diff options
Diffstat (limited to 'net/bridge')
| -rw-r--r-- | net/bridge/br_device.c | 10 | ||||
| -rw-r--r-- | net/bridge/br_forward.c | 7 | ||||
| -rw-r--r-- | net/bridge/br_input.c | 17 | ||||
| -rw-r--r-- | net/bridge/br_netfilter.c | 177 | ||||
| -rw-r--r-- | net/bridge/br_netlink.c | 131 | ||||
| -rw-r--r-- | net/bridge/br_nf_core.c | 1 | ||||
| -rw-r--r-- | net/bridge/br_private.h | 6 | ||||
| -rw-r--r-- | net/bridge/br_sysfs_if.c | 2 | ||||
| -rw-r--r-- | net/bridge/netfilter/ebtable_filter.c | 14 | ||||
| -rw-r--r-- | net/bridge/netfilter/ebtable_nat.c | 14 | ||||
| -rw-r--r-- | net/bridge/netfilter/nf_tables_bridge.c | 28 | ||||
| -rw-r--r-- | net/bridge/netfilter/nft_reject_bridge.c | 84 |
12 files changed, 375 insertions, 116 deletions
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index ffd379db5938..4ff77a16956c 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -25,6 +25,9 @@ #define COMMON_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | \ NETIF_F_GSO_MASK | NETIF_F_HW_CSUM) +const struct nf_br_ops __rcu *nf_br_ops __read_mostly; +EXPORT_SYMBOL_GPL(nf_br_ops); + /* net device transmit always called with BH disabled */ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) { @@ -33,16 +36,15 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) struct net_bridge_fdb_entry *dst; struct net_bridge_mdb_entry *mdst; struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats); + const struct nf_br_ops *nf_ops; u16 vid = 0; rcu_read_lock(); -#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) - if (skb->nf_bridge && (skb->nf_bridge->mask & BRNF_BRIDGED_DNAT)) { - br_nf_pre_routing_finish_bridge_slow(skb); + nf_ops = rcu_dereference(nf_br_ops); + if (nf_ops && nf_ops->br_dev_xmit_hook(skb)) { rcu_read_unlock(); return NETDEV_TX_OK; } -#endif u64_stats_update_begin(&brstats->syncp); brstats->tx_packets++; diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index f96933a823e3..3304a5442331 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -37,9 +37,7 @@ static inline int should_deliver(const struct net_bridge_port *p, int br_dev_queue_push_xmit(struct sk_buff *skb) { - /* ip_fragment doesn't copy the MAC header */ - if (nf_bridge_maybe_copy_header(skb) || - !is_skb_forwardable(skb->dev, skb)) { + if (!is_skb_forwardable(skb->dev, skb)) { kfree_skb(skb); } else { skb_push(skb, ETH_HLEN); @@ -188,6 +186,9 @@ static void br_flood(struct net_bridge *br, struct sk_buff *skb, /* Do not flood to ports that enable proxy ARP */ if (p->flags & BR_PROXYARP) continue; + if ((p->flags & BR_PROXYARP_WIFI) && + BR_INPUT_SKB_CB(skb)->proxyarp_replied) + continue; prev = maybe_deliver(prev, p, skb, __packet_hook); if (IS_ERR(prev)) diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index e2aa7be3a847..052c5ebbc947 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -60,7 +60,7 @@ static int br_pass_frame_up(struct sk_buff *skb) } static void br_do_proxy_arp(struct sk_buff *skb, struct net_bridge *br, - u16 vid) + u16 vid, struct net_bridge_port *p) { struct net_device *dev = br->dev; struct neighbour *n; @@ -68,6 +68,8 @@ static void br_do_proxy_arp(struct sk_buff *skb, struct net_bridge *br, u8 *arpptr, *sha; __be32 sip, tip; + BR_INPUT_SKB_CB(skb)->proxyarp_replied = false; + if (dev->flags & IFF_NOARP) return; @@ -105,9 +107,12 @@ static void br_do_proxy_arp(struct sk_buff *skb, struct net_bridge *br, } f = __br_fdb_get(br, n->ha, vid); - if (f) + if (f && ((p->flags & BR_PROXYARP) || + (f->dst && (f->dst->flags & BR_PROXYARP_WIFI)))) { arp_send(ARPOP_REPLY, ETH_P_ARP, sip, skb->dev, tip, sha, n->ha, sha); + BR_INPUT_SKB_CB(skb)->proxyarp_replied = true; + } neigh_release(n); } @@ -153,12 +158,10 @@ int br_handle_frame_finish(struct sk_buff *skb) dst = NULL; - if (is_broadcast_ether_addr(dest)) { - if (IS_ENABLED(CONFIG_INET) && - p->flags & BR_PROXYARP && - skb->protocol == htons(ETH_P_ARP)) - br_do_proxy_arp(skb, br, vid); + if (IS_ENABLED(CONFIG_INET) && skb->protocol == htons(ETH_P_ARP)) + br_do_proxy_arp(skb, br, vid, p); + if (is_broadcast_ether_addr(dest)) { skb2 = skb; unicast = false; } else if (is_multicast_ether_addr(dest)) { diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index 0ee453fad3de..7527e94dd5dc 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -37,17 +37,16 @@ #include <net/route.h> #include <net/netfilter/br_netfilter.h> +#if IS_ENABLED(CONFIG_NF_CONNTRACK) +#include <net/netfilter/nf_conntrack.h> +#endif + #include <asm/uaccess.h> #include "br_private.h" #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif -#define skb_origaddr(skb) (((struct bridge_skb_cb *) \ - (skb->nf_bridge->data))->daddr.ipv4) -#define store_orig_dstaddr(skb) (skb_origaddr(skb) = ip_hdr(skb)->daddr) -#define dnat_took_place(skb) (skb_origaddr(skb) != ip_hdr(skb)->daddr) - #ifdef CONFIG_SYSCTL static struct ctl_table_header *brnf_sysctl_header; static int brnf_call_iptables __read_mostly = 1; @@ -154,6 +153,18 @@ static inline struct nf_bridge_info *nf_bridge_unshare(struct sk_buff *skb) return nf_bridge; } +static unsigned int nf_bridge_encap_header_len(const struct sk_buff *skb) +{ + switch (skb->protocol) { + case __cpu_to_be16(ETH_P_8021Q): + return VLAN_HLEN; + case __cpu_to_be16(ETH_P_PPP_SES): + return PPPOE_SES_HLEN; + default: + return 0; + } +} + static inline void nf_bridge_push_encap_header(struct sk_buff *skb) { unsigned int len = nf_bridge_encap_header_len(skb); @@ -239,6 +250,14 @@ drop: return -1; } +static 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); +} + /* PF_BRIDGE/PRE_ROUTING *********************************************/ /* Undo the changes made for ip6tables PREROUTING and continue the * bridge PRE_ROUTING hook. */ @@ -314,6 +333,22 @@ free_skb: return 0; } +static bool dnat_took_place(const struct sk_buff *skb) +{ +#if IS_ENABLED(CONFIG_NF_CONNTRACK) + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + + ct = nf_ct_get(skb, &ctinfo); + if (!ct || nf_ct_is_untracked(ct)) + return false; + + return test_bit(IPS_DST_NAT_BIT, &ct->status); +#else + return false; +#endif +} + /* This requires some explaining. If DNAT has taken place, * we will need to fix up the destination Ethernet address. * @@ -527,9 +562,7 @@ bad: * to ip6tables, which doesn't support NAT, so things are fairly simple. */ static unsigned int br_nf_pre_routing_ipv6(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { const struct ipv6hdr *hdr; u32 pkt_len; @@ -577,9 +610,7 @@ static unsigned int br_nf_pre_routing_ipv6(const struct nf_hook_ops *ops, * address to be able to detect DNAT afterwards. */ 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 *)) + const struct nf_hook_state *state) { struct net_bridge_port *p; struct net_bridge *br; @@ -588,7 +619,7 @@ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops, if (unlikely(!pskb_may_pull(skb, len))) return NF_DROP; - p = br_port_get_rcu(in); + p = br_port_get_rcu(state->in); if (p == NULL) return NF_DROP; br = p->br; @@ -598,7 +629,7 @@ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops, return NF_ACCEPT; nf_bridge_pull_encap_header_rcsum(skb); - return br_nf_pre_routing_ipv6(ops, skb, in, out, okfn); + return br_nf_pre_routing_ipv6(ops, skb, state); } if (!brnf_call_iptables && !br->nf_call_iptables) @@ -617,7 +648,7 @@ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops, return NF_DROP; if (!setup_pre_routing(skb)) return NF_DROP; - store_orig_dstaddr(skb); + skb->protocol = htons(ETH_P_IP); NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, skb, skb->dev, NULL, @@ -636,9 +667,7 @@ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops, * prevent this from happening. */ 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 *)) + const struct nf_hook_state *state) { br_drop_fake_rtable(skb); return NF_ACCEPT; @@ -675,9 +704,7 @@ static int br_nf_forward_finish(struct sk_buff *skb) * bridge ports. */ 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 *)) + const struct nf_hook_state *state) { struct nf_bridge_info *nf_bridge; struct net_device *parent; @@ -691,7 +718,7 @@ static unsigned int br_nf_forward_ip(const struct nf_hook_ops *ops, if (!nf_bridge_unshare(skb)) return NF_DROP; - parent = bridge_parent(out); + parent = bridge_parent(state->out); if (!parent) return NF_DROP; @@ -713,31 +740,27 @@ static unsigned int br_nf_forward_ip(const struct nf_hook_ops *ops, 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, brnf_get_logical_dev(skb, in), parent, - br_nf_forward_finish); + NF_HOOK(pf, NF_INET_FORWARD, skb, brnf_get_logical_dev(skb, state->in), + parent, br_nf_forward_finish); return NF_STOLEN; } 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 *)) + const struct nf_hook_state *state) { struct net_bridge_port *p; struct net_bridge *br; struct net_device **d = (struct net_device **)(skb->cb); - p = br_port_get_rcu(out); + p = br_port_get_rcu(state->out); if (p == NULL) return NF_ACCEPT; br = p->br; @@ -756,31 +779,61 @@ static unsigned int br_nf_forward_arp(const struct nf_hook_ops *ops, nf_bridge_push_encap_header(skb); return NF_ACCEPT; } - *d = (struct net_device *)in; - NF_HOOK(NFPROTO_ARP, NF_ARP_FORWARD, skb, (struct net_device *)in, - (struct net_device *)out, br_nf_forward_finish); + *d = state->in; + NF_HOOK(NFPROTO_ARP, NF_ARP_FORWARD, skb, state->in, + state->out, br_nf_forward_finish); return NF_STOLEN; } #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) +static bool nf_bridge_copy_header(struct sk_buff *skb) +{ + int err; + 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 false; + + skb_copy_to_linear_data_offset(skb, -header_size, + skb->nf_bridge->data, header_size); + __skb_push(skb, nf_bridge_encap_header_len(skb)); + return true; +} + +static int br_nf_push_frag_xmit(struct sk_buff *skb) +{ + if (!nf_bridge_copy_header(skb)) { + kfree_skb(skb); + return 0; + } + + return br_dev_queue_push_xmit(skb); +} + static int br_nf_dev_queue_xmit(struct sk_buff *skb) { int ret; int frag_max_size; + unsigned int mtu_reserved; + + if (skb_is_gso(skb) || skb->protocol != htons(ETH_P_IP)) + return br_dev_queue_push_xmit(skb); + mtu_reserved = nf_bridge_mtu_reduction(skb); /* This is wrong! We should