 @@ */ #include <linux/kernel.h> +#include <linux/kmod.h> #include <linux/etherdevice.h> #include <linux/rtnetlink.h> @@ -20,7 +21,7 @@ /* Port id is composed of priority and port number. - * NB: least significant bits of priority are dropped to + * NB: some bits of priority are dropped to * make room for more ports. */ static inline port_id br_make_port_id(__u8 priority, __u16 port_no) @@ -29,6 +30,8 @@ static inline port_id br_make_port_id(__u8 priority, __u16 port_no) | (port_no & ((1<<BR_PORT_BITS)-1)); } +#define BR_MAX_PORT_PRIORITY ((u16)~0 >> BR_PORT_BITS) + /* called under bridge lock */ void br_init_port(struct net_bridge_port *p) { @@ -51,7 +54,7 @@ void br_stp_enable_bridge(struct net_bridge *br) br_config_bpdu_generation(br); list_for_each_entry(p, &br->port_list, list) { - if ((p->dev->flags & IFF_UP) && netif_carrier_ok(p->dev)) + if (netif_running(p->dev) && netif_oper_up(p->dev)) br_stp_enable_port(p); } @@ -85,29 +88,31 @@ void br_stp_enable_port(struct net_bridge_port *p) { br_init_port(p); br_port_state_selection(p->br); + br_log_state(p); + br_ifinfo_notify(RTM_NEWLINK, p); } /* called under bridge lock */ void br_stp_disable_port(struct net_bridge_port *p) { - struct net_bridge *br; + struct net_bridge *br = p->br; int wasroot; - br = p->br; - printk(KERN_INFO "%s: port %i(%s) entering %s state\n", - br->dev->name, p->port_no, p->dev->name, "disabled"); - wasroot = br_is_root_bridge(br); br_become_designated_port(p); p->state = BR_STATE_DISABLED; p->topology_change_ack = 0; p->config_pending = 0; + br_log_state(p); + br_ifinfo_notify(RTM_NEWLINK, p); + del_timer(&p->message_age_timer); del_timer(&p->forward_delay_timer); del_timer(&p->hold_timer); br_fdb_delete_by_port(br, p, 0); + br_multicast_disable_port(p); br_configuration_update(br); @@ -124,19 +129,26 @@ static void br_stp_start(struct net_bridge *br) char *envp[] = { NULL }; r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC); + + spin_lock_bh(&br->lock); + + if (br->bridge_forward_delay < BR_MIN_FORWARD_DELAY) + __br_set_forward_delay(br, BR_MIN_FORWARD_DELAY); + else if (br->bridge_forward_delay > BR_MAX_FORWARD_DELAY) + __br_set_forward_delay(br, BR_MAX_FORWARD_DELAY); + if (r == 0) { br->stp_enabled = BR_USER_STP; - printk(KERN_INFO "%s: userspace STP started\n", br->dev->name); + br_debug(br, "userspace STP started\n"); } else { br->stp_enabled = BR_KERNEL_STP; - printk(KERN_INFO "%s: starting userspace STP failed, " - "starting kernel STP\n", br->dev->name); + br_debug(br, "using kernel STP\n"); /* To start timers on any ports left in blocking */ - spin_lock_bh(&br->lock); br_port_state_selection(br); - spin_unlock_bh(&br->lock); } + + spin_unlock_bh(&br->lock); } static void br_stp_stop(struct net_bridge *br) @@ -146,10 +158,8 @@ static void br_stp_stop(struct net_bridge *br) char *envp[] = { NULL }; if (br->stp_enabled == BR_USER_STP) { - r = call_usermodehelper(BR_STP_PROG, argv, envp, 1); - printk(KERN_INFO "%s: userspace STP stopped, return code %d\n", - br->dev->name, r); - + 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 */ spin_lock_bh(&br->lock); @@ -176,7 +186,7 @@ void br_stp_set_enabled(struct net_bridge *br, unsigned long val) /* called under bridge lock */ void br_stp_change_bridge_id(struct net_bridge *br, const unsigned char *addr) { - /* should be aligned on 2 bytes for compare_ether_addr() */ + /* should be aligned on 2 bytes for ether_addr_equal() */ unsigned short oldaddr_aligned[ETH_ALEN >> 1]; unsigned char *oldaddr = (unsigned char *)oldaddr_aligned; struct net_bridge_port *p; @@ -184,17 +194,18 @@ void br_stp_change_bridge_id(struct net_bridge *br, const unsigned char *addr) wasroot = br_is_root_bridge(br); + br_fdb_change_mac_address(br, addr); + memcpy(oldaddr, br->bridge_id.addr, ETH_ALEN); memcpy(br->bridge_id.addr, addr, ETH_ALEN); memcpy(br->dev->dev_addr, addr, ETH_ALEN); list_for_each_entry(p, &br->port_list, list) { - if (!compare_ether_addr(p->designated_bridge.addr, oldaddr)) + if (ether_addr_equal(p->designated_bridge.addr, oldaddr)) memcpy(p->designated_bridge.addr, addr, ETH_ALEN); - if (!compare_ether_addr(p->designated_root.addr, oldaddr)) + if (ether_addr_equal(p->designated_root.addr, oldaddr)) memcpy(p->designated_root.addr, addr, ETH_ALEN); - } br_configuration_update(br); @@ -203,11 +214,11 @@ void br_stp_change_bridge_id(struct net_bridge *br, const unsigned char *addr) br_become_root_bridge(br); } -/* should be aligned on 2 bytes for compare_ether_addr() */ +/* should be aligned on 2 bytes for ether_addr_equal() */ static const unsigned short br_mac_zero_aligned[ETH_ALEN >> 1]; /* called under bridge lock */ -void br_stp_recalculate_bridge_id(struct net_bridge *br) +bool br_stp_recalculate_bridge_id(struct net_bridge *br) { const unsigned char *br_mac_zero = (const unsigned char *)br_mac_zero_aligned; @@ -215,8 +226,8 @@ void br_stp_recalculate_bridge_id(struct net_bridge *br) struct net_bridge_port *p; /* user has chosen a value so keep it */ - if (br->flags & BR_SET_MAC_ADDR) - return; + if (br->dev->addr_assign_type == NET_ADDR_SET) + return false; list_for_each_entry(p, &br->port_list, list) { if (addr == br_mac_zero || @@ -225,8 +236,11 @@ void br_stp_recalculate_bridge_id(struct net_bridge *br) } - if (compare_ether_addr(br->bridge_id.addr, addr)) - br_stp_change_bridge_id(br, addr); + if (ether_addr_equal(br->bridge_id.addr, addr)) + return false; /* no change */ + + br_stp_change_bridge_id(br, addr); + return true; } /* called under bridge lock */ @@ -255,10 +269,14 @@ void br_stp_set_bridge_priority(struct net_bridge *br, u16 newprio) } /* called under bridge lock */ -void br_stp_set_port_priority(struct net_bridge_port *p, u8 newprio) +int br_stp_set_port_priority(struct net_bridge_port *p, unsigned long newprio) { - port_id new_port_id = br_make_port_id(newprio, p->port_no); + port_id new_port_id; + + if (newprio > BR_MAX_PORT_PRIORITY) + return -ERANGE; + new_port_id = br_make_port_id(newprio, p->port_no); if (br_is_designated_port(p)) p->designated_port = new_port_id; @@ -269,14 +287,22 @@ void br_stp_set_port_priority(struct net_bridge_port *p, u8 newprio) br_become_designated_port(p); br_port_state_selection(p->br); } + + return 0; } /* called under bridge lock */ -void br_stp_set_path_cost(struct net_bridge_port *p, u32 path_cost) +int br_stp_set_path_cost(struct net_bridge_port *p, unsigned long path_cost) { + if (path_cost < BR_MIN_PATH_COST || + path_cost > BR_MAX_PATH_COST) + return -ERANGE; + + p->flags |= BR_ADMIN_COST; p->path_cost = path_cost; br_configuration_update(p->br); br_port_state_selection(p->br); + return 0; } ssize_t br_show_bridge_id(char *buf, const struct bridge_id *id) diff --git a/net/bridge/br_stp_timer.c b/net/bridge/br_stp_timer.c index 772a140bfdf..558c46d19e0 100644 --- a/net/bridge/br_stp_timer.c +++ b/net/bridge/br_stp_timer.c @@ -35,7 +35,7 @@ static void br_hello_timer_expired(unsigned long arg) { struct net_bridge *br = (struct net_bridge *)arg; - pr_debug("%s: hello timer expired\n", br->dev->name); + br_debug(br, "hello timer expired\n"); spin_lock(&br->lock); if (br->dev->flags & IFF_UP) { br_config_bpdu_generation(br); @@ -55,13 +55,9 @@ static void br_message_age_timer_expired(unsigned long arg) if (p->state == BR_STATE_DISABLED) return; - - pr_info("%s: neighbor %.2x%.2x.%.2x:%.2x:%.2x:%.2x:%.2x:%.2x lost on port %d(%s)\n", - br->dev->name, - id->prio[0], id->prio[1], - id->addr[0], id->addr[1], id->addr[2], - id->addr[3], id->addr[4], id->addr[5], - p->port_no, p->dev->name); + br_info(br, "port %u(%s) neighbor %.2x%.2x.%pM lost\n", + (unsigned int) p->port_no, p->dev->name, + id->prio[0], id->prio[1], &id->addr); /* * According to the spec, the message age timer cannot be @@ -87,8 +83,8 @@ static void br_forward_delay_timer_expired(unsigned long arg) struct net_bridge_port *p = (struct net_bridge_port *) arg; struct net_bridge *br = p->br; - pr_debug("%s: %d(%s) forward delay timer\n", - br->dev->name, p->port_no, p->dev->name); + br_debug(br, "port %u(%s) forward delay timer\n", + (unsigned int) p->port_no, p->dev->name); spin_lock(&br->lock); if (p->state == BR_STATE_LISTENING) { p->state = BR_STATE_LEARNING; @@ -98,8 +94,10 @@ static void br_forward_delay_timer_expired(unsigned long arg) p->state = BR_STATE_FORWARDING; if (br_is_designated_for_some_port(br)) br_topology_change_detection(br); + netif_carrier_on(br->dev); } br_log_state(p); + br_ifinfo_notify(RTM_NEWLINK, p); spin_unlock(&br->lock); } @@ -107,12 +105,12 @@ static void br_tcn_timer_expired(unsigned long arg) { struct net_bridge *br = (struct net_bridge *) arg; - pr_debug("%s: tcn timer expired\n", br->dev->name); + br_debug(br, "tcn timer expired\n"); spin_lock(&br->lock); - if (br->dev->flags & IFF_UP) { + if (!br_is_root_bridge(br) && (br->dev->flags & IFF_UP)) { br_transmit_tcn(br); - mod_timer(&br->tcn_timer,jiffies + br->bridge_hello_time); + mod_timer(&br->tcn_timer, jiffies + br->bridge_hello_time); } spin_unlock(&br->lock); } @@ -121,7 +119,7 @@ static void br_topology_change_timer_expired(unsigned long arg) { struct net_bridge *br = (struct net_bridge *) arg; - pr_debug("%s: topo change timer expired\n", br->dev->name); + br_debug(br, "topo change timer expired\n"); spin_lock(&br->lock); br->topology_change_detected = 0; br->topology_change = 0; @@ -132,8 +130,8 @@ static void br_hold_timer_expired(unsigned long arg) { struct net_bridge_port *p = (struct net_bridge_port *) arg; - pr_debug("%s: %d(%s) hold timer expired\n", - p->br->dev->name, p->port_no, p->dev->name); + br_debug(p->br, "port %u(%s) hold timer expired\n", + (unsigned int) p->port_no, p->dev->name); spin_lock(&p->br->lock); if (p->config_pending) @@ -172,5 +170,5 @@ void br_stp_port_timer_init(struct net_bridge_port *p) unsigned long br_timer_value(const struct timer_list *timer) { return timer_pending(timer) - ? jiffies_to_clock_t(timer->expires - jiffies) : 0; + ? jiffies_delta_to_clock_t(timer->expires - jiffies) : 0; } diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c index bee4f300d0c..c9e2572b15f 100644 --- a/net/bridge/br_sysfs_br.c +++ b/net/bridge/br_sysfs_br.c @@ -1,5 +1,5 @@ /* - * Sysfs attributes of bridge ports + * Sysfs attributes of bridge * Linux ethernet bridge * * Authors: @@ -14,6 +14,7 @@ #include <linux/capability.h> #include <linux/kernel.h> #include <linux/netdevice.h> +#include <linux/etherdevice.h> #include <linux/if_bridge.h> #include <linux/rtnetlink.h> #include <linux/spinlock.h> @@ -36,98 +37,63 @@ static ssize_t store_bridge_parm(struct device *d, unsigned long val; int err; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(dev_net(br->dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; val = simple_strtoul(buf, &endp, 0); if (endp == buf) return -EINVAL; - spin_lock_bh(&br->lock); err = (*set)(br, val); - spin_unlock_bh(&br->lock); return err ? err : len; } -static ssize_t show_forward_delay(struct device *d, +static ssize_t forward_delay_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%lu\n", jiffies_to_clock_t(br->forward_delay)); } -static int set_forward_delay(struct net_bridge *br, unsigned long val) -{ - unsigned long delay = clock_t_to_jiffies(val); - br->forward_delay = delay; - if (br_is_root_bridge(br)) - br->bridge_forward_delay = delay; - return 0; -} - -static ssize_t store_forward_delay(struct device *d, +static ssize_t forward_delay_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { - return store_bridge_parm(d, buf, len, set_forward_delay); + return store_bridge_parm(d, buf, len, br_set_forward_delay); } -static DEVICE_ATTR(forward_delay, S_IRUGO | S_IWUSR, - show_forward_delay, store_forward_delay); +static DEVICE_ATTR_RW(forward_delay); -static ssize_t show_hello_time(struct device *d, struct device_attribute *attr, +static ssize_t hello_time_show(struct device *d, struct device_attribute *attr, char *buf) { return sprintf(buf, "%lu\n", jiffies_to_clock_t(to_bridge(d)->hello_time)); } -static int set_hello_time(struct net_bridge *br, unsigned long val) -{ - unsigned long t = clock_t_to_jiffies(val); - - if (t < HZ) - return -EINVAL; - - br->hello_time = t; - if (br_is_root_bridge(br)) - br->bridge_hello_time = t; - return 0; -} - -static ssize_t store_hello_time(struct device *d, +static ssize_t hello_time_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { - return store_bridge_parm(d, buf, len, set_hello_time); + return store_bridge_parm(d, buf, len, br_set_hello_time); } -static DEVICE_ATTR(hello_time, S_IRUGO | S_IWUSR, show_hello_time, - store_hello_time); +static DEVICE_ATTR_RW(hello_time); -static ssize_t show_max_age(struct device *d, struct device_attribute *attr, +static ssize_t max_age_show(struct device *d, struct device_attribute *attr, char *buf) { return sprintf(buf, "%lu\n", jiffies_to_clock_t(to_bridge(d)->max_age)); } -static int set_max_age(struct net_bridge *br, unsigned long val) -{ - unsigned long t = clock_t_to_jiffies(val); - br->max_age = t; - if (br_is_root_bridge(br)) - br->bridge_max_age = t; - return 0; -} - -static ssize_t store_max_age(struct device *d, struct device_attribute *attr, +static ssize_t max_age_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { - return store_bridge_parm(d, buf, len, set_max_age); + return store_bridge_parm(d, buf, len, br_set_max_age); } -static DEVICE_ATTR(max_age, S_IRUGO | S_IWUSR, show_max_age, store_max_age); +static DEVICE_ATTR_RW(max_age); -static ssize_t show_ageing_time(struct device *d, +static ssize_t ageing_time_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); @@ -140,16 +106,15 @@ static int set_ageing_time(struct net_bridge *br, unsigned long val) return 0; } -static ssize_t store_ageing_time(struct device *d, +static ssize_t ageing_time_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_ageing_time); } -static DEVICE_ATTR(ageing_time, S_IRUGO | S_IWUSR, show_ageing_time, - store_ageing_time); +static DEVICE_ATTR_RW(ageing_time); -static ssize_t show_stp_state(struct device *d, +static ssize_t stp_state_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); @@ -157,7 +122,7 @@ static ssize_t show_stp_state(struct device *d, } -static ssize_t store_stp_state(struct device *d, +static ssize_t stp_state_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { @@ -165,7 +130,7 @@ static ssize_t store_stp_state(struct device *d, char *endp; unsigned long val; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(dev_net(br->dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; val = simple_strtoul(buf, &endp, 0); @@ -179,10 +144,43 @@ static ssize_t store_stp_state(struct device *d, return len; } -static DEVICE_ATTR(stp_state, S_IRUGO | S_IWUSR, show_stp_state, - store_stp_state); +static DEVICE_ATTR_RW(stp_state); + +static ssize_t group_fwd_mask_show(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf(buf, "%#x\n", br->group_fwd_mask); +} -static ssize_t show_priority(struct device *d, struct device_attribute *attr, + +static ssize_t group_fwd_mask_store(struct device *d, + struct device_attribute *attr, + const char *buf, + size_t len) +{ + struct net_bridge *br = to_bridge(d); + char *endp; + unsigned long val; + + if (!ns_capable(dev_net(br->dev)->user_ns, CAP_NET_ADMIN)) + return -EPERM; + + val = simple_strtoul(buf, &endp, 0); + if (endp == buf) + return -EINVAL; + + if (val & BR_GROUPFWD_RESTRICTED) + return -EINVAL; + + br->group_fwd_mask = val; + + return len; +} +static DEVICE_ATTR_RW(group_fwd_mask); + +static ssize_t priority_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); @@ -196,93 +194,91 @@ static int set_priority(struct net_bridge *br, unsigned long val) return 0; } -static ssize_t store_priority(struct device *d, struct device_attribute *attr, - const char *buf, size_t len) +static ssize_t priority_store(struct device *d, struct device_attribute *attr, + const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_priority); } -static DEVICE_ATTR(priority, S_IRUGO | S_IWUSR, show_priority, store_priority); +static DEVICE_ATTR_RW(priority); -static ssize_t show_root_id(struct device *d, struct device_attribute *attr, +static ssize_t root_id_show(struct device *d, struct device_attribute *attr, char *buf) { return br_show_bridge_id(buf, &to_bridge(d)->designated_root); } -static DEVICE_ATTR(root_id, S_IRUGO, show_root_id, NULL); +static DEVICE_ATTR_RO(root_id); -static ssize_t show_bridge_id(struct device *d, struct device_attribute *attr, +static ssize_t bridge_id_show(struct device *d, struct device_attribute *attr, char *buf) { return br_show_bridge_id(buf, &to_bridge(d)->bridge_id); } -static DEVICE_ATTR(bridge_id, S_IRUGO, show_bridge_id, NULL); +static DEVICE_ATTR_RO(bridge_id); -static ssize_t show_root_port(struct device *d, struct device_attribute *attr, +static ssize_t root_port_show(struct device *d, struct device_attribute *attr, char *buf) { return sprintf(buf, "%d\n", to_bridge(d)->root_port); } -static DEVICE_ATTR(root_port, S_IRUGO, show_root_port, NULL); +static DEVICE_ATTR_RO(root_port); -static ssize_t show_root_path_cost(struct device *d, +static ssize_t root_path_cost_show(struct device *d, struct device_attribute *attr, char *buf) { return sprintf(buf, "%d\n", to_bridge(d)->root_path_cost); } -static DEVICE_ATTR(root_path_cost, S_IRUGO, show_root_path_cost, NULL); +static DEVICE_ATTR_RO(root_path_cost); -static ssize_t show_topology_change(struct device *d, +static ssize_t topology_change_show(struct device *d, struct device_attribute *attr, char *buf) { return sprintf(buf, "%d\n", to_bridge(d)->topology_change); } -static DEVICE_ATTR(topology_change, S_IRUGO, show_topology_change, NULL); +static DEVICE_ATTR_RO(topology_change); -static ssize_t show_topology_change_detected(struct device *d, +static ssize_t topology_change_detected_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%d\n", br->topology_change_detected); } -static DEVICE_ATTR(topology_change_detected, S_IRUGO, - show_topology_change_detected, NULL); +static DEVICE_ATTR_RO(topology_change_detected); -static ssize_t show_hello_timer(struct device *d, +static ssize_t hello_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->hello_timer)); } -static DEVICE_ATTR(hello_timer, S_IRUGO, show_hello_timer, NULL); +static DEVICE_ATTR_RO(hello_timer); -static ssize_t show_tcn_timer(struct device *d, struct device_attribute *attr, +static ssize_t tcn_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->tcn_timer)); } -static DEVICE_ATTR(tcn_timer, S_IRUGO, show_tcn_timer, NULL); +static DEVICE_ATTR_RO(tcn_timer); -static ssize_t show_topology_change_timer(struct device *d, +static ssize_t topology_change_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->topology_change_timer)); } -static DEVICE_ATTR(topology_change_timer, S_IRUGO, show_topology_change_timer, - NULL); +static DEVICE_ATTR_RO(topology_change_timer); -static ssize_t show_gc_timer(struct device *d, struct device_attribute *attr, +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)); } -static DEVICE_ATTR(gc_timer, S_IRUGO, show_gc_timer, NULL); +static DEVICE_ATTR_RO(gc_timer); -static ssize_t show_group_addr(struct device *d, +static ssize_t group_addr_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); @@ -292,28 +288,23 @@ static ssize_t show_group_addr(struct device *d, br->group_addr[4], br->group_addr[5]); } -static ssize_t store_group_addr(struct device *d, +static ssize_t group_addr_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { struct net_bridge *br = to_bridge(d); - unsigned new_addr[6]; + u8 new_addr[6]; int i; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(dev_net(br->dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; - if (sscanf(buf, "%x:%x:%x:%x:%x:%x", + if (sscanf(buf, "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx", &new_addr[0], &new_addr[1], &new_addr[2], &new_addr[3], &new_addr[4], &new_addr[5]) != 6) return -EINVAL; - /* Must be 01:80:c2:00:00:0X */ - for (i = 0; i < 5; i++) - if (new_addr[i] != br_group_address[i]) - return -EINVAL; - - if (new_addr[5] & ~0xf) + if (!is_link_local_ether_addr(new_addr)) return -EINVAL; if (new_addr[5] == 1 || /* 802.3x Pause address */ @@ -321,29 +312,420 @@ static ssize_t store_group_addr(struct device *d, new_addr[5] == 3) /* 802.1X PAE address */ return -EINVAL; + if (!rtnl_trylock()) + return restart_syscall(); + spin_lock_bh(&br->lock); for (i = 0; i < 6; i++) br->group_addr[i] = new_addr[i]; spin_unlock_bh(&br->lock); + + br->group_addr_set = true; + br_recalculate_fwd_mask(br); + + rtnl_unlock(); + return len; } -static DEVICE_ATTR(group_addr, S_IRUGO | S_IWUSR, - show_group_addr, store_group_addr); +static DEVICE_ATTR_RW(group_addr); -static ssize_t store_flush(struct device *d, +static ssize_t flush_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { struct net_bridge *br = to_bridge(d); - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(dev_net(br->dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; br_fdb_flush(br); return len; } -static DEVICE_ATTR(flush, S_IWUSR, NULL, store_flush); +static DEVICE_ATTR_WO(flush); + +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING +static ssize_t multicast_router_show(struct device *d, + struct device_attribute *attr, char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf(buf, "%d\n", br->multicast_router); +} + +static ssize_t multicast_router_store(struct device *d, + struct device_attribute *attr, + const char *buf, size_t len) +{ + return store_bridge_parm(d, buf, len, br_multicast_set_router); +} +static DEVICE_ATTR_RW(multicast_router); + +static ssize_t multicast_snooping_show(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf(buf, "%d\n", !br->multicast_disabled); +} + +static ssize_t multicast_snooping_store(struct device *d, + struct device_attribute *attr, + const char *buf, size_t len) +{ + return store_bridge_parm(d, buf, len, br_multicast_toggle); +} +static DEVICE_ATTR_RW(multicast_snooping); + +static ssize_t multicast_query_use_ifaddr_show(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf(buf, "%d\n", br->multicast_query_use_ifaddr); +} + +static int set_query_use_ifaddr(struct net_bridge *br, unsigned long val) +{ + br->multicast_query_use_ifaddr = !!val; + return 0; +} + +static ssize_t +multicast_query_use_ifaddr_store(struct device *d, + struct device_attribute *attr, + const char *buf, size_t len) +{ + return store_bridge_parm(d, buf, len, set_query_use_ifaddr); +} +static DEVICE_ATTR_RW(multicast_query_use_ifaddr); + +static ssize_t multicast_querier_show(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf(buf, "%d\n", br->multicast_querier); +} + +static ssize_t multicast_querier_store(struct device *d, + struct device_attribute *attr, + const char *buf, size_t len) +{ + return store_bridge_parm(d, buf, len, br_multicast_set_querier); +} +static DEVICE_ATTR_RW(multicast_querier); + +static ssize_t hash_elasticity_show(struct device *d, + struct device_attribute *attr, char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf(buf, "%u\n", br->hash_elasticity); +} + +static int set_elasticity(struct net_bridge *br, unsigned long val) +{ + br->hash_elasticity = val; + return 0; +} + +static ssize_t hash_elasticity_store(struct device *d, + struct device_attribute *attr, + const char *buf, size_t len) +{ + return store_bridge_parm(d, buf, len, set_elasticity); +} +static DEVICE_ATTR_RW(hash_elasticity); + +static ssize_t hash_max_show(struct device *d, struct device_attribute *attr, + char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf(buf, "%u\n", br->hash_max); +} + +static ssize_t hash_max_store(struct device *d, struct device_attribute *attr, + const char *buf, size_t len) +{ + return store_bridge_parm(d, buf, len, br_multicast_set_hash_max); +} +static DEVICE_ATTR_RW(hash_max); + +static ssize_t multicast_last_member_count_show(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf(buf, "%u\n", br->multicast_last_member_count); +} + +static int set_last_member_count(struct net_bridge *br, unsigned long val) +{ + br->multicast_last_member_count = val; + return 0; +} + +static ssize_t multicast_last_member_count_store(struct device *d, + struct device_attribute *attr, + const char *buf, size_t len) +{ + return store_bridge_parm(d, buf, len, set_last_member_count); +} +static DEVICE_ATTR_RW(multicast_last_member_count); + +static ssize_t multicast_startup_query_count_show( + struct device *d, struct device_attribute *attr, char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf(buf, "%u\n", br->multicast_startup_query_count); +} + +static int set_startup_query_count(struct net_bridge *br, unsigned long val) +{ + br->multicast_startup_query_count = val; + return 0; +} + +static ssize_t multicast_startup_query_count_store( + struct device *d, struct device_attribute *attr, const char *buf, + size_t len) +{ + return store_bridge_parm(d, buf, len, set_startup_query_count); +} +static DEVICE_ATTR_RW(multicast_startup_query_count); + +static ssize_t multicast_last_member_interval_show( + struct device *d, struct device_attribute *attr, char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf(buf, "%lu\n", + jiffies_to_clock_t(br->multicast_last_member_interval)); +} + +static int set_last_member_interval(struct net_bridge *br, unsigned long val) +{ + br->multicast_last_member_interval = clock_t_to_jiffies(val); + return 0; +} + +static ssize_t multicast_last_member_interval_store( + struct device *d, struct device_attribute *attr, const char *buf, + size_t len) +{ + return store_bridge_parm(d, buf, len, set_last_member_interval); +} +static DEVICE_ATTR_RW(multicast_last_member_interval); + +static ssize_t multicast_membership_interval_show( + struct device *d, struct device_attribute *attr, char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf(buf, "%lu\n", + jiffies_to_clock_t(br->multicast_membership_interval)); +} + +static int set_membership_interval(struct net_bridge *br, unsigned long val) +{ + br->multicast_membership_interval = clock_t_to_jiffies(val); + return 0; +} + +static ssize_t multicast_membership_interval_store( + struct device *d, struct device_attribute *attr, const char *buf, + size_t len) +{ + return store_bridge_parm(d, buf, len, set_membership_interval); +} +static DEVICE_ATTR_RW(multicast_membership_interval); + +static ssize_t multicast_querier_interval_show(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf(buf, "%lu\n", + jiffies_to_clock_t(br->multicast_querier_interval)); +} + +static int set_querier_interval(struct net_bridge *br, unsigned long val) +{ + br->multicast_querier_interval = clock_t_to_jiffies(val); + return 0; +} + +static ssize_t multicast_querier_interval_store(struct device *d, + struct device_attribute *attr, + const char *buf, size_t len) +{ + return store_bridge_parm(d, buf, len, set_querier_interval); +} +static DEVICE_ATTR_RW(multicast_querier_interval); + +static ssize_t multicast_query_interval_show(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf(buf, "%lu\n", + jiffies_to_clock_t(br->multicast_query_interval)); +} + +static int set_query_interval(struct net_bridge *br, unsigned long val) +{ + br->multicast_query_interval = clock_t_to_jiffies(val); + return 0; +} + +static ssize_t multicast_query_interval_store(struct device *d, + struct device_attribute *attr, + const char *buf, size_t len) +{ + return store_bridge_parm(d, buf, len, set_query_interval); +} +static DEVICE_ATTR_RW(multicast_query_interval); + +static ssize_t multicast_query_response_interval_show( + struct device *d, struct device_attribute *attr, char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf( + buf, "%lu\n", + jiffies_to_clock_t(br->multicast_query_response_interval)); +} + +static int set_query_response_interval(struct net_bridge *br, unsigned long val) +{ + br->multicast_query_response_interval = clock_t_to_jiffies(val); + return 0; +} + +static ssize_t multicast_query_response_interval_store( + struct device *d, struct device_attribute *attr, const char *buf, + size_t len) +{ + return store_bridge_parm(d, buf, len, set_query_response_interval); +} +static DEVICE_ATTR_RW(multicast_query_response_interval); + +static ssize_t multicast_startup_query_interval_show( + struct device *d, struct device_attribute *attr, char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf( + buf, "%lu\n", + jiffies_to_clock_t(br->multicast_startup_query_interval)); +} + +static int set_startup_query_interval(struct net_bridge *br, unsigned long val) +{ + br->multicast_startup_query_interval = clock_t_to_jiffies(val); + return 0; +} + +static ssize_t multicast_startup_query_interval_store( + struct device *d, struct device_attribute *attr, const char *buf, + size_t len) +{ + return store_bridge_parm(d, buf, len, set_startup_query_interval); +} +static DEVICE_ATTR_RW(multicast_startup_query_interval); +#endif +#ifdef CONFIG_BRIDGE_NETFILTER +static ssize_t nf_call_iptables_show( + struct device *d, struct device_attribute *attr, char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf(buf, "%u\n", br->nf_call_iptables); +} + +static int set_nf_call_iptables(struct net_bridge *br, unsigned long val) +{ + br->nf_call_iptables = val ? true : false; + return 0; +} + +static ssize_t nf_call_iptables_store( + struct device *d, struct device_attribute *attr, const char *buf, + size_t len) +{ + return store_bridge_parm(d, buf, len, set_nf_call_iptables); +} +static DEVICE_ATTR_RW(nf_call_iptables); + +static ssize_t nf_call_ip6tables_show( + struct device *d, struct device_attribute *attr, char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf(buf, "%u\n", br->nf_call_ip6tables); +} + +static int set_nf_call_ip6tables(struct net_bridge *br, unsigned long val) +{ + br->nf_call_ip6tables = val ? true : false; + return 0; +} + +static ssize_t nf_call_ip6tables_store( + struct device *d, struct device_attribute *attr, const char *buf, + size_t len) +{ + return store_bridge_parm(d, buf, len, set_nf_call_ip6tables); +} +static DEVICE_ATTR_RW(nf_call_ip6tables); + +static ssize_t nf_call_arptables_show( + struct device *d, struct device_attribute *attr, char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf(buf, "%u\n", br->nf_call_arptables); +} + +static int set_nf_call_arptables(struct net_bridge *br, unsigned long val) +{ + br->nf_call_arptables = val ? true : false; + return 0; +} + +static ssize_t nf_call_arptables_store( + struct device *d, struct device_attribute *attr, const char *buf, + size_t len) +{ + return store_bridge_parm(d, buf, len, set_nf_call_arptables); +} +static DEVICE_ATTR_RW(nf_call_arptables); +#endif +#ifdef CONFIG_BRIDGE_VLAN_FILTERING +static ssize_t vlan_filtering_show(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf(buf, "%d\n", br->vlan_enabled); +} + +static ssize_t vlan_filtering_store(struct device *d, + struct device_attribute *attr, + const char *buf, size_t len) +{ + return store_bridge_parm(d, buf, len, br_vlan_filter_toggle); +} +static DEVICE_ATTR_RW(vlan_filtering); + +static ssize_t vlan_protocol_show(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf(buf, "%#06x\n", ntohs(br->vlan_proto)); +} + +static ssize_t vlan_protocol_store(struct device *d, + struct device_attribute *attr, + const char *buf, size_t len) +{ + return store_bridge_parm(d, buf, len, br_vlan_set_proto); +} +static DEVICE_ATTR_RW(vlan_protocol); +#endif static struct attribute *bridge_attrs[] = { &dev_attr_forward_delay.attr, @@ -351,6 +733,7 @@ static struct attribute *bridge_attrs[] = { &dev_attr_max_age.attr, &dev_attr_ageing_time.attr, &dev_attr_stp_state.attr, + &dev_attr_group_fwd_mask.attr, &dev_attr_priority.attr, &dev_attr_bridge_id.attr, &dev_attr_root_id.attr, @@ -364,6 +747,31 @@ static struct attribute *bridge_attrs[] = { &dev_attr_gc_timer.attr, &dev_attr_group_addr.attr, &dev_attr_flush.attr, +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + &dev_attr_multicast_router.attr, + &dev_attr_multicast_snooping.attr, + &dev_attr_multicast_querier.attr, + &dev_attr_multicast_query_use_ifaddr.attr, + &dev_attr_hash_elasticity.attr, + &dev_attr_hash_max.attr, + &dev_attr_multicast_last_member_count.attr, + &dev_attr_multicast_startup_query_count.attr, + &dev_attr_multicast_last_member_interval.attr, + &dev_attr_multicast_membership_interval.attr, + &dev_attr_multicast_querier_interval.attr, + &dev_attr_multicast_query_interval.attr, + &dev_attr_multicast_query_response_interval.attr, + &dev_attr_multicast_startup_query_interval.attr, +#endif +#ifdef CONFIG_BRIDGE_NETFILTER + &dev_attr_nf_call_iptables.attr, + &dev_attr_nf_call_ip6tables.attr, + &dev_attr_nf_call_arptables.attr, +#endif +#ifdef CONFIG_BRIDGE_VLAN_FILTERING + &dev_attr_vlan_filtering.attr, + &dev_attr_vlan_protocol.attr, +#endif NULL }; @@ -378,7 +786,7 @@ static struct attribute_group bridge_group = { * * Returns the number of bytes read. */ -static ssize_t brforward_read(struct kobject *kobj, +static ssize_t brforward_read(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index 820643a3ba9..e561cd59b8a 100644 --- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -23,42 +23,64 @@ struct brport_attribute { struct attribute attr; ssize_t (*show)(struct net_bridge_port *, char *); - ssize_t (*store)(struct net_bridge_port *, unsigned long); + int (*store)(struct net_bridge_port *, unsigned long); }; -#define BRPORT_ATTR(_name,_mode,_show,_store) \ -struct brport_attribute brport_attr_##_name = { \ +#define BRPORT_ATTR(_name, _mode, _show, _store) \ +const struct brport_attribute brport_attr_##_name = { \ .attr = {.name = __stringify(_name), \ .mode = _mode }, \ .show = _show, \ .store = _store, \ }; -static ssize_t show_path_cost(struct net_bridge_port *p, char *buf) +#define BRPORT_ATTR_FLAG(_name, _mask) \ +static ssize_t show_##_name(struct net_bridge_port *p, char *buf) \ +{ \ + return sprintf(buf, "%d\n", !!(p->flags & _mask)); \ +} \ +static int store_##_name(struct net_bridge_port *p, unsigned long v) \ +{ \ + return store_flag(p, v, _mask); \ +} \ +static BRPORT_ATTR(_name, S_IRUGO | S_IWUSR, \ + show_##_name, store_##_name) + +static int store_flag(struct net_bridge_port *p, unsigned long v, + unsigned long mask) { - return sprintf(buf, "%d\n", p->path_cost); + unsigned long flags; + + flags = p->flags; + + if (v) + flags |= mask; + else + flags &= ~mask; + + if (flags != p->flags) { + p->flags = flags; + br_port_flags_change(p, mask); + br_ifinfo_notify(RTM_NEWLINK, p); + } + return 0; } -static ssize_t store_path_cost(struct net_bridge_port *p, unsigned long v) + +static ssize_t show_path_cost(struct net_bridge_port *p, char *buf) { - br_stp_set_path_cost(p, v); - return 0; + return sprintf(buf, "%d\n", p->path_cost); } + static BRPORT_ATTR(path_cost, S_IRUGO | S_IWUSR, - show_path_cost, store_path_cost); + show_path_cost, br_stp_set_path_cost); static ssize_t show_priority(struct net_bridge_port *p, char *buf) { return sprintf(buf, "%d\n", p->priority); } -static ssize_t store_priority(struct net_bridge_port *p, unsigned long v) -{ - if (v >= (1<<(16-BR_PORT_BITS))) - return -ERANGE; - br_stp_set_port_priority(p, v); - return 0; -} + static BRPORT_ATTR(priority, S_IRUGO | S_IWUSR, - show_priority, store_priority); + show_priority, br_stp_set_port_priority); static ssize_t show_designated_root(struct net_bridge_port *p, char *buf) { @@ -136,30 +158,37 @@ static ssize_t show_hold_timer(struct net_bridge_port *p, } static BRPORT_ATTR(hold_timer, S_IRUGO, show_hold_timer, NULL); -static ssize_t store_flush(struct net_bridge_port *p, unsigned long v) +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 return 0; } static BRPORT_ATTR(flush, S_IWUSR, NULL, store_flush); -static ssize_t show_hairpin_mode(struct net_bridge_port *p, char *buf) +BRPORT_ATTR_FLAG(hairpin_mode, BR_HAIRPIN_MODE); +BRPORT_ATTR_FLAG(bpdu_guard, BR_BPDU_GUARD); +BRPORT_ATTR_FLAG(root_block, BR_ROOT_BLOCK); +BRPORT_ATTR_FLAG(learning, BR_LEARNING); +BRPORT_ATTR_FLAG(unicast_flood, BR_FLOOD); + +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING +static ssize_t show_multicast_router(struct net_bridge_port *p, char *buf) { - int hairpin_mode = (p->flags & BR_HAIRPIN_MODE) ? 1 : 0; - return sprintf(buf, "%d\n", hairpin_mode); + return sprintf(buf, "%d\n", p->multicast_router); } -static ssize_t store_hairpin_mode(struct net_bridge_port *p, unsigned long v) + +static int store_multicast_router(struct net_bridge_port *p, + unsigned long v) { - if (v) - p->flags |= BR_HAIRPIN_MODE; - else - p->flags &= ~BR_HAIRPIN_MODE; - return 0; + return br_multicast_set_port_router(p, v); } -static BRPORT_ATTR(hairpin_mode, S_IRUGO | S_IWUSR, - show_hairpin_mode, store_hairpin_mode); +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); +#endif -static struct brport_attribute *brport_attrs[] = { +static const struct brport_attribute *brport_attrs[] = { &brport_attr_path_cost, &brport_attr_priority, &brport_attr_port_id, @@ -176,32 +205,40 @@ static struct brport_attribute *brport_attrs[] = { &brport_attr_hold_timer, &brport_attr_flush, &brport_attr_hairpin_mode, + &brport_attr_bpdu_guard, + &brport_attr_root_block, + &brport_attr_learning, + &brport_attr_unicast_flood, +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + &brport_attr_multicast_router, + &brport_attr_multicast_fast_leave, +#endif NULL }; #define to_brport_attr(_at) container_of(_at, struct brport_attribute, attr) #define to_brport(obj) container_of(obj, struct net_bridge_port, kobj) -static ssize_t brport_show(struct kobject * kobj, - struct attribute * attr, char * buf) +static ssize_t brport_show(struct kobject *kobj, + struct attribute *attr, char *buf) { - struct brport_attribute * brport_attr = to_brport_attr(attr); - struct net_bridge_port * p = to_brport(kobj); + struct brport_attribute *brport_attr = to_brport_attr(attr); + struct net_bridge_port *p = to_brport(kobj); return brport_attr->show(p, buf); } -static ssize_t brport_store(struct kobject * kobj, - struct attribute * attr, - const char * buf, size_t count) +static ssize_t brport_store(struct kobject *kobj, + struct attribute *attr, + const char *buf, size_t count) { - struct brport_attribute * brport_attr = to_brport_attr(attr); - struct net_bridge_port * p = to_brport(kobj); + struct brport_attribute *brport_attr = to_brport_attr(attr); + struct net_bridge_port *p = to_brport(kobj); ssize_t ret = -EINVAL; char *endp; unsigned long val; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(dev_net(p->dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; val = simple_strtoul(buf, &endp, 0); @@ -220,7 +257,7 @@ static ssize_t brport_store(struct kobject * kobj, return ret; } -struct sysfs_ops brport_sysfs_ops = { +const struct sysfs_ops brport_sysfs_ops = { .show = brport_show, .store = brport_store, }; @@ -228,26 +265,48 @@ struct sysfs_ops brport_sysfs_ops = { /* * Add sysfs entries to ethernet device added to a bridge. * Creates a brport subdirectory with bridge attributes. - * Puts symlink in bridge's brport subdirectory + * Puts symlink in bridge's brif subdirectory */ int br_sysfs_addif(struct net_bridge_port *p) { struct net_bridge *br = p->br; - struct brport_attribute **a; + const struct brport_attribute **a; int err; err = sysfs_create_link(&p->kobj, &br->dev->dev.kobj, SYSFS_BRIDGE_PORT_LINK); if (err) - goto out2; + return err; for (a = brport_attrs; *a; ++a) { err = sysfs_create_file(&p->kobj, &((*a)->attr)); if (err) - goto out2; + return err; } - err = sysfs_create_link(br->ifobj, &p->kobj, p->dev->name); -out2: + strlcpy(p->sysfs_name, p->dev->name, IFNAMSIZ); + return sysfs_create_link(br->ifobj, &p->kobj, p->sysfs_name); +} + +/* Rename bridge's brif symlink */ +int br_sysfs_renameif(struct net_bridge_port *p) +{ + struct net_bridge *br = p->br; + int err; + + /* If a rename fails, the rollback will cause another + * rename call with the existing name. + */ + if (!strncmp(p->sysfs_name, p->dev->name, IFNAMSIZ)) + return 0; + + err = sysfs_rename_link(br->ifobj, &p->kobj, + p->sysfs_name, p->dev->name); + if (err) + netdev_notice(br->dev, "unable to rename link %s to %s", + p->sysfs_name, p->dev->name); + else + strlcpy(p->sysfs_name, p->dev->name, IFNAMSIZ); + return err; } diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c new file mode 100644 index 00000000000..2b2774fe070 --- /dev/null +++ b/net/bridge/br_vlan.c @@ -0,0 +1,587 @@ +#include <linux/kernel.h> +#include <linux/netdevice.h> +#include <linux/rtnetlink.h> +#include <linux/slab.h> + +#include "br_private.h" + +static void __vlan_add_pvid(struct net_port_vlans *v, u16 vid) +{ + if (v->pvid == vid) + return; + + smp_wmb(); + v->pvid = vid; +} + +static void __vlan_delete_pvid(struct net_port_vlans *v, u16 vid) +{ + if (v->pvid != vid) + return; + + smp_wmb(); + v->pvid = 0; +} + +static void __vlan_add_flags(struct net_port_vlans *v, u16 vid, u16 flags) +{ + if (flags & BRIDGE_VLAN_INFO_PVID) + __vlan_add_pvid(v, vid); + + if (flags & BRIDGE_VLAN_INFO_UNTAGGED) + set_bit(vid, v->untagged_bitmap); +} + +static int __vlan_add(struct net_port_vlans *v, u16 vid, u16 flags) +{ + struct net_bridge_port *p = NULL; + struct net_bridge *br; + struct net_device *dev; + int err; + + if (test_bit(vid, v->vlan_bitmap)) { + __vlan_add_flags(v, vid, flags); + return 0; + } + + if (v->port_idx) { + p = v->parent.port; + br = p->br; + dev = p->dev; + } else { + br = v->parent.br; + dev = br->dev; + } + + if (p) { + /* Add VLAN to the device filter if it is supported. + * Stricly speaking, this is not necessary now, since + * devices are made promiscuous by the bridge, but if + * that ever changes this code will allow tagged + * traffic to enter the bridge. + */ + err = vlan_vid_add(dev, br->vlan_proto, vid); + if (err) + return err; + } + + err = br_fdb_insert(br, p, dev->dev_addr, vid); + if (err) { + br_err(br, "failed insert local address into bridge " + "forwarding table\n"); + goto out_filt; + } + + set_bit(vid, v->vlan_bitmap); + v->num_vlans++; + __vlan_add_flags(v, vid, flags); + + return 0; + +out_filt: + if (p) + vlan_vid_del(dev, br->vlan_proto, vid); + return err; +} + +static int __vlan_del(struct net_port_vlans *v, u16 vid) +{ + if (!test_bit(vid, v->vlan_bitmap)) + return -EINVAL; + + __vlan_delete_pvid(v, vid); + clear_bit(vid, v->untagged_bitmap); + + if (v->port_idx) { + struct net_bridge_port *p = v->parent.port; + vlan_vid_del(p->dev, p->br->vlan_proto, vid); + } + + clear_bit(vid, v->vlan_bitmap); + v->num_vlans--; + if (bitmap_empty(v->vlan_bitmap, VLAN_N_VID)) { + if (v->port_idx) + RCU_INIT_POINTER(v->parent.port->vlan_info, NULL); + else + RCU_INIT_POINTER(v->parent.br->vlan_info, NULL); + kfree_rcu(v, rcu); + } + return 0; +} + +static void __vlan_flush(struct net_port_vlans *v) +{ + smp_wmb(); + v->pvid = 0; + bitmap_zero(v->vlan_bitmap, VLAN_N_VID); + if (v->port_idx) + RCU_INIT_POINTER(v->parent.port->vlan_info, NULL); + else + RCU_INIT_POINTER(v->parent.br->vlan_info, NULL); + kfree_rcu(v, rcu); +} + +struct sk_buff *br_handle_vlan(struct net_bridge *br, + const struct net_port_vlans *pv, + struct sk_buff *skb) +{ + u16 vid; + + if (!br->vlan_enabled) + goto out; + + /* Vlan filter table must be configured at this point. The + * only exception is the bridge is set in promisc mode and the + * packet is destined for the bridge device. In this case + * pass the packet as is. + */ + if (!pv) { + if ((br->dev->flags & IFF_PROMISC) && skb->dev == br->dev) { + goto out; + } else { + kfree_skb(skb); + return NULL; + } + } + + /* At this point, we know that the frame was filtered and contains + * a valid vlan id. If the vlan id is set in the untagged bitmap, + * send untagged; otherwise, send tagged. + */ + br_vlan_get_tag(skb, &vid); + if (test_bit(vid, pv->untagged_bitmap)) + skb->vlan_tci = 0; + +out: + return skb; +} + +/* Called under RCU */ +bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, + struct sk_buff *skb, u16 *vid) +{ + bool tagged; + __be16 proto; + + /* If VLAN filtering is disabled on the bridge, all packets are + * permitted. + */ + if (!br->vlan_enabled) + return true; + + /* If there are no vlan in the permitted list, all packets are + * rejected. + */ + if (!v) + goto drop; + + proto = br->vlan_proto; + + /* If vlan tx offload is disabled on bridge device and frame was + * sent from vlan device on the bridge device, it does not have + * HW accelerated vlan tag. + */ + if (unlikely(!vlan_tx_tag_present(skb) && + skb->protocol == proto)) { + skb = vlan_untag(skb); + if (unlikely(!skb)) + return false; + } + + if (!br_vlan_get_tag(skb, vid)) { + /* Tagged frame */ + if (skb->vlan_proto != proto) { + /* Protocol-mismatch, empty out vlan_tci for new tag */ + skb_push(skb, ETH_HLEN); + skb = __vlan_put_tag(skb, skb->vlan_proto, + vlan_tx_tag_get(skb)); + if (unlikely(!skb)) + return false; + + skb_pull(skb, ETH_HLEN); + skb_reset_mac_len(skb); + *vid = 0; + tagged = false; + } else { + tagged = true; + } + } else { + /* Untagged frame */ + tagged = false; + } + + if (!*vid) { + u16 pvid = br_get_pvid(v); + + /* Frame had a tag with VID 0 or did not have a tag. + * See if pvid is set on this port. That tells us which + * vlan untagged or priority-tagged traffic belongs to. + */ + if (pvid == VLAN_N_VID) + goto drop; + + /* PVID is set on this port. Any untagged or priority-tagged + * ingress frame is considered to belong to this vlan. + */ + *vid = pvid; + if (likely(!tagged)) + /* Untagged Frame. */ + __vlan_hwaccel_put_tag(skb, proto, pvid); + else + /* Priority-tagged Frame. + * At this point, We know that skb->vlan_tci had + * VLAN_TAG_PRESENT bit and its VID field was 0x000. + * We update only VID field and preserve PCP field. + */ + skb->vlan_tci |= pvid; + + return true; + } + + /* Frame had a valid vlan tag. See if vlan is allowed */ + if (test_bit(*vid, v->vlan_bitmap)) + return true; +drop: + kfree_skb(skb); + return false; +} + +/* Called under RCU. */ +bool br_allowed_egress(struct net_bridge *br, + const struct net_port_vlans *v, + const struct sk_buff *skb) +{ + u16 vid; + + if (!br->vlan_enabled) + return true; + + if (!v) + return false; + + br_vlan_get_tag(skb, &vid); + if (test_bit(vid, v->vlan_bitmap)) + return true; + + return false; +} + +/* Called under RCU */ +bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid) +{ + struct net_bridge *br = p->br; + struct net_port_vlans *v; + + if (!br->vlan_enabled) + return true; + + v = rcu_dereference(p->vlan_info); + if (!v) + return false; + + if (!br_vlan_get_tag(skb, vid) && skb->vlan_proto != br->vlan_proto) + *vid = 0; + + if (!*vid) { + *vid = br_get_pvid(v); + if (*vid == VLAN_N_VID) + return false; + + return true; + } + + if (test_bit(*vid, v->vlan_bitmap)) + return true; + + return false; +} + +/* Must be protected by RTNL. + * Must be called with vid in range from 1 to 4094 inclusive. + */ +int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags) +{ + struct net_port_vlans *pv = NULL; + int err; + + ASSERT_RTNL(); + + pv = rtnl_dereference(br->vlan_info); + if (pv) + return __vlan_add(pv, vid, flags); + + /* Create port vlan infomration + */ + pv = kzalloc(sizeof(*pv), GFP_KERNEL); + if (!pv) + return -ENOMEM; + + pv->parent.br = br; + err = __vlan_add(pv, vid, flags); + if (err) + goto out; + + rcu_assign_pointer(br->vlan_info, pv); + return 0; +out: + kfree(pv); + return err; +} + +/* Must be protected by RTNL. + * Must be called with vid in range from 1 to 4094 inclusive. + */ +int br_vlan_delete(struct net_bridge *br, u16 vid) +{ + struct net_port_vlans *pv; + + ASSERT_RTNL(); + + pv = rtnl_dereference(br->vlan_info); + if (!pv) + return -EINVAL; + + br_fdb_find_delete_local(br, NULL, br->dev->dev_addr, vid); + + __vlan_del(pv, vid); + return 0; +} + +void br_vlan_flush(struct net_bridge *br) +{ + struct net_port_vlans *pv; + + ASSERT_RTNL(); + pv = rtnl_dereference(br->vlan_info); + if (!pv) + return; + + __vlan_flush(pv); +} + +bool br_vlan_find(struct net_bridge *br, u16 vid) +{ + struct net_port_vlans *pv; + bool found = false; + + rcu_read_lock(); + pv = rcu_dereference(br->vlan_info); + + if (!pv) + goto out; + + if (test_bit(vid, pv->vlan_bitmap)) + found = true; + +out: + rcu_read_unlock(); + return found; +} + +/* Must be protected by RTNL. */ +static void recalculate_group_addr(struct net_bridge *br) +{ + if (br->group_addr_set) + return; + + spin_lock_bh(&br->lock); + if (!br->vlan_enabled || br->vlan_proto == htons(ETH_P_8021Q)) { + /* Bridge Group Address */ + br->group_addr[5] = 0x00; + } else { /* vlan_enabled && ETH_P_8021AD */ + /* Provider Bridge Group Address */ + br->group_addr[5] = 0x08; + } + spin_unlock_bh(&br->lock); +} + +/* Must be protected by RTNL. */ +void br_recalculate_fwd_mask(struct net_bridge *br) +{ + if (!br->vlan_enabled || br->vlan_proto == htons(ETH_P_8021Q)) + br->group_fwd_mask_required = BR_GROUPFWD_DEFAULT; + else /* vlan_enabled && ETH_P_8021AD */ + br->group_fwd_mask_required = BR_GROUPFWD_8021AD & + ~(1u << br->group_addr[5]); +} + +int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val) +{ + if (!rtnl_trylock()) + return restart_syscall(); + + if (br->vlan_enabled == val) + goto unlock; + + br->vlan_enabled = val; + br_manage_promisc(br); + recalculate_group_addr(br); + br_recalculate_fwd_mask(br); + +unlock: + rtnl_unlock(); + return 0; +} + +int br_vlan_set_proto(struct net_bridge *br, unsigned long val) +{ + int err = 0; + struct net_bridge_port *p; + struct net_port_vlans *pv; + __be16 proto, oldproto; + u16 vid, errvid; + + if (val != ETH_P_8021Q && val != ETH_P_8021AD) + return -EPROTONOSUPPORT; + + if (!rtnl_trylock()) + return restart_syscall(); + + proto = htons(val); + if (br->vlan_proto == proto) + goto unlock; + + /* Add VLANs for the new proto to the device filter. */ + list_for_each_entry(p, &br->port_list, list) { + pv = rtnl_dereference(p->vlan_info); + if (!pv) + continue; + + for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { + err = vlan_vid_add(p->dev, proto, vid); + if (err) + goto err_filt; + } + } + + oldproto = br->vlan_proto; + br->vlan_proto = proto; + + recalculate_group_addr(br); + br_recalculate_fwd_mask(br); + + /* Delete VLANs for the old proto from the device filter. */ + list_for_each_entry(p, &br->port_list, list) { + pv = rtnl_dereference(p->vlan_info); + if (!pv) + continue; + + for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) + vlan_vid_del(p->dev, oldproto, vid); + } + +unlock: + rtnl_unlock(); + return err; + +err_filt: + errvid = vid; + for_each_set_bit(vid, pv->vlan_bitmap, errvid) + vlan_vid_del(p->dev, proto, vid); + + list_for_each_entry_continue_reverse(p, &br->port_list, list) { + pv = rtnl_dereference(p->vlan_info); + if (!pv) + continue; + + for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) + vlan_vid_del(p->dev, proto, vid); + } + + goto unlock; +} + +void br_vlan_init(struct net_bridge *br) +{ + br->vlan_proto = htons(ETH_P_8021Q); +} + +/* Must be protected by RTNL. + * Must be called with vid in range from 1 to 4094 inclusive. + */ +int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags) +{ + struct net_port_vlans *pv = NULL; + int err; + + ASSERT_RTNL(); + + pv = rtnl_dereference(port->vlan_info); + if (pv) + return __vlan_add(pv, vid, flags); + + /* Create port vlan infomration + */ + pv = kzalloc(sizeof(*pv), GFP_KERNEL); + if (!pv) { + err = -ENOMEM; + goto clean_up; + } + + pv->port_idx = port->port_no; + pv->parent.port = port; + err = __vlan_add(pv, vid, flags); + if (err) + goto clean_up; + + rcu_assign_pointer(port->vlan_info, pv); + return 0; + +clean_up: + kfree(pv); + return err; +} + +/* Must be protected by RTNL. + * Must be called with vid in range from 1 to 4094 inclusive. + */ +int nbp_vlan_delete(struct net_bridge_port *port, u16 vid) +{ + struct net_port_vlans *pv; + + ASSERT_RTNL(); + + pv = rtnl_dereference(port->vlan_info); + if (!pv) + return -EINVAL; + + br_fdb_find_delete_local(port->br, port, port->dev->dev_addr, vid); + + return __vlan_del(pv, vid); +} + +void nbp_vlan_flush(struct net_bridge_port *port) +{ + struct net_port_vlans *pv; + u16 vid; + + ASSERT_RTNL(); + + pv = rtnl_dereference(port->vlan_info); + if (!pv) + return; + + for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) + vlan_vid_del(port->dev, port->br->vlan_proto, vid); + + __vlan_flush(pv); +} + +bool nbp_vlan_find(struct net_bridge_port *port, u16 vid) +{ + struct net_port_vlans *pv; + bool found = false; + + rcu_read_lock(); + pv = rcu_dereference(port->vlan_info); + + if (!pv) + goto out; + + if (test_bit(vid, pv->vlan_bitmap)) + found = true; + +out: + rcu_read_unlock(); + return found; +} diff --git a/net/bridge/netfilter/Kconfig b/net/bridge/netfilter/Kconfig index ba6f73eb06c..629dc77874a 100644 --- a/net/bridge/netfilter/Kconfig +++ b/net/bridge/netfilter/Kconfig @@ -1,11 +1,24 @@ # # Bridge netfilter configuration # +# +menuconfig NF_TABLES_BRIDGE + depends on BRIDGE && NETFILTER && NF_TABLES + tristate "Ethernet Bridge nf_tables support" + +if NF_TABLES_BRIDGE + +config NFT_BRIDGE_META + tristate "Netfilter nf_table bridge meta support" + depends on NFT_META + help + Add support for bridge dedicated meta key. + +endif # NF_TABLES_BRIDGE menuconfig BRIDGE_NF_EBTABLES tristate "Ethernet Bridge tables (ebtables) support" - depends on BRIDGE && BRIDGE_NETFILTER - select NETFILTER_XTABLES + depends on BRIDGE && NETFILTER && NETFILTER_XTABLES help ebtables is a general, extensible frame/packet identification framework. Say 'Y' or 'M' here if you want to do Ethernet diff --git a/net/bridge/netfilter/Makefile b/net/bridge/netfilter/Makefile index 0718699540b..6f2f3943d66 100644 --- a/net/bridge/netfilter/Makefile +++ b/net/bridge/netfilter/Makefile @@ -2,6 +2,9 @@ # Makefile for the netfilter modules for Link Layer filtering on a bridge. # +obj-$(CONFIG_NF_TABLES_BRIDGE) += nf_tables_bridge.o +obj-$(CONFIG_NFT_BRIDGE_META) += nft_meta_bridge.o + obj-$(CONFIG_BRIDGE_NF_EBTABLES) += ebtables.o # tables diff --git a/net/bridge/netfilter/ebt_802_3.c b/net/bridge/netfilter/ebt_802_3.c index bd91dc58d49..2a449b7ab8f 100644 --- a/net/bridge/netfilter/ebt_802_3.c +++ b/net/bridge/netfilter/ebt_802_3.c @@ -13,7 +13,7 @@ #include <linux/netfilter_bridge/ebt_802_3.h> static bool -ebt_802_3_mt(const struct sk_buff *skb, const struct xt_match_param *par) +ebt_802_3_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct ebt_802_3_info *info = par->matchinfo; const struct ebt_802_3_hdr *hdr = ebt_802_3_hdr(skb); @@ -36,14 +36,14 @@ ebt_802_3_mt(const struct sk_buff *skb, const struct xt_match_param *par) return true; } -static bool ebt_802_3_mt_check(const struct xt_mtchk_param *par) +static int ebt_802_3_mt_check(const struct xt_mtchk_param *par) { const struct ebt_802_3_info *info = par->matchinfo; if (info->bitmask & ~EBT_802_3_MASK || info->invflags & ~EBT_802_3_MASK) - return false; + return -EINVAL; - return true; + return 0; } static struct xt_match ebt_802_3_mt_reg __read_mostly = { @@ -52,7 +52,7 @@ static struct xt_match ebt_802_3_mt_reg __read_mostly = { .family = NFPROTO_BRIDGE, .match = ebt_802_3_mt, .checkentry = ebt_802_3_mt_check, - .matchsize = XT_ALIGN(sizeof(struct ebt_802_3_info)), + .matchsize = sizeof(struct ebt_802_3_info), .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebt_among.c b/net/bridge/netfilter/ebt_among.c index b595f091f35..9024283d2bc 100644 --- a/net/bridge/netfilter/ebt_among.c +++ b/net/bridge/netfilter/ebt_among.c @@ -7,6 +7,7 @@ * August, 2003 * */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/ip.h> #include <linux/if_arp.h> #include <linux/module.h> @@ -27,7 +28,7 @@ static bool ebt_mac_wormhash_contains(const struct ebt_mac_wormhash *wh, uint32_t cmp[2] = { 0, 0 }; int key = ((const unsigned char *)mac)[5]; - memcpy(((char *) cmp) + 2, mac, 6); + ether_addr_copy(((char *) cmp) + 2, mac); start = wh->table[key]; limit = wh->table[key + 1]; if (ip) { @@ -128,7 +129,7 @@ static int get_ip_src(const struct sk_buff *skb, __be32 *addr) } static bool -ebt_among_mt(const struct sk_buff *skb, const struct xt_match_param *par) +ebt_among_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct ebt_among_info *info = par->matchinfo; const char *dmac, *smac; @@ -171,7 +172,7 @@ ebt_among_mt(const struct sk_buff *skb, const struct xt_match_param *par) return true; } -static bool ebt_among_mt_check(const struct xt_mtchk_param *par) +static int ebt_among_mt_check(const struct xt_mtchk_param *par) { const struct ebt_among_info *info = par->matchinfo; const struct ebt_entry_match *em = @@ -186,24 +187,20 @@ static bool ebt_among_mt_check(const struct xt_mtchk_param *par) expected_length += ebt_mac_wormhash_size(wh_src); if (em->match_size != EBT_ALIGN(expected_length)) { - printk(KERN_WARNING - "ebtables: among: wrong size: %d " - "against expected %d, rounded to %Zd\n", - em->match_size, expected_length, - EBT_ALIGN(expected_length)); - return false; + pr_info("wrong size: %d against expected %d, rounded to %Zd\n", + em->match_size, expected_length, + EBT_ALIGN(expected_length)); + return -EINVAL; } if (wh_dst && (err = ebt_mac_wormhash_check_integrity(wh_dst))) { - printk(KERN_WARNING - "ebtables: among: dst integrity fail: %x\n", -err); - return false; + pr_info("dst integrity fail: %x\n", -err); + return -EINVAL; } if (wh_src && (err = ebt_mac_wormhash_check_integrity(wh_src))) { - printk(KERN_WARNING - "ebtables: among: src integrity fail: %x\n", -err); - return false; + pr_info("src integrity fail: %x\n", -err); + return -EINVAL; } - return true; + return 0; } static struct xt_match ebt_among_mt_reg __read_mostly = { diff --git a/net/bridge/netfilter/ebt_arp.c b/net/bridge/netfilter/ebt_arp.c index b7ad60419f9..cd457b891b2 100644 --- a/net/bridge/netfilter/ebt_arp.c +++ b/net/bridge/netfilter/ebt_arp.c @@ -16,7 +16,7 @@ #include <linux/netfilter_bridge/ebt_arp.h> static bool -ebt_arp_mt(const struct sk_buff *skb, const struct xt_match_param *par) +ebt_arp_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct ebt_arp_info *info = par->matchinfo; const struct arphdr *ah; @@ -100,7 +100,7 @@ ebt_arp_mt(const struct sk_buff *skb, const struct xt_match_param *par) return true; } -static bool ebt_arp_mt_check(const struct xt_mtchk_param *par) +static int ebt_arp_mt_check(const struct xt_mtchk_param *par) { const struct ebt_arp_info *info = par->matchinfo; const struct ebt_entry *e = par->entryinfo; @@ -108,10 +108,10 @@ static bool ebt_arp_mt_check(const struct xt_mtchk_param *par) if ((e->ethproto != htons(ETH_P_ARP) && e->ethproto != htons(ETH_P_RARP)) || e->invflags & EBT_IPROTO) - return false; + return -EINVAL; if (info->bitmask & ~EBT_ARP_MASK || info->invflags & ~EBT_ARP_MASK) - return false; - return true; + return -EINVAL; + return 0; } static struct xt_match ebt_arp_mt_reg __read_mostly = { @@ -120,7 +120,7 @@ static struct xt_match ebt_arp_mt_reg __read_mostly = { .family = NFPROTO_BRIDGE, .match = ebt_arp_mt, .checkentry = ebt_arp_mt_check, - .matchsize = XT_ALIGN(sizeof(struct ebt_arp_info)), + .matchsize = sizeof(struct ebt_arp_info), .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebt_arpreply.c b/net/bridge/netfilter/ebt_arpreply.c index 76584cd72e5..070cf134a22 100644 --- a/net/bridge/netfilter/ebt_arpreply.c +++ b/net/bridge/netfilter/ebt_arpreply.c @@ -16,7 +16,7 @@ #include <linux/netfilter_bridge/ebt_arpreply.h> static unsigned int -ebt_arpreply_tg(struct sk_buff *skb, const struct xt_target_param *par) +ebt_arpreply_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ebt_arpreply_info *info = par->targinfo; const __be32 *siptr, *diptr; @@ -57,17 +57,17 @@ ebt_arpreply_tg(struct sk_buff *skb, const struct xt_target_param *par) return info->target; } -static bool ebt_arpreply_tg_check(const struct xt_tgchk_param *par) +static int ebt_arpreply_tg_check(const struct xt_tgchk_param *par) { const struct ebt_arpreply_info *info = par->targinfo; const struct ebt_entry *e = par->entryinfo; if (BASE_CHAIN && info->target == EBT_RETURN) - return false; + return -EINVAL; if (e->ethproto != htons(ETH_P_ARP) || e->invflags & EBT_IPROTO) - return false; - return true; + return -EINVAL; + return 0; } static struct xt_target ebt_arpreply_tg_reg __read_mostly = { @@ -78,7 +78,7 @@ static struct xt_target ebt_arpreply_tg_reg __read_mostly = { .hooks = (1 << NF_BR_NUMHOOKS) | (1 << NF_BR_PRE_ROUTING), .target = ebt_arpreply_tg, .checkentry = ebt_arpreply_tg_check, - .targetsize = XT_ALIGN(sizeof(struct ebt_arpreply_info)), + .targetsize = sizeof(struct ebt_arpreply_info), .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebt_dnat.c b/net/bridge/netfilter/ebt_dnat.c index 6b49ea9e31f..4e0b0c35932 100644 --- a/net/bridge/netfilter/ebt_dnat.c +++ b/net/bridge/netfilter/ebt_dnat.c @@ -15,24 +15,24 @@ #include <linux/netfilter_bridge/ebt_nat.h> static unsigned int -ebt_dnat_tg(struct sk_buff *skb, const struct xt_target_param *par) +ebt_dnat_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ebt_nat_info *info = par->targinfo; if (!skb_make_writable(skb, 0)) return EBT_DROP; - memcpy(eth_hdr(skb)->h_dest, info->mac, ETH_ALEN); + ether_addr_copy(eth_hdr(skb)->h_dest, info->mac); return info->target; } -static bool ebt_dnat_tg_check(const struct xt_tgchk_param *par) +static int ebt_dnat_tg_check(const struct xt_tgchk_param *par) { const struct ebt_nat_info *info = par->targinfo; unsigned int hook_mask; if (BASE_CHAIN && info->target == EBT_RETURN) - return false; + return -EINVAL; hook_mask = par->hook_mask & ~(1 << NF_BR_NUMHOOKS); if ((strcmp(par->table, "nat") != 0 || @@ -40,10 +40,10 @@ static bool ebt_dnat_tg_check(const struct xt_tgchk_param *par) (1 << NF_BR_LOCAL_OUT)))) && (strcmp(par->table, "broute") != 0 || hook_mask & ~(1 << NF_BR_BROUTING))) - return false; + return -EINVAL; if (INVALID_TARGET) - return false; - return true; + return -EINVAL; + return 0; } static struct xt_target ebt_dnat_tg_reg __read_mostly = { @@ -54,7 +54,7 @@ static struct xt_target ebt_dnat_tg_reg __read_mostly = { (1 << NF_BR_LOCAL_OUT) | (1 << NF_BR_BROUTING), .target = ebt_dnat_tg, .checkentry = ebt_dnat_tg_check, - .targetsize = XT_ALIGN(sizeof(struct ebt_nat_info)), + .targetsize = sizeof(struct ebt_nat_info), .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebt_ip.c b/net/bridge/netfilter/ebt_ip.c index d771bbfbcbe..23bca62d58d 100644 --- a/net/bridge/netfilter/ebt_ip.c +++ b/net/bridge/netfilter/ebt_ip.c @@ -25,7 +25,7 @@ struct tcpudphdr { }; static bool -ebt_ip_mt(const struct sk_buff *skb, const struct xt_match_param *par) +ebt_ip_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct ebt_ip_info *info = par->matchinfo; const struct iphdr *ih; @@ -77,31 +77,31 @@ ebt_ip_mt(const struct sk_buff *skb, const struct xt_match_param *par) return true; } -static bool ebt_ip_mt_check(const struct xt_mtchk_param *par) +static int ebt_ip_mt_check(const struct xt_mtchk_param *par) { const struct ebt_ip_info *info = par->matchinfo; const struct ebt_entry *e = par->entryinfo; if (e->ethproto != htons(ETH_P_IP) || e->invflags & EBT_IPROTO) - return false; + return -EINVAL; if (info->bitmask & ~EBT_IP_MASK || info->invflags & ~EBT_IP_MASK) - return false; + return -EINVAL; if (info->bitmask & (EBT_IP_DPORT | EBT_IP_SPORT)) { if (info->invflags & EBT_IP_PROTO) - return false; + return -EINVAL; if (info->protocol != IPPROTO_TCP && info->protocol != IPPROTO_UDP && info->protocol != IPPROTO_UDPLITE && info->protocol != IPPROTO_SCTP && info->protocol != IPPROTO_DCCP) - return false; + return -EINVAL; } if (info->bitmask & EBT_IP_DPORT && info->dport[0] > info->dport[1]) - return false; + return -EINVAL; if (info->bitmask & EBT_IP_SPORT && info->sport[0] > info->sport[1]) - return false; - return true; + return -EINVAL; + return 0; } static struct xt_match ebt_ip_mt_reg __read_mostly = { @@ -110,7 +110,7 @@ static struct xt_match ebt_ip_mt_reg __read_mostly = { .family = NFPROTO_BRIDGE, .match = ebt_ip_mt, .checkentry = ebt_ip_mt_check, - .matchsize = XT_ALIGN(sizeof(struct ebt_ip_info)), + .matchsize = sizeof(struct ebt_ip_info), .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebt_ip6.c b/net/bridge/netfilter/ebt_ip6.c index 784a6573876..17fd5f2cb4b 100644 --- a/net/bridge/netfilter/ebt_ip6.c +++ b/net/bridge/netfilter/ebt_ip6.c @@ -4,7 +4,7 @@ * Authors: * Manohar Castelino <manohar.r.castelino@intel.com> * Kuo-Lang Tseng <kuo-lang.tseng@intel.com> - * Jan Engelhardt <jengelh@computergmbh.de> + * Jan Engelhardt <jengelh@medozas.de> * * Summary: * This is just a modification of the IPv4 code written by @@ -22,21 +22,25 @@ #include <linux/netfilter_bridge/ebtables.h> #include <linux/netfilter_bridge/ebt_ip6.h> -struct tcpudphdr { - __be16 src; - __be16 dst; +union pkthdr { + struct { + __be16 src; + __be16 dst; + } tcpudphdr; + struct { + u8 type; + u8 code; + } icmphdr; }; static bool -ebt_ip6_mt(const struct sk_buff *skb, const struct xt_match_param *par) +ebt_ip6_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct ebt_ip6_info *info = par->matchinfo; const struct ipv6hdr *ih6; struct ipv6hdr _ip6h; - const struct tcpudphdr *pptr; - struct tcpudphdr _ports; - struct in6_addr tmp_addr; - int i; + const union pkthdr *pptr; + union pkthdr _pkthdr; ih6 = skb_header_pointer(skb, 0, sizeof(_ip6h), &_ip6h); if (ih6 == NULL) @@ -44,76 +48,87 @@ ebt_ip6_mt(const struct sk_buff *skb, const struct xt_match_param *par) if (info->bitmask & EBT_IP6_TCLASS && FWINV(info->tclass != ipv6_get_dsfield(ih6), EBT_IP6_TCLASS)) return false; - for (i = 0; i < 4; i++) - tmp_addr.in6_u.u6_addr32[i] = ih6->saddr.in6_u.u6_addr32[i] & - info->smsk.in6_u.u6_addr32[i]; - if (info->bitmask & EBT_IP6_SOURCE && - FWINV((ipv6_addr_cmp(&tmp_addr, &info->saddr) != 0), - EBT_IP6_SOURCE)) - return false; - for (i = 0; i < 4; i++) - tmp_addr.in6_u.u6_addr32[i] = ih6->daddr.in6_u.u6_addr32[i] & - info->dmsk.in6_u.u6_addr32[i]; - if (info->bitmask & EBT_IP6_DEST && - FWINV((ipv6_addr_cmp(&tmp_addr, &info->daddr) != 0), EBT_IP6_DEST)) + if ((info->bitmask & EBT_IP6_SOURCE && + FWINV(ipv6_masked_addr_cmp(&ih6->saddr, &info->smsk, + &info->saddr), EBT_IP6_SOURCE)) || + (info->bitmask & EBT_IP6_DEST && + FWINV(ipv6_masked_addr_cmp(&ih6->daddr, &info->dmsk, + &info->daddr), EBT_IP6_DEST))) return false; if (info->bitmask & EBT_IP6_PROTO) { uint8_t nexthdr = ih6->nexthdr; + __be16 frag_off; int offset_ph; - offset_ph = ipv6_skip_exthdr(skb, sizeof(_ip6h), &nexthdr); + offset_ph = ipv6_skip_exthdr(skb, sizeof(_ip6h), &nexthdr, &frag_off); if (offset_ph == -1) return false; if (FWINV(info->protocol != nexthdr, EBT_IP6_PROTO)) return false; - if (!(info->bitmask & EBT_IP6_DPORT) && - !(info->bitmask & EBT_IP6_SPORT)) + if (!(info->bitmask & ( EBT_IP6_DPORT | + EBT_IP6_SPORT | EBT_IP6_ICMP6))) return true; - pptr = skb_header_pointer(skb, offset_ph, sizeof(_ports), - &_ports); + + /* min icmpv6 headersize is 4, so sizeof(_pkthdr) is ok. */ + pptr = skb_header_pointer(skb, offset_ph, sizeof(_pkthdr), + &_pkthdr); if (pptr == NULL) return false; if (info->bitmask & EBT_IP6_DPORT) { - u32 dst = ntohs(pptr->dst); + u16 dst = ntohs(pptr->tcpudphdr.dst); if (FWINV(dst < info->dport[0] || dst > info->dport[1], EBT_IP6_DPORT)) return false; } if (info->bitmask & EBT_IP6_SPORT) { - u32 src = ntohs(pptr->src); + u16 src = ntohs(pptr->tcpudphdr.src); if (FWINV(src < info->sport[0] || src > info->sport[1], EBT_IP6_SPORT)) return false; } - return true; + if ((info->bitmask & EBT_IP6_ICMP6) && + FWINV(pptr->icmphdr.type < info->icmpv6_type[0] || + pptr->icmphdr.type > info->icmpv6_type[1] || + pptr->icmphdr.code < info->icmpv6_code[0] || + pptr->icmphdr.code > info->icmpv6_code[1], + EBT_IP6_ICMP6)) + return false; } return true; } -static bool ebt_ip6_mt_check(const struct xt_mtchk_param *par) +static int ebt_ip6_mt_check(const struct xt_mtchk_param *par) { const struct ebt_entry *e = par->entryinfo; struct ebt_ip6_info *info = par->matchinfo; if (e->ethproto != htons(ETH_P_IPV6) || e->invflags & EBT_IPROTO) - return false; + return -EINVAL; if (info->bitmask & ~EBT_IP6_MASK || info->invflags & ~EBT_IP6_MASK) - return false; + return -EINVAL; if (info->bitmask & (EBT_IP6_DPORT | EBT_IP6_SPORT)) { if (info->invflags & EBT_IP6_PROTO) - return false; + return -EINVAL; if (info->protocol != IPPROTO_TCP && info->protocol != IPPROTO_UDP && info->protocol != IPPROTO_UDPLITE && info->protocol != IPPROTO_SCTP && info->protocol != IPPROTO_DCCP) - return false; + return -EINVAL; } if (info->bitmask & EBT_IP6_DPORT && info->dport[0] > info->dport[1]) - return false; + return -EINVAL; if (info->bitmask & EBT_IP6_SPORT && info->sport[0] > info->sport[1]) - return false; - return true; + return -EINVAL; + if (info->bitmask & EBT_IP6_ICMP6) { + if ((info->invflags & EBT_IP6_PROTO) || + info->protocol != IPPROTO_ICMPV6) + return -EINVAL; + if (info->icmpv6_type[0] > info->icmpv6_type[1] || + info->icmpv6_code[0] > info->icmpv6_code[1]) + return -EINVAL; + } + return 0; } static struct xt_match ebt_ip6_mt_reg __read_mostly = { @@ -122,7 +137,7 @@ static struct xt_match ebt_ip6_mt_reg __read_mostly = { .family = NFPROTO_BRIDGE, .match = ebt_ip6_mt, .checkentry = ebt_ip6_mt_check, - .matchsize = XT_ALIGN(sizeof(struct ebt_ip6_info)), + .matchsize = sizeof(struct ebt_ip6_info), .me = THIS_MODULE, }; @@ -139,4 +154,5 @@ static void __exit ebt_ip6_fini(void) module_init(ebt_ip6_init); module_exit(ebt_ip6_fini); MODULE_DESCRIPTION("Ebtables: IPv6 protocol packet match"); +MODULE_AUTHOR("Kuo-Lang Tseng <kuo-lang.tseng@intel.com>"); MODULE_LICENSE("GPL"); diff --git a/net/bridge/netfilter/ebt_limit.c b/net/bridge/netfilter/ebt_limit.c index f7bd9192ff0..517e78befcb 100644 --- a/net/bridge/netfilter/ebt_limit.c +++ b/net/bridge/netfilter/ebt_limit.c @@ -10,6 +10,7 @@ * September, 2003 * */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/netdevice.h> #include <linux/spinlock.h> @@ -31,7 +32,7 @@ static DEFINE_SPINLOCK(limit_lock); #define CREDITS_PER_JIFFY POW2_BELOW32(MAX_CPJ) static bool -ebt_limit_mt(const struct sk_buff *skb, const struct xt_match_param *par) +ebt_limit_mt(const struct sk_buff *skb, struct xt_action_param *par) { struct ebt_limit_info *info = (void *)par->matchinfo; unsigned long now = jiffies; @@ -64,16 +65,16 @@ user2credits(u_int32_t user) return (user * HZ * CREDITS_PER_JIFFY) / EBT_LIMIT_SCALE; } -static bool ebt_limit_mt_check(const struct xt_mtchk_param *par) +static int ebt_limit_mt_check(const struct xt_mtchk_param *par) { struct ebt_limit_info *info = par->matchinfo; /* Check for overflow. */ if (info->burst == 0 || user2credits(info->avg * info->burst) < user2credits(info->avg)) { - printk("Overflow in ebt_limit, try lower: %u/%u\n", + pr_info("overflow, try lower: %u/%u\n", info->avg, info->burst); - return false; + return -EINVAL; } /* User avg in seconds * EBT_LIMIT_SCALE: convert to jiffies * 128. */ @@ -81,16 +82,32 @@ static bool ebt_limit_mt_check(const struct xt_mtchk_param *par) info->credit = user2credits(info->avg * info->burst); info->credit_cap = user2credits(info->avg * info->burst); info->cost = user2credits(info->avg); - return true; + return 0; } + +#ifdef CONFIG_COMPAT +/* + * no conversion function needed -- + * only avg/burst have meaningful values in userspace. + */ +struct ebt_compat_limit_info { + compat_uint_t avg, burst; + compat_ulong_t prev; + compat_uint_t credit, credit_cap, cost; +}; +#endif + static struct xt_match ebt_limit_mt_reg __read_mostly = { .name = "limit", .revision = 0, .family = NFPROTO_BRIDGE, .match = ebt_limit_mt, .checkentry = ebt_limit_mt_check, - .matchsize = XT_ALIGN(sizeof(struct ebt_limit_info)), + .matchsize = sizeof(struct ebt_limit_info), +#ifdef CONFIG_COMPAT + .compatsize = sizeof(struct ebt_compat_limit_info), +#endif .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebt_log.c b/net/bridge/netfilter/ebt_log.c index e4ea3fdd1d4..5322a36867a 100644 --- a/net/bridge/netfilter/ebt_log.c +++ b/net/bridge/netfilter/ebt_log.c @@ -24,16 +24,16 @@ static DEFINE_SPINLOCK(ebt_log_lock); -static bool ebt_log_tg_check(const struct xt_tgchk_param *par) +static int ebt_log_tg_check(const struct xt_tgchk_param *par) { struct ebt_log_info *info = par->targinfo; if (info->bitmask & ~EBT_LOG_MASK) - return false; + return -EINVAL; if (info->loglevel >= 8) - return false; + return -EINVAL; info->prefix[EBT_LOG_PREFIX_SIZE - 1] = '\0'; - return true; + return 0; } struct tcpudphdr @@ -72,15 +72,19 @@ print_ports(const struct sk_buff *skb, uint8_t protocol, int offset) } static void -ebt_log_packet(u_int8_t pf, unsigned int hooknum, - const struct sk_buff *skb, const struct net_device *in, - const struct net_device *out, const struct nf_loginfo *loginfo, - const char *prefix) +ebt_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum, + const struct sk_buff *skb, const struct net_device *in, + const struct net_device *out, const struct nf_loginfo *loginfo, + const char *prefix) { unsigned int bitmask; + /* FIXME: Disabled from containers until syslog ns is supported */ + if (!net_eq(net, &init_net)) + return; + spin_lock_bh(&ebt_log_lock); - printk("<%c>%s IN=%s OUT=%s MAC source = %pM MAC dest = %pM proto = 0x%04x", + printk(KERN_SOH "%c%s IN=%s OUT=%s MAC source = %pM MAC dest = %pM proto = 0x%04x", '0' + loginfo->u.log.level, prefix, in ? in->name : "", out ? out->name : "", eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, @@ -92,7 +96,7 @@ ebt_log_packet(u_int8_t pf, unsigned int hooknum, bitmask = NF_LOG_MASK; if ((bitmask & EBT_LOG_IP) && eth_hdr(skb)->h_proto == - htons(ETH_P_IP)){ + htons(ETH_P_IP)) { const struct iphdr *ih; struct iphdr _iph; @@ -107,12 +111,13 @@ ebt_log_packet(u_int8_t pf, unsigned int hooknum, goto out; } -#if defined(CONFIG_BRIDGE_EBT_IP6) || defined(CONFIG_BRIDGE_EBT_IP6_MODULE) +#if IS_ENABLED(CONFIG_BRIDGE_EBT_IP6) if ((bitmask & EBT_LOG_IP6) && eth_hdr(skb)->h_proto == htons(ETH_P_IPV6)) { const struct ipv6hdr *ih; struct ipv6hdr _iph; uint8_t nexthdr; + __be16 frag_off; int offset_ph; ih = skb_header_pointer(skb, 0, sizeof(_iph), &_iph); @@ -123,7 +128,7 @@ ebt_log_packet(u_int8_t pf, unsigned int hooknum, printk(" IPv6 SRC=%pI6 IPv6 DST=%pI6, IPv6 priority=0x%01X, Next Header=%d", &ih->saddr, &ih->daddr, ih->priority, ih->nexthdr); nexthdr = ih->nexthdr; - offset_ph = ipv6_skip_exthdr(skb, sizeof(_iph), &nexthdr); + offset_ph = ipv6_skip_exthdr(skb, sizeof(_iph), &nexthdr, &frag_off); if (offset_ph == -1) goto out; print_ports(skb, nexthdr, offset_ph); @@ -171,21 +176,22 @@ out: } static unsigned int -ebt_log_tg(struct sk_buff *skb, const struct xt_target_param *par) +ebt_log_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ebt_log_info *info = par->targinfo; struct nf_loginfo li; + struct net *net = dev_net(par->in ? par->in : par->out); li.type = NF_LOG_TYPE_LOG; li.u.log.level = info->loglevel; li.u.log.logflags = info->bitmask; if (info->bitmask & EBT_LOG_NFLOG) - nf_log_packet(NFPROTO_BRIDGE, par->hooknum, skb, par->in, - par->out, &li, "%s", info->prefix); + nf_log_packet(net, NFPROTO_BRIDGE, par->hooknum, skb, + par->in, par->out, &li, "%s", info->prefix); else - ebt_log_packet(NFPROTO_BRIDGE, par->hooknum, skb, par->in, - par->out, &li, info->prefix); + ebt_log_packet(net, NFPROTO_BRIDGE, par->hooknum, skb, par->in, + par->out, &li, info->prefix); return EBT_CONTINUE; } @@ -195,7 +201,7 @@ static struct xt_target ebt_log_tg_reg __read_mostly = { .family = NFPROTO_BRIDGE, .target = ebt_log_tg, .checkentry = ebt_log_tg_check, - .targetsize = XT_ALIGN(sizeof(struct ebt_log_info)), + .targetsize = sizeof(struct ebt_log_info), .me = THIS_MODULE, }; @@ -205,19 +211,47 @@ static struct nf_logger ebt_log_logger __read_mostly = { .me = THIS_MODULE, }; +static int __net_init ebt_log_net_init(struct net *net) +{ + nf_log_set(net, NFPROTO_BRIDGE, &ebt_log_logger); + return 0; +} + +static void __net_exit ebt_log_net_fini(struct net *net) +{ + nf_log_unset(net, &ebt_log_logger); +} + +static struct pernet_operations ebt_log_net_ops = { + .init = ebt_log_net_init, + .exit = ebt_log_net_fini, +}; + static int __init ebt_log_init(void) { int ret; + ret = register_pernet_subsys(&ebt_log_net_ops); + if (ret < 0) + goto err_pernet; + ret = xt_register_target(&ebt_log_tg_reg); if (ret < 0) - return ret; + goto err_target; + nf_log_register(NFPROTO_BRIDGE, &ebt_log_logger); - return 0; + + return ret; + +err_target: + unregister_pernet_subsys(&ebt_log_net_ops); +err_pernet: + return ret; } static void __exit ebt_log_fini(void) { + unregister_pernet_subsys(&ebt_log_net_ops); nf_log_unregister(&ebt_log_logger); xt_unregister_target(&ebt_log_tg_reg); } diff --git a/net/bridge/netfilter/ebt_mark.c b/net/bridge/netfilter/ebt_mark.c index 2fee7e8e2e9..66697cbd0a8 100644 --- a/net/bridge/netfilter/ebt_mark.c +++ b/net/bridge/netfilter/ebt_mark.c @@ -19,7 +19,7 @@ #include <linux/netfilter_bridge/ebt_mark_t.h> static unsigned int -ebt_mark_tg(struct sk_buff *skb, const struct xt_target_param *par) +ebt_mark_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ebt_mark_t_info *info = par->targinfo; int action = info->target & -16; @@ -36,22 +36,48 @@ ebt_mark_tg(struct sk_buff *skb, const struct xt_target_param *par) return info->target | ~EBT_VERDICT_BITS; } -static bool ebt_mark_tg_check(const struct xt_tgchk_param *par) +static int ebt_mark_tg_check(const struct xt_tgchk_param *par) { const struct ebt_mark_t_info *info = par->targinfo; int tmp; tmp = info->target | ~EBT_VERDICT_BITS; if (BASE_CHAIN && tmp == EBT_RETURN) - return false; + return -EINVAL; if (tmp < -NUM_STANDARD_TARGETS || tmp >= 0) - return false; + return -EINVAL; tmp = info->target & ~EBT_VERDICT_BITS; if (tmp != MARK_SET_VALUE && tmp != MARK_OR_VALUE && tmp != MARK_AND_VALUE && tmp != MARK_XOR_VALUE) - return false; - return true; + return -EINVAL; + return 0; } +#ifdef CONFIG_COMPAT +struct compat_ebt_mark_t_info { + compat_ulong_t mark; + compat_uint_t target; +}; + +static void mark_tg_compat_from_user(void *dst, const void *src) +{ + const struct compat_ebt_mark_t_info *user = src; + struct ebt_mark_t_info *kern = dst; + + kern->mark = user->mark; + kern->target = user->target; +} + +static int mark_tg_compat_to_user(void __user *dst, const void *src) +{ + struct compat_ebt_mark_t_info __user *user = dst; + const struct ebt_mark_t_info *kern = src; + + if (put_user(kern->mark, &user->mark) || + put_user(kern->target, &user->target)) + return -EFAULT; + return 0; +} +#endif static struct xt_target ebt_mark_tg_reg __read_mostly = { .name = "mark", @@ -59,7 +85,12 @@ static struct xt_target ebt_mark_tg_reg __read_mostly = { .family = NFPROTO_BRIDGE, .target = ebt_mark_tg, .checkentry = ebt_mark_tg_check, - .targetsize = XT_ALIGN(sizeof(struct ebt_mark_t_info)), + .targetsize = sizeof(struct ebt_mark_t_info), +#ifdef CONFIG_COMPAT + .compatsize = sizeof(struct compat_ebt_mark_t_info), + .compat_from_user = mark_tg_compat_from_user, + .compat_to_user = mark_tg_compat_to_user, +#endif .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebt_mark_m.c b/net/bridge/netfilter/ebt_mark_m.c index ea570f214b1..d98baefc4c7 100644 --- a/net/bridge/netfilter/ebt_mark_m.c +++ b/net/bridge/netfilter/ebt_mark_m.c @@ -13,7 +13,7 @@ #include <linux/netfilter_bridge/ebt_mark_m.h> static bool -ebt_mark_mt(const struct sk_buff *skb, const struct xt_match_param *par) +ebt_mark_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct ebt_mark_m_info *info = par->matchinfo; @@ -22,26 +22,63 @@ ebt_mark_mt(const struct sk_buff *skb, const struct xt_match_param *par) return ((skb->mark & info->mask) == info->mark) ^ info->invert; } -static bool ebt_mark_mt_check(const struct xt_mtchk_param *par) +static int ebt_mark_mt_check(const struct xt_mtchk_param *par) { const struct ebt_mark_m_info *info = par->matchinfo; if (info->bitmask & ~EBT_MARK_MASK) - return false; + return -EINVAL; if ((info->bitmask & EBT_MARK_OR) && (info->bitmask & EBT_MARK_AND)) - return false; + return -EINVAL; if (!info->bitmask) - return false; - return true; + return -EINVAL; + return 0; } + +#ifdef CONFIG_COMPAT +struct compat_ebt_mark_m_info { + compat_ulong_t mark, mask; + uint8_t invert, bitmask; +}; + +static void mark_mt_compat_from_user(void *dst, const void *src) +{ + const struct compat_ebt_mark_m_info *user = src; + struct ebt_mark_m_info *kern = dst; + + kern->mark = user->mark; + kern->mask = user->mask; + kern->invert = user->invert; + kern->bitmask = user->bitmask; +} + +static int mark_mt_compat_to_user(void __user *dst, const void *src) +{ + struct compat_ebt_mark_m_info __user *user = dst; + const struct ebt_mark_m_info *kern = src; + + if (put_user(kern->mark, &user->mark) || + put_user(kern->mask, &user->mask) || + put_user(kern->invert, &user->invert) || + put_user(kern->bitmask, &user->bitmask)) + return -EFAULT; + return 0; +} +#endif + static struct xt_match ebt_mark_mt_reg __read_mostly = { .name = "mark_m", .revision = 0, .family = NFPROTO_BRIDGE, .match = ebt_mark_mt, .checkentry = ebt_mark_mt_check, - .matchsize = XT_ALIGN(sizeof(struct ebt_mark_m_info)), + .matchsize = sizeof(struct ebt_mark_m_info), +#ifdef CONFIG_COMPAT + .compatsize = sizeof(struct compat_ebt_mark_m_info), + .compat_from_user = mark_mt_compat_from_user, + .compat_to_user = mark_mt_compat_to_user, +#endif .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebt_nflog.c b/net/bridge/netfilter/ebt_nflog.c index 2a63d996dd4..59ac7952010 100644 --- a/net/bridge/netfilter/ebt_nflog.c +++ b/net/bridge/netfilter/ebt_nflog.c @@ -20,29 +20,30 @@ #include <net/netfilter/nf_log.h> static unsigned int -ebt_nflog_tg(struct sk_buff *skb, const struct xt_target_param *par) +ebt_nflog_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ebt_nflog_info *info = par->targinfo; struct nf_loginfo li; + struct net *net = dev_net(par->in ? par->in : par->out); li.type = NF_LOG_TYPE_ULOG; li.u.ulog.copy_len = info->len; li.u.ulog.group = info->group; li.u.ulog.qthreshold = info->threshold; - nf_log_packet(PF_BRIDGE, par->hooknum, skb, par->in, par->out, - &li, "%s", info->prefix); + nf_log_packet(net, PF_BRIDGE, par->hooknum, skb, par->in, + par->out, &li, "%s", info->prefix); return EBT_CONTINUE; } -static bool ebt_nflog_tg_check(const struct xt_tgchk_param *par) +static int ebt_nflog_tg_check(const struct xt_tgchk_param *par) { struct ebt_nflog_info *info = par->targinfo; if (info->flags & ~EBT_NFLOG_MASK) - return false; + return -EINVAL; info->prefix[EBT_NFLOG_PREFIX_SIZE - 1] = '\0'; - return true; + return 0; } static struct xt_target ebt_nflog_tg_reg __read_mostly = { @@ -51,7 +52,7 @@ static struct xt_target ebt_nflog_tg_reg __read_mostly = { .family = NFPROTO_BRIDGE, .target = ebt_nflog_tg, .checkentry = ebt_nflog_tg_check, - .targetsize = XT_ALIGN(sizeof(struct ebt_nflog_info)), + .targetsize = sizeof(struct ebt_nflog_info), .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebt_pkttype.c b/net/bridge/netfilter/ebt_pkttype.c index 883e96e2a54..496a5651530 100644 --- a/net/bridge/netfilter/ebt_pkttype.c +++ b/net/bridge/netfilter/ebt_pkttype.c @@ -13,21 +13,21 @@ #include <linux/netfilter_bridge/ebt_pkttype.h> static bool -ebt_pkttype_mt(const struct sk_buff *skb, const struct xt_match_param *par) +ebt_pkttype_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct ebt_pkttype_info *info = par->matchinfo; return (skb->pkt_type == info->pkt_type) ^ info->invert; } -static bool ebt_pkttype_mt_check(const struct xt_mtchk_param *par) +static int ebt_pkttype_mt_check(const struct xt_mtchk_param *par) { const struct ebt_pkttype_info *info = par->matchinfo; if (info->invert != 0 && info->invert != 1) - return false; + return -EINVAL; /* Allow any pkt_type value */ - return true; + return 0; } static struct xt_match ebt_pkttype_mt_reg __read_mostly = { @@ -36,7 +36,7 @@ static struct xt_match ebt_pkttype_mt_reg __read_mostly = { .family = NFPROTO_BRIDGE, .match = ebt_pkttype_mt, .checkentry = ebt_pkttype_mt_check, - .matchsize = XT_ALIGN(sizeof(struct ebt_pkttype_info)), + .matchsize = sizeof(struct ebt_pkttype_info), .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebt_redirect.c b/net/bridge/netfilter/ebt_redirect.c index c8a49f7a57b..203964997a5 100644 --- a/net/bridge/netfilter/ebt_redirect.c +++ b/net/bridge/netfilter/ebt_redirect.c @@ -16,7 +16,7 @@ #include <linux/netfilter_bridge/ebt_redirect.h> static unsigned int -ebt_redirect_tg(struct sk_buff *skb, const struct xt_target_param *par) +ebt_redirect_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ebt_redirect_info *info = par->targinfo; @@ -24,31 +24,32 @@ ebt_redirect_tg(struct sk_buff *skb, const struct xt_target_param *par) return EBT_DROP; if (par->hooknum != NF_BR_BROUTING) - memcpy(eth_hdr(skb)->h_dest, - par->in->br_port->br->dev->dev_addr, ETH_ALEN); + /* rcu_read_lock()ed by nf_hook_slow */ + ether_addr_copy(eth_hdr(skb)->h_dest, + br_port_get_rcu(par->in)->br->dev->dev_addr); else - memcpy(eth_hdr(skb)->h_dest, par->in->dev_addr, ETH_ALEN); + ether_addr_copy(eth_hdr(skb)->h_dest, par->in->dev_addr); skb->pkt_type = PACKET_HOST; return info->target; } -static bool ebt_redirect_tg_check(const struct xt_tgchk_param *par) +static int ebt_redirect_tg_check(const struct xt_tgchk_param *par) { const struct ebt_redirect_info *info = par->targinfo; unsigned int hook_mask; if (BASE_CHAIN && info->target == EBT_RETURN) - return false; + return -EINVAL; hook_mask = par->hook_mask & ~(1 << NF_BR_NUMHOOKS); if ((strcmp(par->table, "nat") != 0 || hook_mask & ~(1 << NF_BR_PRE_ROUTING)) && (strcmp(par->table, "broute") != 0 || hook_mask & ~(1 << NF_BR_BROUTING))) - return false; + return -EINVAL; if (INVALID_TARGET) - return false; - return true; + return -EINVAL; + return 0; } static struct xt_target ebt_redirect_tg_reg __read_mostly = { @@ -59,7 +60,7 @@ static struct xt_target ebt_redirect_tg_reg __read_mostly = { (1 << NF_BR_BROUTING), .target = ebt_redirect_tg, .checkentry = ebt_redirect_tg_check, - .targetsize = XT_ALIGN(sizeof(struct ebt_redirect_info)), + .targetsize = sizeof(struct ebt_redirect_info), .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebt_snat.c b/net/bridge/netfilter/ebt_snat.c index 8d04d4c302b..e56ccd060d2 100644 --- a/net/bridge/netfilter/ebt_snat.c +++ b/net/bridge/netfilter/ebt_snat.c @@ -17,14 +17,14 @@ #include <linux/netfilter_bridge/ebt_nat.h> static unsigned int -ebt_snat_tg(struct sk_buff *skb, const struct xt_target_param *par) +ebt_snat_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ebt_nat_info *info = par->targinfo; if (!skb_make_writable(skb, 0)) return EBT_DROP; - memcpy(eth_hdr(skb)->h_source, info->mac, ETH_ALEN); + ether_addr_copy(eth_hdr(skb)->h_source, info->mac); if (!(info->target & NAT_ARP_BIT) && eth_hdr(skb)->h_proto == htons(ETH_P_ARP)) { const struct arphdr *ap; @@ -35,28 +35,28 @@ ebt_snat_tg(struct sk_buff *skb, const struct xt_target_param *par) return EBT_DROP; if (ap->ar_hln != ETH_ALEN) goto out; - if (skb_store_bits(skb, sizeof(_ah), info->mac,ETH_ALEN)) + if (skb_store_bits(skb, sizeof(_ah), info->mac, ETH_ALEN)) return EBT_DROP; } out: return info->target | ~EBT_VERDICT_BITS; } -static bool ebt_snat_tg_check(const struct xt_tgchk_param *par) +static int ebt_snat_tg_check(const struct xt_tgchk_param *par) { const struct ebt_nat_info *info = par->targinfo; int tmp; tmp = info->target | ~EBT_VERDICT_BITS; if (BASE_CHAIN && tmp == EBT_RETURN) - return false; + return -EINVAL; if (tmp < -NUM_STANDARD_TARGETS || tmp >= 0) - return false; + return -EINVAL; tmp = info->target | EBT_VERDICT_BITS; if ((tmp & ~NAT_ARP_BIT) != ~NAT_ARP_BIT) - return false; - return true; + return -EINVAL; + return 0; } static struct xt_target ebt_snat_tg_reg __read_mostly = { @@ -67,7 +67,7 @@ static struct xt_target ebt_snat_tg_reg __read_mostly = { .hooks = (1 << NF_BR_NUMHOOKS) | (1 << NF_BR_POST_ROUTING), .target = ebt_snat_tg, .checkentry = ebt_snat_tg_check, - .targetsize = XT_ALIGN(sizeof(struct ebt_nat_info)), + .targetsize = sizeof(struct ebt_nat_info), .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebt_stp.c b/net/bridge/netfilter/ebt_stp.c index 75e29a9cebd..071d87214dd 100644 --- a/net/bridge/netfilter/ebt_stp.c +++ b/net/bridge/netfilter/ebt_stp.c @@ -120,7 +120,7 @@ static bool ebt_filter_config(const struct ebt_stp_info *info, } static bool -ebt_stp_mt(const struct sk_buff *skb, const struct xt_match_param *par) +ebt_stp_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct ebt_stp_info *info = par->matchinfo; const struct stp_header *sp; @@ -153,7 +153,7 @@ ebt_stp_mt(const struct sk_buff *skb, const struct xt_match_param *par) return true; } -static bool ebt_stp_mt_check(const struct xt_mtchk_param *par) +static int ebt_stp_mt_check(const struct xt_mtchk_param *par) { const struct ebt_stp_info *info = par->matchinfo; const uint8_t bridge_ula[6] = {0x01, 0x80, 0xc2, 0x00, 0x00, 0x00}; @@ -162,13 +162,13 @@ static bool ebt_stp_mt_check(const struct xt_mtchk_param *par) if (info->bitmask & ~EBT_STP_MASK || info->invflags & ~EBT_STP_MASK || !(info->bitmask & EBT_STP_MASK)) - return false; + return -EINVAL; /* Make sure the match only receives stp frames */ - if (compare_ether_addr(e->destmac, bridge_ula) || - compare_ether_addr(e->destmsk, msk) || !(e->bitmask & EBT_DESTMAC)) - return false; + if (!ether_addr_equal(e->destmac, bridge_ula) || + !ether_addr_equal(e->destmsk, msk) || !(e->bitmask & EBT_DESTMAC)) + return -EINVAL; - return true; + return 0; } static struct xt_match ebt_stp_mt_reg __read_mostly = { @@ -177,7 +177,7 @@ static struct xt_match ebt_stp_mt_reg __read_mostly = { .family = NFPROTO_BRIDGE, .match = ebt_stp_mt, .checkentry = ebt_stp_mt_check, - .matchsize = XT_ALIGN(sizeof(struct ebt_stp_info)), + .matchsize = sizeof(struct ebt_stp_info), .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebt_ulog.c b/net/bridge/netfilter/ebt_ulog.c index ce50688a643..7c470c371e1 100644 --- a/net/bridge/netfilter/ebt_ulog.c +++ b/net/bridge/netfilter/ebt_ulog.c @@ -27,25 +27,24 @@ * flushed even if it is not full yet. * */ - +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> +#include <linux/slab.h> #include <linux/spinlock.h> #include <linux/socket.h> #include <linux/skbuff.h> #include <linux/kernel.h> #include <linux/timer.h> -#include <linux/netlink.h> +#include <net/netlink.h> #include <linux/netdevice.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_bridge/ebtables.h> #include <linux/netfilter_bridge/ebt_ulog.h> #include <net/netfilter/nf_log.h> +#include <net/netns/generic.h> #include <net/sock.h> #include "../br_private.h" -#define PRINTR(format, args...) do { if (net_ratelimit()) \ - printk(format , ## args); } while (0) - static unsigned int nlbufsiz = NLMSG_GOODSIZE; module_param(nlbufsiz, uint, 0600); MODULE_PARM_DESC(nlbufsiz, "netlink buffer size (number of bytes) " @@ -64,16 +63,24 @@ typedef struct { spinlock_t lock; /* the per-queue lock */ } ebt_ulog_buff_t; -static ebt_ulog_buff_t ulog_buffers[EBT_ULOG_MAXNLGROUPS]; -static struct sock *ebtulognl; +static int ebt_ulog_net_id __read_mostly; +struct ebt_ulog_net { + unsigned int nlgroup[EBT_ULOG_MAXNLGROUPS]; + ebt_ulog_buff_t ulog_buffers[EBT_ULOG_MAXNLGROUPS]; + struct sock *ebtulognl; +}; + +static struct ebt_ulog_net *ebt_ulog_pernet(struct net *net) +{ + return net_generic(net, ebt_ulog_net_id); +} /* send one ulog_buff_t to userspace */ -static void ulog_send(unsigned int nlgroup) +static void ulog_send(struct ebt_ulog_net *ebt, unsigned int nlgroup) { - ebt_ulog_buff_t *ub = &ulog_buffers[nlgroup]; + ebt_ulog_buff_t *ub = &ebt->ulog_buffers[nlgroup]; - if (timer_pending(&ub->timer)) - del_timer(&ub->timer); + del_timer(&ub->timer); if (!ub->skb) return; @@ -83,7 +90,7 @@ static void ulog_send(unsigned int nlgroup) ub->lastnlh->nlmsg_type = NLMSG_DONE; NETLINK_CB(ub->skb).dst_group = nlgroup + 1; - netlink_broadcast(ebtulognl, ub->skb, 0, nlgroup + 1, GFP_ATOMIC); + netlink_broadcast(ebt->ebtulognl, ub->skb, 0, nlgroup + 1, GFP_ATOMIC); ub->qlen = 0; ub->skb = NULL; @@ -92,10 +99,15 @@ static void ulog_send(unsigned int nlgroup) /* timer function to flush queue in flushtimeout time */ static void ulog_timer(unsigned long data) { - spin_lock_bh(&ulog_buffers[data].lock); - if (ulog_buffers[data].skb) - ulog_send(data); - spin_unlock_bh(&ulog_buffers[data].lock); + struct ebt_ulog_net *ebt = container_of((void *)data, + struct ebt_ulog_net, + nlgroup[*(unsigned int *)data]); + + ebt_ulog_buff_t *ub = &ebt->ulog_buffers[*(unsigned int *)data]; + spin_lock_bh(&ub->lock); + if (ub->skb) + ulog_send(ebt, *(unsigned int *)data); + spin_unlock_bh(&ub->lock); } static struct sk_buff *ulog_alloc_skb(unsigned int size) @@ -104,32 +116,34 @@ static struct sk_buff *ulog_alloc_skb(unsigned int size) unsigned int n; n = max(size, nlbufsiz); - skb = alloc_skb(n, GFP_ATOMIC); + skb = alloc_skb(n, GFP_ATOMIC | __GFP_NOWARN); if (!skb) { - PRINTR(KERN_ERR "ebt_ulog: can't alloc whole buffer " - "of size %ub!\n", n); if (n > size) { /* try to allocate only as much as we need for * current packet */ skb = alloc_skb(size, GFP_ATOMIC); if (!skb) - PRINTR(KERN_ERR "ebt_ulog: can't even allocate " - "buffer of size %ub\n", size); + pr_debug("cannot even allocate buffer of size %ub\n", + size); } } return skb; } -static void ebt_ulog_packet(unsigned int hooknr, const struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, - const struct ebt_ulog_info *uloginfo, const char *prefix) +static void ebt_ulog_packet(struct net *net, unsigned int hooknr, + const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const struct ebt_ulog_info *uloginfo, + const char *prefix) { ebt_ulog_packet_msg_t *pm; size_t size, copy_len; struct nlmsghdr *nlh; + struct ebt_ulog_net *ebt = ebt_ulog_pernet(net); unsigned int group = uloginfo->nlgroup; - ebt_ulog_buff_t *ub = &ulog_buffers[group]; + ebt_ulog_buff_t *ub = &ebt->ulog_buffers[group]; spinlock_t *lock = &ub->lock; ktime_t kt; @@ -139,10 +153,9 @@ static void ebt_ulog_packet(unsigned int hooknr, const struct sk_buff *skb, else copy_len = uloginfo->cprange; - size = NLMSG_SPACE(sizeof(*pm) + copy_len); + size = nlmsg_total_size(sizeof(*pm) + copy_len); if (size > nlbufsiz) { - PRINTR("ebt_ulog: Size %Zd needed, but nlbufsiz=%d\n", - size, nlbufsiz); + pr_debug("Size %Zd needed, but nlbufsiz=%d\n", size, nlbufsiz); return; } @@ -150,19 +163,25 @@ static void ebt_ulog_packet(unsigned int hooknr, const struct sk_buff *skb, if (!ub->skb) { if (!(ub->skb = ulog_alloc_skb(size))) - goto alloc_failure; + goto unlock; } else if (size > skb_tailroom(ub->skb)) { - ulog_send(group); + ulog_send(ebt, group); if (!(ub->skb = ulog_alloc_skb(size))) - goto alloc_failure; + goto unlock; } - nlh = NLMSG_PUT(ub->skb, 0, ub->qlen, 0, - size - NLMSG_ALIGN(sizeof(*nlh))); + nlh = nlmsg_put(ub->skb, 0, ub->qlen, 0, + size - NLMSG_ALIGN(sizeof(*nlh)), 0); + if (!nlh) { + kfree_skb(ub->skb); + ub->skb = NULL; + goto unlock; + } ub->qlen++; - pm = NLMSG_DATA(nlh); + pm = nlmsg_data(nlh); + memset(pm, 0, sizeof(*pm)); /* Fill in the ulog data */ pm->version = EBT_ULOG_VERSION; @@ -175,25 +194,23 @@ static void ebt_ulog_packet(unsigned int hooknr, const struct sk_buff *skb, pm->hook = hooknr; if (uloginfo->prefix != NULL) strcpy(pm->prefix, uloginfo->prefix); - else - *(pm->prefix) = '\0'; if (in) { strcpy(pm->physindev, in->name); /* If in isn't a bridge, then physindev==indev */ - if (in->br_port) - strcpy(pm->indev, in->br_port->br->dev->name); + if (br_port_exists(in)) + /* rcu_read_lock()ed by nf_hook_slow */ + strcpy(pm->indev, br_port_get_rcu(in)->br->dev->name); else strcpy(pm->indev, in->name); - } else - pm->indev[0] = pm->physindev[0] = '\0'; + } if (out) { /* If out exists, then out is a bridge port */ strcpy(pm->physoutdev, out->name); - strcpy(pm->outdev, out->br_port->br->dev->name); - } else - pm->outdev[0] = pm->physoutdev[0] = '\0'; + /* rcu_read_lock()ed by nf_hook_slow */ + strcpy(pm->outdev, br_port_get_rcu(out)->br->dev->name); + } if (skb_copy_bits(skb, -ETH_HLEN, pm->data, copy_len) < 0) BUG(); @@ -204,7 +221,7 @@ static void ebt_ulog_packet(unsigned int hooknr, const struct sk_buff *skb, ub->lastnlh = nlh; if (ub->qlen >= uloginfo->qthreshold) - ulog_send(group); + ulog_send(ebt, group); else if (!timer_pending(&ub->timer)) { ub->timer.expires = jiffies + flushtimeout * HZ / 100; add_timer(&ub->timer); @@ -212,19 +229,10 @@ static void ebt_ulog_packet(unsigned int hooknr, const struct sk_buff *skb, unlock: spin_unlock_bh(lock); - - return; - -nlmsg_failure: - printk(KERN_CRIT "ebt_ulog: error during NLMSG_PUT. This should " - "not happen, please report to author.\n"); - goto unlock; -alloc_failure: - goto unlock; } /* this function is registered with the netfilter core */ -static void ebt_log_packet(u_int8_t pf, unsigned int hooknum, +static void ebt_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum, const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, const struct nf_loginfo *li, const char *prefix) @@ -243,30 +251,38 @@ static void ebt_log_packet(u_int8_t pf, unsigned int hooknum, strlcpy(loginfo.prefix, prefix, sizeof(loginfo.prefix)); } - ebt_ulog_packet(hooknum, skb, in, out, &loginfo, prefix); + ebt_ulog_packet(net, hooknum, skb, in, out, &loginfo, prefix); } static unsigned int -ebt_ulog_tg(struct sk_buff *skb, const struct xt_target_param *par) +ebt_ulog_tg(struct sk_buff *skb, const struct xt_action_param *par) { - ebt_ulog_packet(par->hooknum, skb, par->in, par->out, + struct net *net = dev_net(par->in ? par->in : par->out); + + ebt_ulog_packet(net, par->hooknum, skb, par->in, par->out, par->targinfo, NULL); return EBT_CONTINUE; } -static bool ebt_ulog_tg_check(const struct xt_tgchk_param *par) +static int ebt_ulog_tg_check(const struct xt_tgchk_param *par) { struct ebt_ulog_info *uloginfo = par->targinfo; + if (!par->net->xt.ebt_ulog_warn_deprecated) { + pr_info("ebt_ulog is deprecated and it will be removed soon, " + "use ebt_nflog instead\n"); + par->net->xt.ebt_ulog_warn_deprecated = true; + } + if (uloginfo->nlgroup > 31) - return false; + return -EINVAL; uloginfo->prefix[EBT_ULOG_PREFIX_LEN - 1] = '\0'; if (uloginfo->qthreshold > EBT_ULOG_MAX_QLEN) uloginfo->qthreshold = EBT_ULOG_MAX_QLEN; - return true; + return 0; } static struct xt_target ebt_ulog_tg_reg __read_mostly = { @@ -275,7 +291,7 @@ static struct xt_target ebt_ulog_tg_reg __read_mostly = { .family = NFPROTO_BRIDGE, .target = ebt_ulog_tg, .checkentry = ebt_ulog_tg_check, - .targetsize = XT_ALIGN(sizeof(struct ebt_ulog_info)), + .targetsize = sizeof(struct ebt_ulog_info), .me = THIS_MODULE, }; @@ -285,59 +301,89 @@ static struct nf_logger ebt_ulog_logger __read_mostly = { .me = THIS_MODULE, }; -static int __init ebt_ulog_init(void) +static int __net_init ebt_ulog_net_init(struct net *net) { - int ret; int i; + struct ebt_ulog_net *ebt = ebt_ulog_pernet(net); - if (nlbufsiz >= 128*1024) { - printk(KERN_NOTICE "ebt_ulog: Netlink buffer has to be <= 128kB," - " please try a smaller nlbufsiz parameter.\n"); - return -EINVAL; - } + struct netlink_kernel_cfg cfg = { + .groups = EBT_ULOG_MAXNLGROUPS, + }; /* initialize ulog_buffers */ for (i = 0; i < EBT_ULOG_MAXNLGROUPS; i++) { - setup_timer(&ulog_buffers[i].timer, ulog_timer, i); - spin_lock_init(&ulog_buffers[i].lock); - } - - ebtulognl = netlink_kernel_create(&init_net, NETLINK_NFLOG, - EBT_ULOG_MAXNLGROUPS, NULL, NULL, - THIS_MODULE); - if (!ebtulognl) { - printk(KERN_WARNING KBUILD_MODNAME ": out of memory trying to " - "call netlink_kernel_create\n"); - ret = -ENOMEM; - } else if ((ret = xt_register_target(&ebt_ulog_tg_reg)) != 0) { - netlink_kernel_release(ebtulognl); + ebt->nlgroup[i] = i; + setup_timer(&ebt->ulog_buffers[i].timer, ulog_timer, + (unsigned long)&ebt->nlgroup[i]); + spin_lock_init(&ebt->ulog_buffers[i].lock); } - if (ret == 0) - nf_log_register(NFPROTO_BRIDGE, &ebt_ulog_logger); + ebt->ebtulognl = netlink_kernel_create(net, NETLINK_NFLOG, &cfg); + if (!ebt->ebtulognl) + return -ENOMEM; - return ret; + nf_log_set(net, NFPROTO_BRIDGE, &ebt_ulog_logger); + return 0; } -static void __exit ebt_ulog_fini(void) +static void __net_exit ebt_ulog_net_fini(struct net *net) { - ebt_ulog_buff_t *ub; int i; + struct ebt_ulog_net *ebt = ebt_ulog_pernet(net); - nf_log_unregister(&ebt_ulog_logger); - xt_unregister_target(&ebt_ulog_tg_reg); + nf_log_unset(net, &ebt_ulog_logger); for (i = 0; i < EBT_ULOG_MAXNLGROUPS; i++) { - ub = &ulog_buffers[i]; - if (timer_pending(&ub->timer)) - del_timer(&ub->timer); - spin_lock_bh(&ub->lock); + ebt_ulog_buff_t *ub = &ebt->ulog_buffers[i]; + del_timer(&ub->timer); + if (ub->skb) { kfree_skb(ub->skb); ub->skb = NULL; } - spin_unlock_bh(&ub->lock); } - netlink_kernel_release(ebtulognl); + netlink_kernel_release(ebt->ebtulognl); +} + +static struct pernet_operations ebt_ulog_net_ops = { + .init = ebt_ulog_net_init, + .exit = ebt_ulog_net_fini, + .id = &ebt_ulog_net_id, + .size = sizeof(struct ebt_ulog_net), +}; + +static int __init ebt_ulog_init(void) +{ + int ret; + + if (nlbufsiz >= 128*1024) { + pr_warn("Netlink buffer has to be <= 128kB," + "please try a smaller nlbufsiz parameter.\n"); + return -EINVAL; + } + + ret = register_pernet_subsys(&ebt_ulog_net_ops); + if (ret) + goto out_pernet; + + ret = xt_register_target(&ebt_ulog_tg_reg); + if (ret) + goto out_target; + + nf_log_register(NFPROTO_BRIDGE, &ebt_ulog_logger); + + return 0; + +out_target: + unregister_pernet_subsys(&ebt_ulog_net_ops); +out_pernet: + return ret; +} + +static void __exit ebt_ulog_fini(void) +{ + nf_log_unregister(&ebt_ulog_logger); + xt_unregister_target(&ebt_ulog_tg_reg); + unregister_pernet_subsys(&ebt_ulog_net_ops); } module_init(ebt_ulog_init); diff --git a/net/bridge/netfilter/ebt_vlan.c b/net/bridge/netfilter/ebt_vlan.c index 3dddd489328..8d3f8c7651f 100644 --- a/net/bridge/netfilter/ebt_vlan.c +++ b/net/bridge/netfilter/ebt_vlan.c @@ -14,8 +14,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #include <linux/if_ether.h> @@ -26,26 +25,19 @@ #include <linux/netfilter_bridge/ebtables.h> #include <linux/netfilter_bridge/ebt_vlan.h> -static int debug; #define MODULE_VERS "0.6" -module_param(debug, int, 0); -MODULE_PARM_DESC(debug, "debug=1 is turn on debug messages"); MODULE_AUTHOR("Nick Fedchik <nick@fedchik.org.ua>"); MODULE_DESCRIPTION("Ebtables: 802.1Q VLAN tag match"); MODULE_LICENSE("GPL"); - -#define DEBUG_MSG(args...) if (debug) printk (KERN_DEBUG "ebt_vlan: " args) #define GET_BITMASK(_BIT_MASK_) info->bitmask & _BIT_MASK_ #define EXIT_ON_MISMATCH(_MATCH_,_MASK_) {if (!((info->_MATCH_ == _MATCH_)^!!(info->invflags & _MASK_))) return false; } static bool -ebt_vlan_mt(const struct sk_buff *skb, const struct xt_match_param *par) +ebt_vlan_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct ebt_vlan_info *info = par->matchinfo; - const struct vlan_hdr *fp; - struct vlan_hdr _frame; unsigned short TCI; /* Whole TCI, given from parsed frame */ unsigned short id; /* VLAN ID, given from frame TCI */ @@ -53,9 +45,20 @@ ebt_vlan_mt(const struct sk_buff *skb, const struct xt_match_param *par) /* VLAN encapsulated Type/Length field, given from orig frame */ __be16 encap; - fp = skb_header_pointer(skb, 0, sizeof(_frame), &_frame); - if (fp == NULL) - return false; + if (vlan_tx_tag_present(skb)) { + TCI = vlan_tx_tag_get(skb); + encap = skb->protocol; + } else { + const struct vlan_hdr *fp; + struct vlan_hdr _frame; + + fp = skb_header_pointer(skb, 0, sizeof(_frame), &_frame); + if (fp == NULL) + return false; + + TCI = ntohs(fp->h_vlan_TCI); + encap = fp->h_vlan_encapsulated_proto; + } /* Tag Control Information (TCI) consists of the following elements: * - User_priority. The user_priority field is three bits in length, @@ -64,10 +67,8 @@ ebt_vlan_mt(const struct sk_buff *skb, const struct xt_match_param *par) * (CFI) is a single bit flag value. Currently ignored. * - VLAN Identifier (VID). The VID is encoded as * an unsigned binary number. */ - TCI = ntohs(fp->h_vlan_TCI); id = TCI & VLAN_VID_MASK; prio = (TCI >> 13) & 0x7; - encap = fp->h_vlan_encapsulated_proto; /* Checking VLAN Identifier (VID) */ if (GET_BITMASK(EBT_VLAN_ID)) @@ -84,32 +85,31 @@ ebt_vlan_mt(const struct sk_buff *skb, const struct xt_match_param *par) return true; } -static bool ebt_vlan_mt_check(const struct xt_mtchk_param *par) +static int ebt_vlan_mt_check(const struct xt_mtchk_param *par) { struct ebt_vlan_info *info = par->matchinfo; const struct ebt_entry *e = par->entryinfo; /* Is it 802.1Q frame checked? */ if (e->ethproto != htons(ETH_P_8021Q)) { - DEBUG_MSG - ("passed entry proto %2.4X is not 802.1Q (8100)\n", - (unsigned short) ntohs(e->ethproto)); - return false; + pr_debug("passed entry proto %2.4X is not 802.1Q (8100)\n", + ntohs(e->ethproto)); + return -EINVAL; } /* Check for bitmask range * True if even one bit is out of mask */ if (info->bitmask & ~EBT_VLAN_MASK) { - DEBUG_MSG("bitmask %2X is out of mask (%2X)\n", - info->bitmask, EBT_VLAN_MASK); - return false; + pr_debug("bitmask %2X is out of mask (%2X)\n", + info->bitmask, EBT_VLAN_MASK); + return -EINVAL; } /* Check for inversion flags range */ if (info->invflags & ~EBT_VLAN_MASK) { - DEBUG_MSG("inversion flags %2X is out of mask (%2X)\n", - info->invflags, EBT_VLAN_MASK); - return false; + pr_debug("inversion flags %2X is out of mask (%2X)\n", + info->invflags, EBT_VLAN_MASK); + return -EINVAL; } /* Reserved VLAN ID (VID) values @@ -117,14 +117,13 @@ static bool ebt_vlan_mt_check(const struct xt_mtchk_param *par) * 0 - The null VLAN ID. * 1 - The default Port VID (PVID) * 0x0FFF - Reserved for implementation use. - * if_vlan.h: VLAN_GROUP_ARRAY_LEN 4096. */ + * if_vlan.h: VLAN_N_VID 4096. */ if (GET_BITMASK(EBT_VLAN_ID)) { if (!!info->id) { /* if id!=0 => check vid range */ - if (info->id > VLAN_GROUP_ARRAY_LEN) { - DEBUG_MSG - ("id %d is out of range (1-4096)\n", - info->id); - return false; + if (info->id > VLAN_N_VID) { + pr_debug("id %d is out of range (1-4096)\n", + info->id); + return -EINVAL; } /* Note: This is valid VLAN-tagged frame point. * Any value of user_priority are acceptable, @@ -137,9 +136,9 @@ static bool ebt_vlan_mt_check(const struct xt_mtchk_param *par) if (GET_BITMASK(EBT_VLAN_PRIO)) { if ((unsigned char) info->prio > 7) { - DEBUG_MSG("prio %d is out of range (0-7)\n", - info->prio); - return false; + pr_debug("prio %d is out of range (0-7)\n", + info->prio); + return -EINVAL; } } /* Check for encapsulated proto range - it is possible to be @@ -147,14 +146,13 @@ static bool ebt_vlan_mt_check(const struct xt_mtchk_param *par) * if_ether.h: ETH_ZLEN 60 - Min. octets in frame sans FCS */ if (GET_BITMASK(EBT_VLAN_ENCAP)) { if ((unsigned short) ntohs(info->encap) < ETH_ZLEN) { - DEBUG_MSG - ("encap frame length %d is less than minimal\n", - ntohs(info->encap)); - return false; + pr_debug("encap frame length %d is less than " + "minimal\n", ntohs(info->encap)); + return -EINVAL; } } - return true; + return 0; } static struct xt_match ebt_vlan_mt_reg __read_mostly = { @@ -163,15 +161,13 @@ static struct xt_match ebt_vlan_mt_reg __read_mostly = { .family = NFPROTO_BRIDGE, .match = ebt_vlan_mt, .checkentry = ebt_vlan_mt_check, - .matchsize = XT_ALIGN(sizeof(struct ebt_vlan_info)), + .matchsize = sizeof(struct ebt_vlan_info), .me = THIS_MODULE, }; static int __init ebt_vlan_init(void) { - DEBUG_MSG("ebtables 802.1Q extension module v" - MODULE_VERS "\n"); - DEBUG_MSG("module debug=%d\n", !!debug); + pr_debug("ebtables 802.1Q extension module v" MODULE_VERS "\n"); return xt_register_match(&ebt_vlan_mt_reg); } diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c index d32ab13e728..d2cdf5d6e98 100644 --- a/net/bridge/netfilter/ebtable_broute.c +++ b/net/bridge/netfilter/ebtable_broute.c @@ -23,8 +23,7 @@ static struct ebt_entries initial_chain = { .policy = EBT_ACCEPT, }; -static struct ebt_replace_kernel initial_table = -{ +static struct ebt_replace_kernel initial_table = { .name = "broute", .valid_hooks = 1 << NF_BR_BROUTING, .entries_size = sizeof(struct ebt_entries), @@ -41,8 +40,7 @@ static int check(const struct ebt_table_info *info, unsigned int valid_hooks) return 0; } -static const struct ebt_table broute_table = -{ +static const struct ebt_table broute_table = { .name = "broute", .table = &initial_table, .valid_hooks = 1 << NF_BR_BROUTING, @@ -64,14 +62,12 @@ static int ebt_broute(struct sk_buff *skb) static int __net_init broute_net_init(struct net *net) { net->xt.broute_table = ebt_register_table(net, &broute_table); - if (IS_ERR(net->xt.broute_table)) - return PTR_ERR(net->xt.broute_table); - return 0; + return PTR_ERR_OR_ZERO(net->xt.broute_table); } static void __net_exit broute_net_exit(struct net *net) { - ebt_unregister_table(net->xt.broute_table); + ebt_unregister_table(net, net->xt.broute_table); } static struct pernet_operations broute_net_ops = { @@ -87,13 +83,14 @@ static int __init ebtable_broute_init(void) if (ret < 0) return ret; /* see br_input.c */ - rcu_assign_pointer(br_should_route_hook, ebt_broute); + RCU_INIT_POINTER(br_should_route_hook, + (br_should_route_hook_t *)ebt_broute); return 0; } static void __exit ebtable_broute_fini(void) { - rcu_assign_pointer(br_should_route_hook, NULL); + RCU_INIT_POINTER(br_should_route_hook, NULL); synchronize_net(); unregister_pernet_subsys(&broute_net_ops); } diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c index 60b1a6ca718..ce205aabf9c 100644 --- a/net/bridge/netfilter/ebtable_filter.c +++ b/net/bridge/netfilter/ebtable_filter.c @@ -14,8 +14,7 @@ #define FILTER_VALID_HOOKS ((1 << NF_BR_LOCAL_IN) | (1 << NF_BR_FORWARD) | \ (1 << NF_BR_LOCAL_OUT)) -static struct ebt_entries initial_chains[] = -{ +static struct ebt_entries initial_chains[] = { { .name = "INPUT", .policy = EBT_ACCEPT, @@ -30,8 +29,7 @@ static struct ebt_entries initial_chains[] = }, }; -static struct ebt_replace_kernel initial_table = -{ +static struct ebt_replace_kernel initial_table = { .name = "filter", .valid_hooks = FILTER_VALID_HOOKS, .entries_size = 3 * sizeof(struct ebt_entries), @@ -50,8 +48,7 @@ static int check(const struct ebt_table_info *info, unsigned int valid_hooks) return 0; } -static const struct ebt_table frame_filter = -{ +static const struct ebt_table frame_filter = { .name = "filter", .table = &initial_table, .valid_hooks = FILTER_VALID_HOOKS, @@ -60,17 +57,21 @@ static const struct ebt_table frame_filter = }; static unsigned int -ebt_in_hook(unsigned int hook, struct sk_buff *skb, const struct net_device *in, - const struct net_device *out, int (*okfn)(struct sk_buff *)) +ebt_in_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + int (*okfn)(struct sk_buff *)) { - return ebt_do_table(hook, skb, in, out, dev_net(in)->xt.frame_filter); + return ebt_do_table(ops->hooknum, skb, in, out, + dev_net(in)->xt.frame_filter); } static unsigned int -ebt_out_hook(unsigned int hook, struct sk_buff *skb, const struct net_device *in, - const struct net_device *out, int (*okfn)(struct sk_buff *)) +ebt_out_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + int (*okfn)(struct sk_buff *)) { - return ebt_do_table(hook, skb, in, out, dev_net(out)->xt.frame_filter); + return ebt_do_table(ops->hooknum, skb, in, out, + dev_net(out)->xt.frame_filter); } static struct nf_hook_ops ebt_ops_filter[] __read_mostly = { @@ -100,14 +101,12 @@ static struct nf_hook_ops ebt_ops_filter[] __read_mostly = { static int __net_init frame_filter_net_init(struct net *net) { net->xt.frame_filter = ebt_register_table(net, &frame_filter); - if (IS_ERR(net->xt.frame_filter)) - return PTR_ERR(net->xt.frame_filter); - return 0; + return PTR_ERR_OR_ZERO(net->xt.frame_filter); } static void __net_exit frame_filter_net_exit(struct net *net) { - ebt_unregister_table(net->xt.frame_filter); + ebt_unregister_table(net, net->xt.frame_filter); } static struct pernet_operations frame_filter_net_ops = { diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c index 4a98804203b..a0ac2984fb6 100644 --- a/net/bridge/netfilter/ebtable_nat.c +++ b/net/bridge/netfilter/ebtable_nat.c @@ -14,8 +14,7 @@ #define NAT_VALID_HOOKS ((1 << NF_BR_PRE_ROUTING) | (1 << NF_BR_LOCAL_OUT) | \ (1 << NF_BR_POST_ROUTING)) -static struct ebt_entries initial_chains[] = -{ +static struct ebt_entries initial_chains[] = { { .name = "PREROUTING", .policy = EBT_ACCEPT, @@ -30,8 +29,7 @@ static struct ebt_entries initial_chains[] = } }; -static struct ebt_replace_kernel initial_table = -{ +static struct ebt_replace_kernel initial_table = { .name = "nat", .valid_hooks = NAT_VALID_HOOKS, .entries_size = 3 * sizeof(struct ebt_entries), @@ -50,8 +48,7 @@ static int check(const struct ebt_table_info *info, unsigned int valid_hooks) return 0; } -static struct ebt_table frame_nat = -{ +static struct ebt_table frame_nat = { .name = "nat", .table = &initial_table, .valid_hooks = NAT_VALID_HOOKS, @@ -60,17 +57,21 @@ static struct ebt_table frame_nat = }; static unsigned int -ebt_nat_in(unsigned int hook, struct sk_buff *skb, const struct net_device *in - , const struct net_device *out, int (*okfn)(struct sk_buff *)) +ebt_nat_in(const struct nf_hook_ops *ops, struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + int (*okfn)(struct sk_buff *)) { - return ebt_do_table(hook, skb, in, out, dev_net(in)->xt.frame_nat); + return ebt_do_table(ops->hooknum, skb, in, out, + dev_net(in)->xt.frame_nat); } static unsigned int -ebt_nat_out(unsigned int hook, struct sk_buff *skb, const struct net_device *in - , const struct net_device *out, int (*okfn)(struct sk_buff *)) +ebt_nat_out(const struct nf_hook_ops *ops, struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + int (*okfn)(struct sk_buff *)) { - return ebt_do_table(hook, skb, in, out, dev_net(out)->xt.frame_nat); + return ebt_do_table(ops->hooknum, skb, in, out, + dev_net(out)->xt.frame_nat); } static struct nf_hook_ops ebt_ops_nat[] __read_mostly = { @@ -100,14 +101,12 @@ static struct nf_hook_ops ebt_ops_nat[] __read_mostly = { static int __net_init frame_nat_net_init(struct net *net) { net->xt.frame_nat = ebt_register_table(net, &frame_nat); - if (IS_ERR(net->xt.frame_nat)) - return PTR_ERR(net->xt.frame_nat); - return 0; + return PTR_ERR_OR_ZERO(net->xt.frame_nat); } static void __net_exit frame_nat_net_exit(struct net *net) { - ebt_unregister_table(net->xt.frame_nat); + ebt_unregister_table(net, net->xt.frame_nat); } static struct pernet_operations frame_nat_net_ops = { diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index bd1c65425d4..1059ed3bc25 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -14,8 +14,7 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ - - +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kmod.h> #include <linux/module.h> #include <linux/vmalloc.h> @@ -23,6 +22,7 @@ #include <linux/netfilter_bridge/ebtables.h> #include <linux/spinlock.h> #include <linux/mutex.h> +#include <linux/slab.h> #include <asm/uaccess.h> #include <linux/smp.h> #include <linux/cpumask.h> @@ -33,11 +33,6 @@ #define BUGPRINT(format, args...) printk("kernel msg: ebtables bug: please "\ "report to author: "format, ## args) /* #define BUGPRINT(format, args...) */ -#define MEMPRINT(format, args...) printk("kernel msg: ebtables "\ - ": out of memory: "format, ## args) -/* #define MEMPRINT(format, args...) */ - - /* * Each cpu has its own set of counters, so there is no need for write_lock in @@ -56,16 +51,42 @@ static DEFINE_MUTEX(ebt_mutex); +#ifdef CONFIG_COMPAT +static void ebt_standard_compat_from_user(void *dst, const void *src) +{ + int v = *(compat_int_t *)src; + + if (v >= 0) + v += xt_compat_calc_jump(NFPROTO_BRIDGE, v); + memcpy(dst, &v, sizeof(v)); +} + +static int ebt_standard_compat_to_user(void __user *dst, const void *src) +{ + compat_int_t cv = *(int *)src; + + if (cv >= 0) + cv -= xt_compat_calc_jump(NFPROTO_BRIDGE, cv); + return copy_to_user(dst, &cv, sizeof(cv)) ? -EFAULT : 0; +} +#endif + + static struct xt_target ebt_standard_target = { .name = "standard", .revision = 0, .family = NFPROTO_BRIDGE, .targetsize = sizeof(int), +#ifdef CONFIG_COMPAT + .compatsize = sizeof(compat_int_t), + .compat_from_user = ebt_standard_compat_from_user, + .compat_to_user = ebt_standard_compat_to_user, +#endif }; static inline int ebt_do_watcher(const struct ebt_entry_watcher *w, struct sk_buff *skb, - struct xt_target_param *par) + struct xt_action_param *par) { par->target = w->u.watcher; par->targinfo = w->data; @@ -74,15 +95,17 @@ ebt_do_watcher(const struct ebt_entry_watcher *w, struct sk_buff *skb, return 0; } -static inline int ebt_do_match (struct ebt_entry_match *m, - const struct sk_buff *skb, struct xt_match_param *par) +static inline int +ebt_do_match(struct ebt_entry_match *m, const struct sk_buff *skb, + struct xt_action_param *par) { par->match = m->u.match; par->matchinfo = m->data; return m->u.match->match(skb, par) ? EBT_MATCH : EBT_NOMATCH; } -static inline int ebt_dev_check(char *entry, const struct net_device *device) +static inline int +ebt_dev_check(const char *entry, const struct net_device *device) { int i = 0; const char *devname; @@ -95,32 +118,42 @@ static inline int ebt_dev_check(char *entry, const struct net_device *device) /* 1 is the wildcard token */ while (entry[i] != '\0' && entry[i] != 1 && entry[i] == devname[i]) i++; - return (devname[i] != entry[i] && entry[i] != 1); + return devname[i] != entry[i] && entry[i] != 1; } -#define FWINV2(bool,invflg) ((bool) ^ !!(e->invflags & invflg)) +#define FWINV2(bool, invflg) ((bool) ^ !!(e->invflags & invflg)) /* process standard matches */ -static inline int ebt_basic_match(struct ebt_entry *e, struct ethhdr *h, - const struct net_device *in, const struct net_device *out) +static inline int +ebt_basic_match(const struct ebt_entry *e, const struct sk_buff *skb, + const struct net_device *in, const struct net_device *out) { + const struct ethhdr *h = eth_hdr(skb); + const struct net_bridge_port *p; + __be16 ethproto; int verdict, i; + if (vlan_tx_tag_present(skb)) + ethproto = htons(ETH_P_8021Q); + else + ethproto = h->h_proto; + if (e->bitmask & EBT_802_3) { - if (FWINV2(ntohs(h->h_proto) >= 1536, EBT_IPROTO)) + if (FWINV2(ntohs(ethproto) >= ETH_P_802_3_MIN, EBT_IPROTO)) return 1; } else if (!(e->bitmask & EBT_NOPROTO) && - FWINV2(e->ethproto != h->h_proto, EBT_IPROTO)) + FWINV2(e->ethproto != ethproto, EBT_IPROTO)) return 1; if (FWINV2(ebt_dev_check(e->in, in), EBT_IIN)) return 1; if (FWINV2(ebt_dev_check(e->out, out), EBT_IOUT)) return 1; - if ((!in || !in->br_port) ? 0 : FWINV2(ebt_dev_check( - e->logical_in, in->br_port->br->dev), EBT_ILOGICALIN)) + /* rcu_read_lock()ed by nf_hook_slow */ + if (in && (p = br_port_get_rcu(in)) != NULL && + FWINV2(ebt_dev_check(e->logical_in, p->br->dev), EBT_ILOGICALIN)) return 1; - if ((!out || !out->br_port) ? 0 : FWINV2(ebt_dev_check( - e->logical_out, out->br_port->br->dev), EBT_ILOGICALOUT)) + if (out && (p = br_port_get_rcu(out)) != NULL && + FWINV2(ebt_dev_check(e->logical_out, p->br->dev), EBT_ILOGICALOUT)) return 1; if (e->bitmask & EBT_SOURCEMAC) { @@ -156,21 +189,19 @@ unsigned int ebt_do_table (unsigned int hook, struct sk_buff *skb, int i, nentries; struct ebt_entry *point; struct ebt_counter *counter_base, *cb_base; - struct ebt_entry_target *t; + const struct ebt_entry_target *t; int verdict, sp = 0; struct ebt_chainstack *cs; struct ebt_entries *chaininfo; - char *base; - struct ebt_table_info *private; - bool hotdrop = false; - struct xt_match_param mtpar; - struct xt_target_param tgpar; - - mtpar.family = tgpar.family = NFPROTO_BRIDGE; - mtpar.in = tgpar.in = in; - mtpar.out = tgpar.out = out; - mtpar.hotdrop = &hotdrop; - mtpar.hooknum = tgpar.hooknum = hook; + const char *base; + const struct ebt_table_info *private; + struct xt_action_param acpar; + + acpar.family = NFPROTO_BRIDGE; + acpar.in = in; + acpar.out = out; + acpar.hotdrop = false; + acpar.hooknum = hook; read_lock_bh(&table->lock); private = table->private; @@ -188,12 +219,12 @@ unsigned int ebt_do_table (unsigned int hook, struct sk_buff *skb, base = private->entries; i = 0; while (i < nentries) { - if (ebt_basic_match(point, eth_hdr(skb), in, out)) + if (ebt_basic_match(point, skb, in, out)) goto letscontinue; - if (EBT_MATCH_ITERATE(point, ebt_do_match, skb, &mtpar) != 0) + if (EBT_MATCH_ITERATE(point, ebt_do_match, skb, &acpar) != 0) goto letscontinue; - if (hotdrop) { + if (acpar.hotdrop) { read_unlock_bh(&table->lock); return NF_DROP; } @@ -204,7 +235,7 @@ unsigned int ebt_do_table (unsigned int hook, struct sk_buff *skb, /* these should only watch: not modify, nor tell us what to do with the packet */ - EBT_WATCHER_ITERATE(point, ebt_do_watcher, skb, &tgpar); + EBT_WATCHER_ITERATE(point, ebt_do_watcher, skb, &acpar); t = (struct ebt_entry_target *) (((char *)point) + point->target_offset); @@ -212,9 +243,9 @@ unsigned int ebt_do_table (unsigned int hook, struct sk_buff *skb, if (!t->u.target->target) verdict = ((struct ebt_standard_target *)t)->verdict; else { - tgpar.target = t->u.target; - tgpar.targinfo = t->data; - verdict = t->u.target->target(skb, &tgpar); + acpar.target = t->u.target; + acpar.targinfo = t->data; + verdict = t->u.target->target(skb, &acpar); } if (verdict == EBT_ACCEPT) { read_unlock_bh(&table->lock); @@ -339,12 +370,9 @@ ebt_check_match(struct ebt_entry_match *m, struct xt_mtchk_param *par, left - sizeof(struct ebt_entry_match) < m->match_size) return -EINVAL; - match = try_then_request_module(xt_find_match(NFPROTO_BRIDGE, - m->u.name, 0), "ebt_%s", m->u.name); + match = xt_request_find_match(NFPROTO_BRIDGE, m->u.name, 0); if (IS_ERR(match)) return PTR_ERR(match); - if (match == NULL) - return -ENOENT; m->u.match = match; par->match = match; @@ -373,13 +401,9 @@ ebt_check_watcher(struct ebt_entry_watcher *w, struct xt_tgchk_param *par, left - sizeof(struct ebt_entry_watcher) < w->watcher_size) return -EINVAL; - watcher = try_then_request_module( - xt_find_target(NFPROTO_BRIDGE, w->u.name, 0), - "ebt_%s", w->u.name); + watcher = xt_request_find_target(NFPROTO_BRIDGE, w->u.name, 0); if (IS_ERR(watcher)) return PTR_ERR(watcher); - if (watcher == NULL) - return -ENOENT; w->u.watcher = watcher; par->target = watcher; @@ -395,7 +419,7 @@ ebt_check_watcher(struct ebt_entry_watcher *w, struct xt_tgchk_param *par, return 0; } -static int ebt_verify_pointers(struct ebt_replace *repl, +static int ebt_verify_pointers(const struct ebt_replace *repl, struct ebt_table_info *newinfo) { unsigned int limit = repl->entries_size; @@ -442,6 +466,8 @@ static int ebt_verify_pointers(struct ebt_replace *repl, break; if (left < e->next_offset) break; + if (e->next_offset < sizeof(struct ebt_entry)) + return -EINVAL; offset += e->next_offset; } } @@ -466,8 +492,8 @@ static int ebt_verify_pointers(struct ebt_replace *repl, * to parse the userspace data */ static inline int -ebt_check_entry_size_and_hooks(struct ebt_entry *e, - struct ebt_table_info *newinfo, +ebt_check_entry_size_and_hooks(const struct ebt_entry *e, + const struct ebt_table_info *newinfo, unsigned int *n, unsigned int *cnt, unsigned int *totalcnt, unsigned int *udc_cnt) { @@ -561,13 +587,14 @@ ebt_get_udc_positions(struct ebt_entry *e, struct ebt_table_info *newinfo, } static inline int -ebt_cleanup_match(struct ebt_entry_match *m, unsigned int *i) +ebt_cleanup_match(struct ebt_entry_match *m, struct net *net, unsigned int *i) { struct xt_mtdtor_param par; if (i && (*i)-- == 0) return 1; + par.net = net; par.match = m->u.match; par.matchinfo = m->data; par.family = NFPROTO_BRIDGE; @@ -578,13 +605,14 @@ ebt_cleanup_match(struct ebt_entry_match *m, unsigned int *i) } static inline int -ebt_cleanup_watcher(struct ebt_entry_watcher *w, unsigned int *i) +ebt_cleanup_watcher(struct ebt_entry_watcher *w, struct net *net, unsigned int *i) { struct xt_tgdtor_param par; if (i && (*i)-- == 0) return 1; + par.net = net; par.target = w->u.watcher; par.targinfo = w->data; par.family = NFPROTO_BRIDGE; @@ -595,7 +623,7 @@ ebt_cleanup_watcher(struct ebt_entry_watcher *w, unsigned int *i) } static inline int -ebt_cleanup_entry(struct ebt_entry *e, unsigned int *cnt) +ebt_cleanup_entry(struct ebt_entry *e, struct net *net, unsigned int *cnt) { struct xt_tgdtor_param par; struct ebt_entry_target *t; @@ -605,10 +633,11 @@ ebt_cleanup_entry(struct ebt_entry *e, unsigned int *cnt) /* we're done */ if (cnt && (*cnt)-- == 0) return 1; - EBT_WATCHER_ITERATE(e, ebt_cleanup_watcher, NULL); - EBT_MATCH_ITERATE(e, ebt_cleanup_match, NULL); + EBT_WATCHER_ITERATE(e, ebt_cleanup_watcher, net, NULL); + EBT_MATCH_ITERATE(e, ebt_cleanup_match, net, NULL); t = (struct ebt_entry_target *)(((char *)e) + e->target_offset); + par.net = net; par.target = t->u.target; par.targinfo = t->data; par.family = NFPROTO_BRIDGE; @@ -619,7 +648,8 @@ ebt_cleanup_entry(struct ebt_entry *e, unsigned int *cnt) } static inline int -ebt_check_entry(struct ebt_entry *e, struct ebt_table_info *newinfo, +ebt_check_entry(struct ebt_entry *e, struct net *net, + const struct ebt_table_info *newinfo, const char *name, unsigned int *cnt, struct ebt_cl_stack *cl_s, unsigned int udc_cnt) { @@ -671,6 +701,7 @@ ebt_check_entry(struct ebt_entry *e, struct ebt_table_info *newinfo, } i = 0; + mtpar.net = tgpar.net = net; mtpar.table = tgpar.table = name; mtpar.entryinfo = tgpar.entryinfo = e; mtpar.hook_mask = tgpar.hook_mask = hookmask; @@ -685,15 +716,10 @@ ebt_check_entry(struct ebt_entry *e, struct ebt_table_info *newinfo, t = (struct ebt_entry_target *)(((char *)e) + e->target_offset); gap = e->next_offset - e->target_offset; - target = try_then_request_module( - xt_find_target(NFPROTO_BRIDGE, t->u.name, 0), - "ebt_%s", t->u.name); + target = xt_request_find_target(NFPROTO_BRIDGE, t->u.name, 0); if (IS_ERR(target)) { ret = PTR_ERR(target); goto cleanup_watchers; - } else if (target == NULL) { - ret = -ENOENT; - goto cleanup_watchers; } t->u.target = target; @@ -726,9 +752,9 @@ ebt_check_entry(struct ebt_entry *e, struct ebt_table_info *newinfo, (*cnt)++; return 0; cleanup_watchers: - EBT_WATCHER_ITERATE(e, ebt_cleanup_watcher, &j); + EBT_WATCHER_ITERATE(e, ebt_cleanup_watcher, net, &j); cleanup_matches: - EBT_MATCH_ITERATE(e, ebt_cleanup_match, &i); + EBT_MATCH_ITERATE(e, ebt_cleanup_match, net, &i); return ret; } @@ -737,12 +763,12 @@ cleanup_matches: * the hook mask for udc tells us from which base chains the udc can be * accessed. This mask is a parameter to the check() functions of the extensions */ -static int check_chainloops(struct ebt_entries *chain, struct ebt_cl_stack *cl_s, +static int check_chainloops(const struct ebt_entries *chain, struct ebt_cl_stack *cl_s, unsigned int udc_cnt, unsigned int hooknr, char *base) { int i, chain_nr = -1, pos = 0, nentries = chain->nentries, verdict; - struct ebt_entry *e = (struct ebt_entry *)chain->data; - struct ebt_entry_target *t; + const struct ebt_entry *e = (struct ebt_entry *)chain->data; + const struct ebt_entry_target *t; while (pos < nentries || chain_nr != -1) { /* end of udc, go back one 'recursion' step */ @@ -808,7 +834,8 @@ letscontinue: } /* do the parsing of the table/chains/entries/matches/watchers/targets, heh */ -static int translate_table(char *name, struct ebt_table_info *newinfo) +static int translate_table(struct net *net, const char *name, + struct ebt_table_info *newinfo) { unsigned int i, j, k, udc_cnt; int ret; @@ -917,17 +944,17 @@ static int translate_table(char *name, struct ebt_table_info *newinfo) /* used to know what we need to clean up if something goes wrong */ i = 0; ret = EBT_ENTRY_ITERATE(newinfo->entries, newinfo->entries_size, - ebt_check_entry, newinfo, name, &i, cl_s, udc_cnt); + ebt_check_entry, net, newinfo, name, &i, cl_s, udc_cnt); if (ret != 0) { EBT_ENTRY_ITERATE(newinfo->entries, newinfo->entries_size, - ebt_cleanup_entry, &i); + ebt_cleanup_entry, net, &i); } vfree(cl_s); return ret; } /* called under write_lock */ -static void get_counters(struct ebt_counter *oldcounters, +static void get_counters(const struct ebt_counter *oldcounters, struct ebt_counter *counters, unsigned int nentries) { int i, cpu; @@ -949,90 +976,45 @@ static void get_counters(struct ebt_counter *oldcounters, } } -/* replace the table */ -static int do_replace(struct net *net, void __user *user, unsigned int len) +static int do_replace_finish(struct net *net, struct ebt_replace *repl, + struct ebt_table_info *newinfo) { - int ret, i, countersize; - struct ebt_table_info *newinfo; - struct ebt_replace tmp; - struct ebt_table *t; + int ret, i; struct ebt_counter *counterstmp = NULL; /* used to be able to unlock earlier */ struct ebt_table_info *table; - - if (copy_from_user(&tmp, user, sizeof(tmp)) != 0) - return -EFAULT; - - if (len != sizeof(tmp) + tmp.entries_size) { - BUGPRINT("Wrong len argument\n"); - return -EINVAL; - } - - if (tmp.entries_size == 0) { - BUGPRINT("Entries_size never zero\n"); - return -EINVAL; - } - /* overflow check */ - if (tmp.nentries >= ((INT_MAX - sizeof(struct ebt_table_info)) / NR_CPUS - - SMP_CACHE_BYTES) / sizeof(struct ebt_counter)) - return -ENOMEM; - if (tmp.num_counters >= INT_MAX / sizeof(struct ebt_counter)) - return -ENOMEM; - - countersize = COUNTER_OFFSET(tmp.nentries) * nr_cpu_ids; - newinfo = vmalloc(sizeof(*newinfo) + countersize); - if (!newinfo) - return -ENOMEM; - - if (countersize) - memset(newinfo->counters, 0, countersize); - - newinfo->entries = vmalloc(tmp.entries_size); - if (!newinfo->entries) { - ret = -ENOMEM; - goto free_newinfo; - } - if (copy_from_user( - newinfo->entries, tmp.entries, tmp.entries_size) != 0) { - BUGPRINT("Couldn't copy entries from userspace\n"); - ret = -EFAULT; - goto free_entries; - } + struct ebt_table *t; /* the user wants counters back the check on the size is done later, when we have the lock */ - if (tmp.num_counters) { - counterstmp = vmalloc(tmp.num_counters * sizeof(*counterstmp)); - if (!counterstmp) { - ret = -ENOMEM; - goto free_entries; - } + if (repl->num_counters) { + unsigned long size = repl->num_counters * sizeof(*counterstmp); + counterstmp = vmalloc(size); + if (!counterstmp) + return -ENOMEM; } - else - counterstmp = NULL; - /* this can get initialized by translate_table() */ newinfo->chainstack = NULL; - ret = ebt_verify_pointers(&tmp, newinfo); + ret = ebt_verify_pointers(repl, newinfo); if (ret != 0) goto free_counterstmp; - ret = translate_table(tmp.name, newinfo); + ret = translate_table(net, repl->name, newinfo); if (ret != 0) goto free_counterstmp; - t = find_table_lock(net, tmp.name, &ret, &ebt_mutex); + t = find_table_lock(net, repl->name, &ret, &ebt_mutex); if (!t) { ret = -ENOENT; goto free_iterate; } /* the table doesn't like it */ - if (t->check && (ret = t->check(newinfo, tmp.valid_hooks))) + if (t->check && (ret = t->check(newinfo, repl->valid_hooks))) goto free_unlock; - if (tmp.num_counters && tmp.num_counters != t->private->nentries) { + if (repl->num_counters && repl->num_counters != t->private->nentries) { BUGPRINT("Wrong nr. of counters requested\n"); ret = -EINVAL; goto free_unlock; @@ -1048,7 +1030,7 @@ static int do_replace(struct net *net, void __user *user, unsigned int len) module_put(t->me); /* we need an atomic snapshot of the counters */ write_lock_bh(&t->lock); - if (tmp.num_counters) + if (repl->num_counters) get_counters(t->private->counters, counterstmp, t->private->nentries); @@ -1059,18 +1041,16 @@ static int do_replace(struct net *net, void __user *user, unsigned int len) allocation. Only reason why this is done is because this way the lock is held only once, while this doesn't bring the kernel into a dangerous state. */ - if (tmp.num_counters && - copy_to_user(tmp.counters, counterstmp, - tmp.num_counters * sizeof(struct ebt_counter))) { - BUGPRINT("Couldn't copy counters to userspace\n"); - ret = -EFAULT; + if (repl->num_counters && + copy_to_user(repl->counters, counterstmp, + repl->num_counters * sizeof(struct ebt_counter))) { + /* Silent error, can't fail, new table is already in place */ + net_warn_ratelimited("ebtables: counters copy to user failed while replacing table\n"); } - else - ret = 0; /* decrease module count and free resources */ EBT_ENTRY_ITERATE(table->entries, table->entries_size, - ebt_cleanup_entry, NULL); + ebt_cleanup_entry, net, NULL); vfree(table->entries); if (table->chainstack) { @@ -1087,7 +1067,7 @@ free_unlock: mutex_unlock(&ebt_mutex); free_iterate: EBT_ENTRY_ITERATE(newinfo->entries, newinfo->entries_size, - ebt_cleanup_entry, NULL); + ebt_cleanup_entry, net, NULL); free_counterstmp: vfree(counterstmp); /* can be initialized in translate_table() */ @@ -1096,6 +1076,61 @@ free_counterstmp: vfree(newinfo->chainstack[i]); vfree(newinfo->chainstack); } + return ret; +} + +/* replace the table */ +static int do_replace(struct net *net, const void __user *user, + unsigned int len) +{ + int ret, countersize; + struct ebt_table_info *newinfo; + struct ebt_replace tmp; + + if (copy_from_user(&tmp, user, sizeof(tmp)) != 0) + return -EFAULT; + + if (len != sizeof(tmp) + tmp.entries_size) { + BUGPRINT("Wrong len argument\n"); + return -EINVAL; + } + + if (tmp.entries_size == 0) { + BUGPRINT("Entries_size never zero\n"); + return -EINVAL; + } + /* overflow check */ + if (tmp.nentries >= ((INT_MAX - sizeof(struct ebt_table_info)) / + NR_CPUS - SMP_CACHE_BYTES) / sizeof(struct ebt_counter)) + return -ENOMEM; + if (tmp.num_counters >= INT_MAX / sizeof(struct ebt_counter)) + return -ENOMEM; + + tmp.name[sizeof(tmp.name) - 1] = 0; + + countersize = COUNTER_OFFSET(tmp.nentries) * nr_cpu_ids; + newinfo = vmalloc(sizeof(*newinfo) + countersize); + if (!newinfo) + return -ENOMEM; + + if (countersize) + memset(newinfo->counters, 0, countersize); + + newinfo->entries = vmalloc(tmp.entries_size); + if (!newinfo->entries) { + ret = -ENOMEM; + goto free_newinfo; + } + if (copy_from_user( + newinfo->entries, tmp.entries, tmp.entries_size) != 0) { + BUGPRINT("Couldn't copy entries from userspace\n"); + ret = -EFAULT; + goto free_entries; + } + + ret = do_replace_finish(net, &tmp, newinfo); + if (ret == 0) + return ret; free_entries: vfree(newinfo->entries); free_newinfo: @@ -1113,7 +1148,7 @@ ebt_register_table(struct net *net, const struct ebt_table *input_table) void *p; if (input_table == NULL || (repl = input_table->table) == NULL || - repl->entries == 0 || repl->entries_size == 0 || + repl->entries == NULL || repl->entries_size == 0 || repl->counters != NULL || input_table->private != NULL) { BUGPRINT("Bad table data for ebt_register_table!!!\n"); return ERR_PTR(-EINVAL); @@ -1154,7 +1189,7 @@ ebt_register_table(struct net *net, const struct ebt_table *input_table) newinfo->hook_entry[i] = p + ((char *)repl->hook_entry[i] - repl->entries); } - ret = translate_table(repl->name, newinfo); + ret = translate_table(net, repl->name, newinfo); if (ret != 0) { BUGPRINT("Translate_table failed\n"); goto free_chainstack; @@ -1162,7 +1197,8 @@ ebt_register_table(struct net *net, const struct ebt_table *input_table) if (table->check && table->check(newinfo, table->valid_hooks)) { BUGPRINT("The table doesn't like its own initial data, lol\n"); - return ERR_PTR(-EINVAL); + ret = -EINVAL; + goto free_chainstack; } table->private = newinfo; @@ -1204,7 +1240,7 @@ out: return ERR_PTR(ret); } -void ebt_unregister_table(struct ebt_table *table) +void ebt_unregister_table(struct net *net, struct ebt_table *table) { int i; @@ -1216,7 +1252,7 @@ void ebt_unregister_table(struct ebt_table *table) list_del(&table->list); mutex_unlock(&ebt_mutex); EBT_ENTRY_ITERATE(table->private->entries, table->private->entries_size, - ebt_cleanup_entry, NULL); + ebt_cleanup_entry, net, NULL); if (table->private->nentries) module_put(table->me); vfree(table->private->entries); @@ -1230,39 +1266,33 @@ void ebt_unregister_table(struct ebt_table *table) } /* userspace just supplied us with counters */ -static int update_counters(struct net *net, void __user *user, unsigned int len) +static int do_update_counters(struct net *net, const char *name, + struct ebt_counter __user *counters, + unsigned int num_counters, + const void __user *user, unsigned int len) { int i, ret; struct ebt_counter *tmp; - struct ebt_replace hlp; struct ebt_table *t; - if (copy_from_user(&hlp, user, sizeof(hlp))) - return -EFAULT; - - if (len != sizeof(hlp) + hlp.num_counters * sizeof(struct ebt_counter)) - return -EINVAL; - if (hlp.num_counters == 0) + if (num_counters == 0) return -EINVAL; - if (!(tmp = vmalloc(hlp.num_counters * sizeof(*tmp)))) { - MEMPRINT("Update_counters && nomemory\n"); + tmp = vmalloc(num_counters * sizeof(*tmp)); + if (!tmp) return -ENOMEM; - } - t = find_table_lock(net, hlp.name, &ret, &ebt_mutex); + t = find_table_lock(net, name, &ret, &ebt_mutex); if (!t) goto free_tmp; - if (hlp.num_counters != t->private->nentries) { + if (num_counters != t->private->nentries) { BUGPRINT("Wrong nr of counters\n"); ret = -EINVAL; goto unlock_mutex; } - if ( copy_from_user(tmp, hlp.counters, - hlp.num_counters * sizeof(struct ebt_counter)) ) { - BUGPRINT("Updata_counters && !cfu\n"); + if (copy_from_user(tmp, counters, num_counters * sizeof(*counters))) { ret = -EFAULT; goto unlock_mutex; } @@ -1271,7 +1301,7 @@ static int update_counters(struct net *net, void __user *user, unsigned int len) write_lock_bh(&t->lock); /* we add to the counters of the first cpu */ - for (i = 0; i < hlp.num_counters; i++) { + for (i = 0; i < num_counters; i++) { t->private->counters[i].pcnt += tmp[i].pcnt; t->private->counters[i].bcnt += tmp[i].bcnt; } @@ -1285,29 +1315,54 @@ free_tmp: return ret; } -static inline int ebt_make_matchname(struct ebt_entry_match *m, - char *base, char __user *ubase) +static int update_counters(struct net *net, const void __user *user, + unsigned int len) +{ + struct ebt_replace hlp; + + if (copy_from_user(&hlp, user, sizeof(hlp))) + return -EFAULT; + + if (len != sizeof(hlp) + hlp.num_counters * sizeof(struct ebt_counter)) + return -EINVAL; + + return do_update_counters(net, hlp.name, hlp.counters, + hlp.num_counters, user, len); +} + +static inline int ebt_make_matchname(const struct ebt_entry_match *m, + const char *base, char __user *ubase) { char __user *hlp = ubase + ((char *)m - base); - if (copy_to_user(hlp, m->u.match->name, EBT_FUNCTION_MAXNAMELEN)) + char name[EBT_FUNCTION_MAXNAMELEN] = {}; + + /* 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)) return -EFAULT; return 0; } -static inline int ebt_make_watchername(struct ebt_entry_watcher *w, - char *base, char __user *ubase) +static inline int ebt_make_watchername(const struct ebt_entry_watcher *w, + const char *base, char __user *ubase) { char __user *hlp = ubase + ((char *)w - base); - if (copy_to_user(hlp , w->u.watcher->name, EBT_FUNCTION_MAXNAMELEN)) + char name[EBT_FUNCTION_MAXNAMELEN] = {}; + + 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_make_names(struct ebt_entry *e, char *base, char __user *ubase) +static inline int +ebt_make_names(struct ebt_entry *e, const char *base, char __user *ubase) { int ret; char __user *hlp; - struct ebt_entry_target *t; + const struct ebt_entry_target *t; + char name[EBT_FUNCTION_MAXNAMELEN] = {}; if (e->bitmask == 0) return 0; @@ -1321,18 +1376,52 @@ static inline int ebt_make_names(struct ebt_entry *e, char *base, char __user *u ret = EBT_WATCHER_ITERATE(e, ebt_make_watchername, base, ubase); if (ret != 0) return ret; - if (copy_to_user(hlp, t->u.target->name, EBT_FUNCTION_MAXNAMELEN)) + strlcpy(name, t->u.target->name, sizeof(name)); + if (copy_to_user(hlp, name, EBT_FUNCTION_MAXNAMELEN)) return -EFAULT; return 0; } +static int copy_counters_to_user(struct ebt_table *t, + const struct ebt_counter *oldcounters, + void __user *user, unsigned int num_counters, + unsigned int nentries) +{ + struct ebt_counter *counterstmp; + int ret = 0; + + /* userspace might not need the counters */ + if (num_counters == 0) + return 0; + + if (num_counters != nentries) { + BUGPRINT("Num_counters wrong\n"); + return -EINVAL; + } + + counterstmp = vmalloc(nentries * sizeof(*counterstmp)); + if (!counterstmp) + return -ENOMEM; + + write_lock_bh(&t->lock); + get_counters(oldcounters, counterstmp, nentries); + write_unlock_bh(&t->lock); + + if (copy_to_user(user, counterstmp, + nentries * sizeof(struct ebt_counter))) + ret = -EFAULT; + vfree(counterstmp); + return ret; +} + /* called with ebt_mutex locked */ static int copy_everything_to_user(struct ebt_table *t, void __user *user, - int *len, int cmd) + const int *len, int cmd) { struct ebt_replace tmp; - struct ebt_counter *counterstmp, *oldcounters; + const struct ebt_counter *oldcounters; unsigned int entries_size, nentries; + int ret; char *entries; if (cmd == EBT_SO_GET_ENTRIES) { @@ -1347,16 +1436,12 @@ static int copy_everything_to_user(struct ebt_table *t, void __user *user, oldcounters = t->table->counters; } - if (copy_from_user(&tmp, user, sizeof(tmp))) { - BUGPRINT("Cfu didn't work\n"); + if (copy_from_user(&tmp, user, sizeof(tmp))) return -EFAULT; - } if (*len != sizeof(struct ebt_replace) + entries_size + - (tmp.num_counters? nentries * sizeof(struct ebt_counter): 0)) { - BUGPRINT("Wrong size\n"); + (tmp.num_counters ? nentries * sizeof(struct ebt_counter) : 0)) return -EINVAL; - } if (tmp.nentries != nentries) { BUGPRINT("Nentries wrong\n"); @@ -1368,29 +1453,10 @@ static int copy_everything_to_user(struct ebt_table *t, void __user *user, return -EINVAL; } - /* userspace might not need the counters */ - if (tmp.num_counters) { - if (tmp.num_counters != nentries) { - BUGPRINT("Num_counters wrong\n"); - return -EINVAL; - } - counterstmp = vmalloc(nentries * sizeof(*counterstmp)); - if (!counterstmp) { - MEMPRINT("Couldn't copy counters, out of memory\n"); - return -ENOMEM; - } - write_lock_bh(&t->lock); - get_counters(oldcounters, counterstmp, nentries); - write_unlock_bh(&t->lock); - - if (copy_to_user(tmp.counters, counterstmp, - nentries * sizeof(struct ebt_counter))) { - BUGPRINT("Couldn't copy counters to userspace\n"); - vfree(counterstmp); - return -EFAULT; - } - vfree(counterstmp); - } + ret = copy_counters_to_user(t, oldcounters, tmp.counters, + tmp.num_counters, nentries); + if (ret) + return ret; if (copy_to_user(tmp.entries, entries, entries_size)) { BUGPRINT("Couldn't copy entries to userspace\n"); @@ -1405,17 +1471,21 @@ static int do_ebt_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) { int ret; + struct net *net = sock_net(sk); + + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + return -EPERM; - switch(cmd) { + switch (cmd) { case EBT_SO_SET_ENTRIES: - ret = do_replace(sock_net(sk), user, len); + ret = do_replace(net, user, len); break; case EBT_SO_SET_COUNTERS: - ret = update_counters(sock_net(sk), user, len); + ret = update_counters(net, user, len); break; default: ret = -EINVAL; - } + } return ret; } @@ -1424,18 +1494,22 @@ static int do_ebt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) int ret; struct ebt_replace tmp; struct ebt_table *t; + struct net *net = sock_net(sk); + + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + return -EPERM; if (copy_from_user(&tmp, user, sizeof(tmp))) return -EFAULT; - t = find_table_lock(sock_net(sk), tmp.name, &ret, &ebt_mutex); + t = find_table_lock(net, tmp.name, &ret, &ebt_mutex); if (!t) return ret; - switch(cmd) { + switch (cmd) { case EBT_SO_GET_INFO: case EBT_SO_GET_INIT_INFO: - if (*len != sizeof(struct ebt_replace)){ + if (*len != sizeof(struct ebt_replace)) { ret = -EINVAL; mutex_unlock(&ebt_mutex); break; @@ -1450,7 +1524,7 @@ static int do_ebt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) tmp.valid_hooks = t->table->valid_hooks; } mutex_unlock(&ebt_mutex); - if (copy_to_user(user, &tmp, *len) != 0){ + if (copy_to_user(user, &tmp, *len) != 0) { BUGPRINT("c2u Didn't work\n"); ret = -EFAULT; break; @@ -1472,15 +1546,848 @@ static int do_ebt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) return ret; } -static struct nf_sockopt_ops ebt_sockopts = +#ifdef CONFIG_COMPAT +/* 32 bit-userspace compatibility definitions. */ +struct compat_ebt_replace { + char name[EBT_TABLE_MAXNAMELEN]; + compat_uint_t valid_hooks; + compat_uint_t nentries; + compat_uint_t entries_size; + /* start of the chains */ + compat_uptr_t hook_entry[NF_BR_NUMHOOKS]; + /* nr of counters userspace expects back */ + compat_uint_t num_counters; + /* where the kernel will put the old counters. */ + compat_uptr_t counters; + compat_uptr_t entries; +}; + +/* struct ebt_entry_match, _target and _watcher have same layout */ +struct compat_ebt_entry_mwt { + union { + char name[EBT_FUNCTION_MAXNAMELEN]; + compat_uptr_t ptr; + } u; + compat_uint_t match_size; + compat_uint_t data[0]; +}; + +/* account for possible padding between match_size and ->data */ +static int ebt_compat_entry_padsize(void) +{ + BUILD_BUG_ON(XT_ALIGN(sizeof(struct ebt_entry_match)) < + COMPAT_XT_ALIGN(sizeof(struct compat_ebt_entry_mwt))); + return (int) XT_ALIGN(sizeof(struct ebt_entry_match)) - + COMPAT_XT_ALIGN(sizeof(struct compat_ebt_entry_mwt)); +} + +static int ebt_compat_match_offset(const struct xt_match *match, + unsigned int userlen) +{ + /* + * ebt_among needs special handling. The kernel .matchsize is + * set to -1 at registration time; at runtime an EBT_ALIGN()ed + * value is expected. + * Example: userspace sends 4500, ebt_among.c wants 4504. + */ + if (unlikely(match->matchsize == -1)) + return XT_ALIGN(userlen) - COMPAT_XT_ALIGN(userlen); + return xt_compat_match_offset(match); +} + +static int compat_match_to_user(struct ebt_entry_match *m, void __user **dstptr, + unsigned int *size) +{ + const struct xt_match *match = m->u.match; + struct compat_ebt_entry_mwt __user *cm = *dstptr; + int off = ebt_compat_match_offset(match, m->match_size); + compat_uint_t msize = m->match_size - off; + + BUG_ON(off >= m->match_size); + + if (copy_to_user(cm->u.name, match->name, + strlen(match->name) + 1) || put_user(msize, &cm->match_size)) + return -EFAULT; + + 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)) + return -EFAULT; + + *size -= ebt_compat_entry_padsize() + off; + *dstptr = cm->data; + *dstptr += msize; + return 0; +} + +static int compat_target_to_user(struct ebt_entry_target *t, + void __user **dstptr, + unsigned int *size) +{ + const struct xt_target *target = t->u.target; + struct compat_ebt_entry_mwt __user *cm = *dstptr; + int off = xt_compat_target_offset(target); + compat_uint_t tsize = t->target_size - off; + + BUG_ON(off >= t->target_size); + + if (copy_to_user(cm->u.name, target->name, + strlen(target->name) + 1) || put_user(tsize, &cm->match_size)) + return -EFAULT; + + 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; + + *size -= ebt_compat_entry_padsize() + off; + *dstptr = cm->data; + *dstptr += tsize; + return 0; +} + +static int compat_watcher_to_user(struct ebt_entry_watcher *w, + void __user **dstptr, + unsigned int *size) +{ + return compat_target_to_user((struct ebt_entry_target *)w, + dstptr, size); +} + +static int compat_copy_entry_to_user(struct ebt_entry *e, void __user **dstptr, + unsigned int *size) +{ + struct ebt_entry_target *t; + struct ebt_entry __user *ce; + u32 watchers_offset, target_offset, next_offset; + compat_uint_t origsize; + int ret; + + if (e->bitmask == 0) { + if (*size < sizeof(struct ebt_entries)) + return -EINVAL; + if (copy_to_user(*dstptr, e, sizeof(struct ebt_entries))) + return -EFAULT; + + *dstptr += sizeof(struct ebt_entries); + *size -= sizeof(struct ebt_entries); + return 0; + } + + if (*size < sizeof(*ce)) + return -EINVAL; + + ce = (struct ebt_entry __user *)*dstptr; + if (copy_to_user(ce, e, sizeof(*ce))) + return -EFAULT; + + origsize = *size; + *dstptr += sizeof(*ce); + + ret = EBT_MATCH_ITERATE(e, compat_match_to_user, dstptr, size); + if (ret) + return ret; + watchers_offset = e->watchers_offset - (origsize - *size); + + ret = EBT_WATCHER_ITERATE(e, compat_watcher_to_user, dstptr, size); + if (ret) + return ret; + target_offset = e->target_offset - (origsize - *size); + + t = (struct ebt_entry_target *) ((char *) e + e->target_offset); + + ret = compat_target_to_user(t, dstptr, size); + if (ret) + return ret; + next_offset = e->next_offset - (origsize - *size); + + if (put_user(watchers_offset, &ce->watchers_offset) || + put_user(target_offset, &ce->target_offset) || + put_user(next_offset, &ce->next_offset)) + return -EFAULT; + + *size -= sizeof(*ce); + return 0; +} + +static int compat_calc_match(struct ebt_entry_match *m, int *off) +{ + *off += ebt_compat_match_offset(m->u.match, m->match_size); + *off += ebt_compat_entry_padsize(); + return 0; +} + +static int compat_calc_watcher(struct ebt_entry_watcher *w, int *off) +{ + *off += xt_compat_target_offset(w->u.watcher); + *off += ebt_compat_entry_padsize(); + return 0; +} + +static int compat_calc_entry(const struct ebt_entry *e, + const struct ebt_table_info *info, + const void *base, + struct compat_ebt_replace *newinfo) +{ + const struct ebt_entry_target *t; + unsigned int entry_offset; + int off, ret, i; + + if (e->bitmask == 0) + return 0; + + off = 0; + entry_offset = (void *)e - base; + + EBT_MATCH_ITERATE(e, compat_calc_match, &off); + EBT_WATCHER_ITERATE(e, compat_calc_watcher, &off); + + t = (const struct ebt_entry_target *) ((char *) e + e->target_offset); + + off += xt_compat_target_offset(t->u.target); + off += ebt_compat_entry_padsize(); + + newinfo->entries_size -= off; + + ret = xt_compat_add_offset(NFPROTO_BRIDGE, entry_offset, off); + if (ret) + return ret; + + for (i = 0; i < NF_BR_NUMHOOKS; i++) { + const void *hookptr = info->hook_entry[i]; + if (info->hook_entry[i] && + (e < (struct ebt_entry *)(base - hookptr))) { + newinfo->hook_entry[i] -= off; + pr_debug("0x%08X -> 0x%08X\n", + newinfo->hook_entry[i] + off, + newinfo->hook_entry[i]); + } + } + + return 0; +} + + +static int compat_table_info(const struct ebt_table_info *info, + struct compat_ebt_replace *newinfo) +{ + unsigned int size = info->entries_size; + const void *entries = info->entries; + + newinfo->entries_size = size; + + xt_compat_init_offsets(NFPROTO_BRIDGE, info->nentries); + return EBT_ENTRY_ITERATE(entries, size, compat_calc_entry, info, + entries, newinfo); +} + +static int compat_copy_everything_to_user(struct ebt_table *t, + void __user *user, int *len, int cmd) +{ + struct compat_ebt_replace repl, tmp; + struct ebt_counter *oldcounters; + struct ebt_table_info tinfo; + int ret; + void __user *pos; + + memset(&tinfo, 0, sizeof(tinfo)); + + if (cmd == EBT_SO_GET_ENTRIES) { + tinfo.entries_size = t->private->entries_size; + tinfo.nentries = t->private->nentries; + tinfo.entries = t->private->entries; + oldcounters = t->private->counters; + } else { + tinfo.entries_size = t->table->entries_size; + tinfo.nentries = t->table->nentries; + tinfo.entries = t->table->entries; + oldcounters = t->table->counters; + } + + if (copy_from_user(&tmp, user, sizeof(tmp))) + return -EFAULT; + + if (tmp.nentries != tinfo.nentries || + (tmp.num_counters && tmp.num_counters != tinfo.nentries)) + return -EINVAL; + + memcpy(&repl, &tmp, sizeof(repl)); + if (cmd == EBT_SO_GET_ENTRIES) + ret = compat_table_info(t->private, &repl); + else + ret = compat_table_info(&tinfo, &repl); + if (ret) + return ret; + + if (*len != sizeof(tmp) + repl.entries_size + + (tmp.num_counters? tinfo.nentries * sizeof(struct ebt_counter): 0)) { + pr_err("wrong size: *len %d, entries_size %u, replsz %d\n", + *len, tinfo.entries_size, repl.entries_size); + return -EINVAL; + } + + /* userspace might not need the counters */ + ret = copy_counters_to_user(t, oldcounters, compat_ptr(tmp.counters), + tmp.num_counters, tinfo.nentries); + if (ret) + return ret; + + pos = compat_ptr(tmp.entries); + return EBT_ENTRY_ITERATE(tinfo.entries, tinfo.entries_size, + compat_copy_entry_to_user, &pos, &tmp.entries_size); +} + +struct ebt_entries_buf_state { + char *buf_kern_start; /* kernel buffer to copy (translated) data to */ + u32 buf_kern_len; /* total size of kernel buffer */ + u32 buf_kern_offset; /* amount of data copied so far */ + u32 buf_user_offset; /* read position in userspace buffer */ +}; + +static int ebt_buf_count(struct ebt_entries_buf_state *state, unsigned int sz) +{ + state->buf_kern_offset += sz; + return state->buf_kern_offset >= sz ? 0 : -EINVAL; +} + +static int ebt_buf_add(struct ebt_entries_buf_state *state, + void *data, unsigned int sz) +{ + if (state->buf_kern_start == NULL) + goto count_only; + + BUG_ON(state->buf_kern_offset + sz > state->buf_kern_len); + + memcpy(state->buf_kern_start + state->buf_kern_offset, data, sz); + + count_only: + state->buf_user_offset += sz; + return ebt_buf_count(state, sz); +} + +static int ebt_buf_add_pad(struct ebt_entries_buf_state *state, unsigned int sz) +{ + char *b = state->buf_kern_start; + + BUG_ON(b && state->buf_kern_offset > state->buf_kern_len); + + if (b != NULL && sz > 0) + memset(b + state->buf_kern_offset, 0, sz); + /* do not adjust ->buf_user_offset here, we added kernel-side padding */ + return ebt_buf_count(state, sz); +} + +enum compat_mwt { + EBT_COMPAT_MATCH, + EBT_COMPAT_WATCHER, + EBT_COMPAT_TARGET, +}; + +static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt, + enum compat_mwt compat_mwt, + struct ebt_entries_buf_state *state, + const unsigned char *base) +{ + char name[EBT_FUNCTION_MAXNAMELEN]; + struct xt_match *match; + struct xt_target *wt; + void *dst = NULL; + int off, pad = 0; + unsigned int size_kern, match_size = mwt->match_size; + + strlcpy(name, mwt->u.name, sizeof(name)); + + if (state->buf_kern_start) + dst = state->buf_kern_start + state->buf_kern_offset; + + switch (compat_mwt) { + case EBT_COMPAT_MATCH: + match = xt_request_find_match(NFPROTO_BRIDGE, name, 0); + if (IS_ERR(match)) + return PTR_ERR(match); + + off = ebt_compat_match_offset(match, match_size); + if (dst) { + if (match->compat_from_user) + match->compat_from_user(dst, mwt->data); + else + memcpy(dst, mwt->data, match_size); + } + + size_kern = match->matchsize; + if (unlikely(size_kern == -1)) + size_kern = match_size; + module_put(match->me); + break; + case EBT_COMPAT_WATCHER: /* fallthrough */ + case EBT_COMPAT_TARGET: + wt = xt_request_find_target(NFPROTO_BRIDGE, name, 0); + if (IS_ERR(wt)) + return PTR_ERR(wt); + off = xt_compat_target_offset(wt); + + if (dst) { + if (wt->compat_from_user) + wt->compat_from_user(dst, mwt->data); + else + memcpy(dst, mwt->data, match_size); + } + + size_kern = wt->targetsize; + module_put(wt->me); + break; + + default: + return -EINVAL; + } + + state->buf_kern_offset += match_size + off; + state->buf_user_offset += match_size; + pad = XT_ALIGN(size_kern) - size_kern; + + if (pad > 0 && dst) { + BUG_ON(state->buf_kern_len <= pad); + BUG_ON(state->buf_kern_offset - (match_size + off) + size_kern > state->buf_kern_len - pad); + memset(dst + size_kern, 0, pad); + } + return off + match_size; +} + +/* + * return size of all matches, watchers or target, including necessary + * alignment and padding. + */ +static int ebt_size_mwt(struct compat_ebt_entry_mwt *match32, + unsigned int size_left, enum compat_mwt type, + struct ebt_entries_buf_state *state, const void *base) +{ + int growth = 0; + char *buf; + + if (size_left == 0) + return 0; + + buf = (char *) match32; + + while (size_left >= sizeof(*match32)) { + struct ebt_entry_match *match_kern; + int ret; + + match_kern = (struct ebt_entry_match *) state->buf_kern_start; + if (match_kern) { + char *tmp; + tmp = state->buf_kern_start + state->buf_kern_offset; + match_kern = (struct ebt_entry_match *) tmp; + } + ret = ebt_buf_add(state, buf, sizeof(*match32)); + if (ret < 0) + return ret; + size_left -= sizeof(*match32); + + /* add padding before match->data (if any) */ + ret = ebt_buf_add_pad(state, ebt_compat_entry_padsize()); + if (ret < 0) + return ret; + + if (match32->match_size > size_left) + return -EINVAL; + + size_left -= match32->match_size; + + ret = compat_mtw_from_user(match32, type, state, base); + if (ret < 0) + return ret; + + BUG_ON(ret < match32->match_size); + growth += ret - match32->match_size; + growth += ebt_compat_entry_padsize(); + + buf += sizeof(*match32); + buf += match32->match_size; + + if (match_kern) + match_kern->match_size = ret; + + WARN_ON(type == EBT_COMPAT_TARGET && size_left); + match32 = (struct compat_ebt_entry_mwt *) buf; + } + + return growth; +} + +/* called for all ebt_entry structures. */ +static int size_entry_mwt(struct ebt_entry *entry, const unsigned char *base, + unsigned int *total, + struct ebt_entries_buf_state *state) +{ + unsigned int i, j, startoff, new_offset = 0; + /* stores match/watchers/targets & offset of next struct ebt_entry: */ + unsigned int offsets[4]; + unsigned int *offsets_update = NULL; + int ret; + char *buf_start; + + if (*total < sizeof(struct ebt_entries)) + return -EINVAL; + + if (!entry->bitmask) { + *total -= sizeof(struct ebt_entries); + return ebt_buf_add(state, entry, sizeof(struct ebt_entries)); + } + if (*total < sizeof(*entry) || entry->next_offset < sizeof(*entry)) + return -EINVAL; + + startoff = state->buf_user_offset; + /* pull in most part of ebt_entry, it does not need to be changed. */ + ret = ebt_buf_add(state, entry, + offsetof(struct ebt_entry, watchers_offset)); + if (ret < 0) + return ret; + + offsets[0] = sizeof(struct ebt_entry); /* matches come first */ + memcpy(&offsets[1], &entry->watchers_offset, + sizeof(offsets) - sizeof(offsets[0])); + + if (state->buf_kern_start) { + buf_start = state->buf_kern_start + state->buf_kern_offset; + offsets_update = (unsigned int *) buf_start; + } + ret = ebt_buf_add(state, &offsets[1], + sizeof(offsets) - sizeof(offsets[0])); + if (ret < 0) + return ret; + buf_start = (char *) entry; + /* + * 0: matches offset, always follows ebt_entry. + * 1: watchers offset, from ebt_entry structure + * 2: target offset, from ebt_entry structure + * 3: next ebt_entry offset, from ebt_entry structure + * + * offsets are relative to beginning of struct ebt_entry (i.e., 0). + */ + for (i = 0, j = 1 ; j < 4 ; j++, i++) { + struct compat_ebt_entry_mwt *match32; + unsigned int size; + char *buf = buf_start; + + buf = buf_start + offsets[i]; + if (offsets[i] > offsets[j]) + return -EINVAL; + + match32 = (struct compat_ebt_entry_mwt *) buf; + size = offsets[j] - offsets[i]; + ret = ebt_size_mwt(match32, size, i, state, base); + if (ret < 0) + return ret; + new_offset += ret; + if (offsets_update && new_offset) { + pr_debug("change offset %d to %d\n", + offsets_update[i], offsets[j] + new_offset); + offsets_update[i] = offsets[j] + new_offset; + } + } + + if (state->buf_kern_start == NULL) { + unsigned int offset = buf_start - (char *) base; + + ret = xt_compat_add_offset(NFPROTO_BRIDGE, offset, new_offset); + if (ret < 0) + return ret; + } + + startoff = state->buf_user_offset - startoff; + + BUG_ON(*total < startoff); + *total -= startoff; + return 0; +} + +/* + * repl->entries_size is the size of the ebt_entry blob in userspace. + * It might need more memory when copied to a 64 bit kernel in case + * userspace is 32-bit. So, first task: find out how much memory is needed. + * + * Called before validation is performed. + */ +static int compat_copy_entries(unsigned char *data, unsigned int size_user, + struct ebt_entries_buf_state *state) +{ + unsigned int size_remaining = size_user; + int ret; + + ret = EBT_ENTRY_ITERATE(data, size_user, size_entry_mwt, data, + &size_remaining, state); + if (ret < 0) + return ret; + + WARN_ON(size_remaining); + return state->buf_kern_offset; +} + + +static int compat_copy_ebt_replace_from_user(struct ebt_replace *repl, + void __user *user, unsigned int len) +{ + struct compat_ebt_replace tmp; + int i; + + if (len < sizeof(tmp)) + return -EINVAL; + + if (copy_from_user(&tmp, user, sizeof(tmp))) + return -EFAULT; + + if (len != sizeof(tmp) + tmp.entries_size) + return -EINVAL; + + if (tmp.entries_size == 0) + return -EINVAL; + + if (tmp.nentries >= ((INT_MAX - sizeof(struct ebt_table_info)) / + NR_CPUS - SMP_CACHE_BYTES) / sizeof(struct ebt_counter)) + return -ENOMEM; + if (tmp.num_counters >= INT_MAX / sizeof(struct ebt_counter)) + return -ENOMEM; + + memcpy(repl, &tmp, offsetof(struct ebt_replace, hook_entry)); + + /* starting with hook_entry, 32 vs. 64 bit structures are different */ + for (i = 0; i < NF_BR_NUMHOOKS; i++) + repl->hook_entry[i] = compat_ptr(tmp.hook_entry[i]); + + repl->num_counters = tmp.num_counters; + repl->counters = compat_ptr(tmp.counters); + repl->entries = compat_ptr(tmp.entries); + return 0; +} + +static int compat_do_replace(struct net *net, void __user *user, + unsigned int len) +{ + int ret, i, countersize, size64; + struct ebt_table_info *newinfo; + struct ebt_replace tmp; + struct ebt_entries_buf_state state; + void *entries_tmp; + + ret = compat_copy_ebt_replace_from_user(&tmp, user, len); + if (ret) { + /* try real handler in case userland supplied needed padding */ + if (ret == -EINVAL && do_replace(net, user, len) == 0) + ret = 0; + return ret; + } + + countersize = COUNTER_OFFSET(tmp.nentries) * nr_cpu_ids; + newinfo = vmalloc(sizeof(*newinfo) + countersize); + if (!newinfo) + return -ENOMEM; + + if (countersize) + memset(newinfo->counters, 0, countersize); + + memset(&state, 0, sizeof(state)); + + newinfo->entries = vmalloc(tmp.entries_size); + if (!newinfo->entries) { + ret = -ENOMEM; + goto free_newinfo; + } + if (copy_from_user( + newinfo->entries, tmp.entries, tmp.entries_size) != 0) { + ret = -EFAULT; + goto free_entries; + } + + entries_tmp = newinfo->entries; + + xt_compat_lock(NFPROTO_BRIDGE); + + xt_compat_init_offsets(NFPROTO_BRIDGE, tmp.nentries); + ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state); + if (ret < 0) + goto out_unlock; + + pr_debug("tmp.entries_size %d, kern off %d, user off %d delta %d\n", + tmp.entries_size, state.buf_kern_offset, state.buf_user_offset, + xt_compat_calc_jump(NFPROTO_BRIDGE, tmp.entries_size)); + + size64 = ret; + newinfo->entries = vmalloc(size64); + if (!newinfo->entries) { + vfree(entries_tmp); + ret = -ENOMEM; + goto out_unlock; + } + + memset(&state, 0, sizeof(state)); + state.buf_kern_start = newinfo->entries; + state.buf_kern_len = size64; + + ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state); + BUG_ON(ret < 0); /* parses same data again */ + + vfree(entries_tmp); + tmp.entries_size = size64; + + for (i = 0; i < NF_BR_NUMHOOKS; i++) { + char __user *usrptr; + if (tmp.hook_entry[i]) { + unsigned int delta; + usrptr = (char __user *) tmp.hook_entry[i]; + delta = usrptr - tmp.entries; + usrptr += xt_compat_calc_jump(NFPROTO_BRIDGE, delta); + tmp.hook_entry[i] = (struct ebt_entries __user *)usrptr; + } + } + + xt_compat_flush_offsets(NFPROTO_BRIDGE); + xt_compat_unlock(NFPROTO_BRIDGE); + + ret = do_replace_finish(net, &tmp, newinfo); + if (ret == 0) + return ret; +free_entries: + vfree(newinfo->entries); +free_newinfo: + vfree(newinfo); + return ret; +out_unlock: + xt_compat_flush_offsets(NFPROTO_BRIDGE); + xt_compat_unlock(NFPROTO_BRIDGE); + goto free_entries; +} + +static int compat_update_counters(struct net *net, void __user *user, + unsigned int len) +{ + struct compat_ebt_replace hlp; + + if (copy_from_user(&hlp, user, sizeof(hlp))) + return -EFAULT; + + /* try real handler in case userland supplied needed padding */ + if (len != sizeof(hlp) + hlp.num_counters * sizeof(struct ebt_counter)) + return update_counters(net, user, len); + + return do_update_counters(net, hlp.name, compat_ptr(hlp.counters), + hlp.num_counters, user, len); +} + +static int compat_do_ebt_set_ctl(struct sock *sk, + int cmd, void __user *user, unsigned int len) +{ + int ret; + struct net *net = sock_net(sk); + + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + return -EPERM; + + switch (cmd) { + case EBT_SO_SET_ENTRIES: + ret = compat_do_replace(net, user, len); + break; + case EBT_SO_SET_COUNTERS: + ret = compat_update_counters(net, user, len); + break; + default: + ret = -EINVAL; + } + return ret; +} + +static int compat_do_ebt_get_ctl(struct sock *sk, int cmd, + void __user *user, int *len) { + int ret; + struct compat_ebt_replace tmp; + struct ebt_table *t; + struct net *net = sock_net(sk); + + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + return -EPERM; + + /* try real handler in case userland supplied needed padding */ + if ((cmd == EBT_SO_GET_INFO || + cmd == EBT_SO_GET_INIT_INFO) && *len != sizeof(tmp)) + return do_ebt_get_ctl(sk, cmd, user, len); + + if (copy_from_user(&tmp, user, sizeof(tmp))) + return -EFAULT; + + t = find_table_lock(net, tmp.name, &ret, &ebt_mutex); + if (!t) + return ret; + + xt_compat_lock(NFPROTO_BRIDGE); + switch (cmd) { + case EBT_SO_GET_INFO: + tmp.nentries = t->private->nentries; + ret = compat_table_info(t->private, &tmp); + if (ret) + goto out; + tmp.valid_hooks = t->valid_hooks; + + if (copy_to_user(user, &tmp, *len) != 0) { + ret = -EFAULT; + break; + } + ret = 0; + break; + case EBT_SO_GET_INIT_INFO: + tmp.nentries = t->table->nentries; + tmp.entries_size = t->table->entries_size; + tmp.valid_hooks = t->table->valid_hooks; + + if (copy_to_user(user, &tmp, *len) != 0) { + ret = -EFAULT; + break; + } + ret = 0; + break; + case EBT_SO_GET_ENTRIES: + case EBT_SO_GET_INIT_ENTRIES: + /* + * try real handler first in case of userland-side padding. + * in case we are dealing with an 'ordinary' 32 bit binary + * without 64bit compatibility padding, this will fail right + * after copy_from_user when the *len argument is validated. + * + * the compat_ variant needs to do one pass over the kernel + * data set to adjust for size differences before it the check. + */ + if (copy_everything_to_user(t, user, len, cmd) == 0) + ret = 0; + else + ret = compat_copy_everything_to_user(t, user, len, cmd); + break; + default: + ret = -EINVAL; + } + out: + xt_compat_flush_offsets(NFPROTO_BRIDGE); + xt_compat_unlock(NFPROTO_BRIDGE); + mutex_unlock(&ebt_mutex); + return ret; +} +#endif + +static struct nf_sockopt_ops ebt_sockopts = { .pf = PF_INET, .set_optmin = EBT_BASE_CTL, .set_optmax = EBT_SO_SET_MAX + 1, .set = do_ebt_set_ctl, +#ifdef CONFIG_COMPAT + .compat_set = compat_do_ebt_set_ctl, +#endif .get_optmin = EBT_BASE_CTL, .get_optmax = EBT_SO_GET_MAX + 1, .get = do_ebt_get_ctl, +#ifdef CONFIG_COMPAT + .compat_get = compat_do_ebt_get_ctl, +#endif .owner = THIS_MODULE, }; diff --git a/net/bridge/netfilter/nf_tables_bridge.c b/net/bridge/netfilter/nf_tables_bridge.c new file mode 100644 index 00000000000..5bcc0d8b31f --- /dev/null +++ b/net/bridge/netfilter/nf_tables_bridge.c @@ -0,0 +1,104 @@ +/* + * Copyright (c) 2008 Patrick McHardy <kaber@trash.net> + * Copyright (c) 2013 Pablo Neira Ayuso <pablo@netfilter.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Development of this code funded by Astaro AG (http://www.astaro.com/) + */ + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/netfilter_bridge.h> +#include <net/netfilter/nf_tables.h> + +static unsigned int +nft_do_chain_bridge(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + struct nft_pktinfo pkt; + + nft_set_pktinfo(&pkt, ops, skb, in, out); + + return nft_do_chain(&pkt, ops); +} + +static struct nft_af_info nft_af_bridge __read_mostly = { + .family = NFPROTO_BRIDGE, + .nhooks = NF_BR_NUMHOOKS, + .owner = THIS_MODULE, + .nops = 1, + .hooks = { + [NF_BR_LOCAL_IN] = nft_do_chain_bridge, + [NF_BR_FORWARD] = nft_do_chain_bridge, + [NF_BR_LOCAL_OUT] = nft_do_chain_bridge, + }, +}; + +static int nf_tables_bridge_init_net(struct net *net) +{ + net->nft.bridge = kmalloc(sizeof(struct nft_af_info), GFP_KERNEL); + if (net->nft.bridge == NULL) + return -ENOMEM; + + memcpy(net->nft.bridge, &nft_af_bridge, sizeof(nft_af_bridge)); + + if (nft_register_afinfo(net, net->nft.bridge) < 0) + goto err; + + return 0; +err: + kfree(net->nft.bridge); + return -ENOMEM; +} + +static void nf_tables_bridge_exit_net(struct net *net) +{ + nft_unregister_afinfo(net->nft.bridge); + kfree(net->nft.bridge); +} + +static struct pernet_operations nf_tables_bridge_net_ops = { + .init = nf_tables_bridge_init_net, + .exit = nf_tables_bridge_exit_net, +}; + +static const struct nf_chain_type filter_bridge = { + .name = "filter", + .type = NFT_CHAIN_T_DEFAULT, + .family = NFPROTO_BRIDGE, + .owner = THIS_MODULE, + .hook_mask = (1 << NF_BR_LOCAL_IN) | + (1 << NF_BR_FORWARD) | + (1 << NF_BR_LOCAL_OUT), +}; + +static int __init nf_tables_bridge_init(void) +{ + int ret; + + nft_register_chain_type(&filter_bridge); + ret = register_pernet_subsys(&nf_tables_bridge_net_ops); + if (ret < 0) + nft_unregister_chain_type(&filter_bridge); + + return ret; +} + +static void __exit nf_tables_bridge_exit(void) +{ + unregister_pernet_subsys(&nf_tables_bridge_net_ops); + nft_unregister_chain_type(&filter_bridge); +} + +module_init(nf_tables_bridge_init); +module_exit(nf_tables_bridge_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_ALIAS_NFT_FAMILY(AF_BRIDGE); diff --git a/net/bridge/netfilter/nft_meta_bridge.c b/net/bridge/netfilter/nft_meta_bridge.c new file mode 100644 index 00000000000..4f02109d708 --- /dev/null +++ b/net/bridge/netfilter/nft_meta_bridge.c @@ -0,0 +1,139 @@ +/* + * Copyright (c) 2014 Intel Corporation + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables.h> +#include <net/netfilter/nft_meta.h> + +#include "../br_private.h" + +static void nft_meta_bridge_get_eval(const struct nft_expr *expr, + struct nft_data data[NFT_REG_MAX + 1], + const struct nft_pktinfo *pkt) +{ + const struct nft_meta *priv = nft_expr_priv(expr); + const struct net_device *in = pkt->in, *out = pkt->out; + struct nft_data *dest = &data[priv->dreg]; + const struct net_bridge_port *p; + + switch (priv->key) { + case NFT_META_BRI_IIFNAME: + if (in == NULL || (p = br_port_get_rcu(in)) == NULL) + goto err; + break; + case NFT_META_BRI_OIFNAME: + if (out == NULL || (p = br_port_get_rcu(out)) == NULL) + goto err; + break; + default: + goto out; + } + + strncpy((char *)dest->data, p->br->dev->name, sizeof(dest->data)); + return; +out: + return nft_meta_get_eval(expr, data, pkt); +err: + data[NFT_REG_VERDICT].verdict = NFT_BREAK; +} + +static int nft_meta_bridge_get_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_meta *priv = nft_expr_priv(expr); + int err; + + priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY])); + switch (priv->key) { + case NFT_META_BRI_IIFNAME: + case NFT_META_BRI_OIFNAME: + break; + default: + return nft_meta_get_init(ctx, expr, tb); + } + + priv->dreg = ntohl(nla_get_be32(tb[NFTA_META_DREG])); + err = nft_validate_output_register(priv->dreg); + if (err < 0) + return err; + + err = nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE); + if (err < 0) + return err; + + return 0; +} + +static struct nft_expr_type nft_meta_bridge_type; +static const struct nft_expr_ops nft_meta_bridge_get_ops = { + .type = &nft_meta_bridge_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_meta)), + .eval = nft_meta_bridge_get_eval, + .init = nft_meta_bridge_get_init, + .dump = nft_meta_get_dump, +}; + +static const struct nft_expr_ops nft_meta_bridge_set_ops = { + .type = &nft_meta_bridge_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_meta)), + .eval = nft_meta_set_eval, + .init = nft_meta_set_init, + .dump = nft_meta_set_dump, +}; + +static const struct nft_expr_ops * +nft_meta_bridge_select_ops(const struct nft_ctx *ctx, + const struct nlattr * const tb[]) +{ + if (tb[NFTA_META_KEY] == NULL) + return ERR_PTR(-EINVAL); + + if (tb[NFTA_META_DREG] && tb[NFTA_META_SREG]) + return ERR_PTR(-EINVAL); + + if (tb[NFTA_META_DREG]) + return &nft_meta_bridge_get_ops; + + if (tb[NFTA_META_SREG]) + return &nft_meta_bridge_set_ops; + + return ERR_PTR(-EINVAL); +} + +static struct nft_expr_type nft_meta_bridge_type __read_mostly = { + .family = NFPROTO_BRIDGE, + .name = "meta", + .select_ops = &nft_meta_bridge_select_ops, + .policy = nft_meta_policy, + .maxattr = NFTA_META_MAX, + .owner = THIS_MODULE, +}; + +static int __init nft_meta_bridge_module_init(void) +{ + return nft_register_expr(&nft_meta_bridge_type); +} + +static void __exit nft_meta_bridge_module_exit(void) +{ + nft_unregister_expr(&nft_meta_bridge_type); +} + +module_init(nft_meta_bridge_module_init); +module_exit(nft_meta_bridge_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Tomasz Bursztyka <tomasz.bursztyka@linux.intel.com>"); +MODULE_ALIAS_NFT_AF_EXPR(AF_BRIDGE, "meta"); |