preserve the original fragment * boundaries by preserving frag_list rather than refragmenting. */ - if (skb->protocol == htons(ETH_P_IP) && - skb->len + nf_bridge_mtu_reduction(skb) > skb->dev->mtu && - !skb_is_gso(skb)) { + if (skb->len + mtu_reserved > skb->dev->mtu) { frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size; if (br_parse_ip_options(skb)) /* Drop invalid packet */ return NF_DROP; IPCB(skb)->frag_max_size = frag_max_size; - ret = ip_fragment(skb, br_dev_queue_push_xmit); + ret = ip_fragment(skb, br_nf_push_frag_xmit); } else ret = br_dev_queue_push_xmit(skb); @@ -796,15 +849,18 @@ static int br_nf_dev_queue_xmit(struct sk_buff *skb) /* PF_BRIDGE/POST_ROUTING ********************************************/ 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 *)) + const struct nf_hook_state *state) { struct nf_bridge_info *nf_bridge = skb->nf_bridge; struct net_device *realoutdev = bridge_parent(skb->dev); u_int8_t pf; - if (!nf_bridge || !(nf_bridge->mask & BRNF_BRIDGED)) + /* if nf_bridge is set, but ->physoutdev is NULL, this packet came in + * on a bridge, but was delivered locally and is now being routed: + * + * POST_ROUTING was already invoked from the ip stack. + */ + if (!nf_bridge || !nf_bridge->physoutdev) return NF_ACCEPT; if (!realoutdev) @@ -842,9 +898,7 @@ static unsigned int br_nf_post_routing(const struct nf_hook_ops *ops, * for the second time. */ 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 *)) + const struct nf_hook_state *state) { if (skb->nf_bridge && !(skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING)) { @@ -854,6 +908,41 @@ static unsigned int ip_sabotage_in(const struct nf_hook_ops *ops, return NF_ACCEPT; } +/* This is called when br_netfilter has called into iptables/netfilter, + * and DNAT has taken place on a bridge-forwarded packet. + * + * neigh->output has created a new MAC header, with local br0 MAC + * as saddr. + * + * This restores the original MAC saddr of the bridged packet + * before invoking bridge forward logic to transmit the packet. + */ +static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb) +{ + struct nf_bridge_info *nf_bridge = skb->nf_bridge; + + skb_pull(skb, ETH_HLEN); + nf_bridge->mask &= ~BRNF_BRIDGED_DNAT; + + skb_copy_to_linear_data_offset(skb, -(ETH_HLEN-ETH_ALEN), + skb->nf_bridge->data, ETH_HLEN-ETH_ALEN); + skb->dev = nf_bridge->physindev; + br_handle_frame_finish(skb); +} + +static int br_nf_dev_xmit(struct sk_buff *skb) +{ + if (skb->nf_bridge && (skb->nf_bridge->mask & BRNF_BRIDGED_DNAT)) { + br_nf_pre_routing_finish_bridge_slow(skb); + return 1; + } + return 0; +} + +static const struct nf_br_ops br_ops = { + .br_dev_xmit_hook = br_nf_dev_xmit, +}; + void br_netfilter_enable(void) { } @@ -991,12 +1080,14 @@ static int __init br_netfilter_init(void) return -ENOMEM; } #endif + RCU_INIT_POINTER(nf_br_ops, &br_ops); printk(KERN_NOTICE "Bridge firewalling registered\n"); return 0; } static void __exit br_netfilter_fini(void) { + RCU_INIT_POINTER(nf_br_ops, NULL); nf_unregister_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops)); #ifdef CONFIG_SYSCTL unregister_net_sysctl_table(brnf_sysctl_header); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 4fbcea0e7ecb..0e4ddb81610d 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -22,6 +22,85 @@ #include "br_private.h" #include "br_private_stp.h" +static int br_get_num_vlan_infos(const struct net_port_vlans *pv, + u32 filter_mask) +{ + u16 vid_range_start = 0, vid_range_end = 0; + u16 vid_range_flags = 0; + u16 pvid, vid, flags; + int num_vlans = 0; + + if (filter_mask & RTEXT_FILTER_BRVLAN) + return pv->num_vlans; + + if (!(filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) + return 0; + + /* Count number of vlan info's + */ + pvid = br_get_pvid(pv); + for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { + flags = 0; + if (vid == pvid) + flags |= BRIDGE_VLAN_INFO_PVID; + + if (test_bit(vid, pv->untagged_bitmap)) + flags |= BRIDGE_VLAN_INFO_UNTAGGED; + + if (vid_range_start == 0) { + goto initvars; + } else if ((vid - vid_range_end) == 1 && + flags == vid_range_flags) { + vid_range_end = vid; + continue; + } else { + if ((vid_range_end - vid_range_start) > 0) + num_vlans += 2; + else + num_vlans += 1; + } +initvars: + vid_range_start = vid; + vid_range_end = vid; + vid_range_flags = flags; + } + + if (vid_range_start != 0) { + if ((vid_range_end - vid_range_start) > 0) + num_vlans += 2; + else + num_vlans += 1; + } + + return num_vlans; +} + +static size_t br_get_link_af_size_filtered(const struct net_device *dev, + u32 filter_mask) +{ + struct net_port_vlans *pv; + int num_vlan_infos; + + rcu_read_lock(); + if (br_port_exists(dev)) + pv = nbp_get_vlan_info(br_port_get_rcu(dev)); + else if (dev->priv_flags & IFF_EBRIDGE) + pv = br_get_vlan_info((struct net_bridge *)netdev_priv(dev)); + else + pv = NULL; + if (pv) + num_vlan_infos = br_get_num_vlan_infos(pv, filter_mask); + else + num_vlan_infos = 0; + rcu_read_unlock(); + + if (!num_vlan_infos) + return 0; + + /* Each VLAN is returned in bridge_vlan_info along with flags */ + return num_vlan_infos * nla_total_size(sizeof(struct bridge_vlan_info)); +} + static inline size_t br_port_info_size(void) { return nla_total_size(1) /* IFLA_BRPORT_STATE */ @@ -36,7 +115,7 @@ static inline size_t br_port_info_size(void) + 0; } -static inline size_t br_nlmsg_size(void) +static inline size_t br_nlmsg_size(struct net_device *dev, u32 filter_mask) { return NLMSG_ALIGN(sizeof(struct ifinfomsg)) + nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */ @@ -45,7 +124,9 @@ static inline size_t br_nlmsg_size(void) + 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 */ + + nla_total_size(br_port_info_size()) /* IFLA_PROTINFO */ + + nla_total_size(br_get_link_af_size_filtered(dev, + filter_mask)); /* IFLA_AF_SPEC */ } static int br_port_fill_attrs(struct sk_buff *skb, @@ -62,7 +143,9 @@ static int br_port_fill_attrs(struct sk_buff *skb, 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)) || - nla_put_u8(skb, IFLA_BRPORT_PROXYARP, !!(p->flags & BR_PROXYARP))) + nla_put_u8(skb, IFLA_BRPORT_PROXYARP, !!(p->flags & BR_PROXYARP)) || + nla_put_u8(skb, IFLA_BRPORT_PROXYARP_WIFI, + !!(p->flags & BR_PROXYARP_WIFI))) return -EMSGSIZE; return 0; @@ -222,8 +305,8 @@ static int br_fill_ifinfo(struct sk_buff *skb, 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))) + (dev->ifindex != dev_get_iflink(dev) && + nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev)))) goto nla_put_failure; if (event == RTM_NEWLINK && port) { @@ -280,6 +363,7 @@ void br_ifinfo_notify(int event, struct net_bridge_port *port) struct net *net; struct sk_buff *skb; int err = -ENOBUFS; + u32 filter = RTEXT_FILTER_BRVLAN_COMPRESSED; if (!port) return; @@ -288,11 +372,11 @@ void br_ifinfo_notify(int event, struct net_bridge_port *port) 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); + skb = nlmsg_new(br_nlmsg_size(port->dev, filter), GFP_ATOMIC); if (skb == NULL) goto errout; - err = br_fill_ifinfo(skb, port, 0, 0, event, 0, 0, port->dev); + err = br_fill_ifinfo(skb, port, 0, 0, event, 0, filter, port->dev); if (err < 0) { /* -EMSGSIZE implies BUG in br_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); @@ -471,6 +555,7 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[]) br_set_port_flag(p, tb, IFLA_BRPORT_LEARNING, BR_LEARNING); br_set_port_flag(p, tb, IFLA_BRPORT_UNICAST_FLOOD, BR_FLOOD); br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP, BR_PROXYARP); + br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP_WIFI, BR_PROXYARP_WIFI); if (tb[IFLA_BRPORT_COST]) { err = br_stp_set_path_cost(p, nla_get_u32(tb[IFLA_BRPORT_COST])); @@ -648,6 +733,9 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_FORWARD_DELAY] = { .type = NLA_U32 }, [IFLA_BR_HELLO_TIME] = { .type = NLA_U32 }, [IFLA_BR_MAX_AGE] = { .type = NLA_U32 }, + [IFLA_BR_AGEING_TIME] = { .type = NLA_U32 }, + [IFLA_BR_STP_STATE] = { .type = NLA_U32 }, + [IFLA_BR_PRIORITY] = { .type = NLA_U16 }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], @@ -677,6 +765,24 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], return err; } + if (data[IFLA_BR_AGEING_TIME]) { + u32 ageing_time = nla_get_u32(data[IFLA_BR_AGEING_TIME]); + + br->ageing_time = clock_t_to_jiffies(ageing_time); + } + + if (data[IFLA_BR_STP_STATE]) { + u32 stp_enabled = nla_get_u32(data[IFLA_BR_STP_STATE]); + + br_stp_set_enabled(br, stp_enabled); + } + + if (data[IFLA_BR_PRIORITY]) { + u32 priority = nla_get_u16(data[IFLA_BR_PRIORITY]); + + br_stp_set_bridge_priority(br, priority); + } + return 0; } @@ -685,6 +791,9 @@ static size_t br_get_size(const struct net_device *brdev) return nla_total_size(sizeof(u32)) + /* IFLA_BR_FORWARD_DELAY */ nla_total_size(sizeof(u32)) + /* IFLA_BR_HELLO_TIME */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MAX_AGE */ + nla_total_size(sizeof(u32)) + /* IFLA_BR_AGEING_TIME */ + nla_total_size(sizeof(u32)) + /* IFLA_BR_STP_STATE */ + nla_total_size(sizeof(u16)) + /* IFLA_BR_PRIORITY */ 0; } @@ -694,10 +803,16 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) u32 forward_delay = jiffies_to_clock_t(br->forward_delay); u32 hello_time = jiffies_to_clock_t(br->hello_time); u32 age_time = jiffies_to_clock_t(br->max_age); + u32 ageing_time = jiffies_to_clock_t(br->ageing_time); + u32 stp_enabled = br->stp_enabled; + u16 priority = (br->bridge_id.prio[0] << 8) | br->bridge_id.prio[1]; if (nla_put_u32(skb, IFLA_BR_FORWARD_DELAY, forward_delay) || nla_put_u32(skb, IFLA_BR_HELLO_TIME, hello_time) || - nla_put_u32(skb, IFLA_BR_MAX_AGE, age_time)) + nla_put_u32(skb, IFLA_BR_MAX_AGE, age_time) || + nla_put_u32(skb, IFLA_BR_AGEING_TIME, ageing_time) || + nla_put_u32(skb, IFLA_BR_STP_STATE, stp_enabled) || + nla_put_u16(skb, IFLA_BR_PRIORITY, priority)) return -EMSGSIZE; return 0; diff --git a/net/bridge/br_nf_core.c b/net/bridge/br_nf_core.c index 387cb3bd017c..20cbb727df4d 100644 --- a/net/bridge/br_nf_core.c +++ b/net/bridge/br_nf_core.c @@ -54,7 +54,6 @@ static unsigned int fake_mtu(const struct dst_entry *dst) static struct dst_ops fake_dst_ops = { .family = AF_INET, - .protocol = cpu_to_be16(ETH_P_IP), .update_pmtu = fake_update_pmtu, .redirect = fake_redirect, .cow_metrics = fake_cow_metrics, diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index de0919975a25..b46fa0c5b8ec 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -305,6 +305,7 @@ struct br_input_skb_cb { #endif u16 frag_max_size; + bool proxyarp_replied; #ifdef CONFIG_BRIDGE_VLAN_FILTERING bool vlan_filtered; @@ -762,6 +763,11 @@ static inline int br_vlan_enabled(struct net_bridge *br) } #endif +struct nf_br_ops { + int (*br_dev_xmit_hook)(struct sk_buff *skb); +}; +extern const struct nf_br_ops __rcu *nf_br_ops; + /* br_netfilter.c */ #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) int br_nf_core_init(void); diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index 2de5d91199e8..4905845a94e9 100644 --- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -171,6 +171,7 @@ BRPORT_ATTR_FLAG(root_block, BR_ROOT_BLOCK); BRPORT_ATTR_FLAG(learning, BR_LEARNING); BRPORT_ATTR_FLAG(unicast_flood, BR_FLOOD); BRPORT_ATTR_FLAG(proxyarp, BR_PROXYARP); +BRPORT_ATTR_FLAG(proxyarp_wifi, BR_PROXYARP_WIFI); #ifdef CONFIG_BRIDGE_IGMP_SNOOPING static ssize_t show_multicast_router(struct net_bridge_port *p, char *buf) @@ -215,6 +216,7 @@ static const struct brport_attribute *brport_attrs[] = { &brport_attr_multicast_fast_leave, #endif &brport_attr_proxyarp, + &brport_attr_proxyarp_wifi, NULL }; diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c index ce205aabf9c5..8a3f63b2e807 100644 --- a/net/bridge/netfilter/ebtable_filter.c +++ b/net/bridge/netfilter/ebtable_filter.c @@ -58,20 +58,18 @@ static const struct ebt_table frame_filter = { static unsigned int 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 *)) + const struct nf_hook_state *state) { - return ebt_do_table(ops->hooknum, skb, in, out, - dev_net(in)->xt.frame_filter); + return ebt_do_table(ops->hooknum, skb, state->in, state->out, + dev_net(state->in)->xt.frame_filter); } static unsigned int 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 *)) + const struct nf_hook_state *state) { - return ebt_do_table(ops->hooknum, skb, in, out, - dev_net(out)->xt.frame_filter); + return ebt_do_table(ops->hooknum, skb, state->in, state->out, + dev_net(state->out)->xt.frame_filter); } static struct nf_hook_ops ebt_ops_filter[] __read_mostly = { diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c index a0ac2984fb6c..c5ef5b1ab678 100644 --- a/net/bridge/netfilter/ebtable_nat.c +++ b/net/bridge/netfilter/ebtable_nat.c @@ -58,20 +58,18 @@ static struct ebt_table frame_nat = { static unsigned int 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 *)) + const struct nf_hook_state *state) { - return ebt_do_table(ops->hooknum, skb, in, out, - dev_net(in)->xt.frame_nat); + return ebt_do_table(ops->hooknum, skb, state->in, state->out, + dev_net(state->in)->xt.frame_nat); } static unsigned int 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 *)) + const struct nf_hook_state *state) { - return ebt_do_table(ops->hooknum, skb, in, out, - dev_net(out)->xt.frame_nat); + return ebt_do_table(ops->hooknum, skb, state->in, state->out, + dev_net(state->out)->xt.frame_nat); } static struct nf_hook_ops ebt_ops_nat[] __read_mostly = { diff --git a/net/bridge/netfilter/nf_tables_bridge.c b/net/bridge/netfilter/nf_tables_bridge.c index 19473a9371b8..a343e62442b1 100644 --- a/net/bridge/netfilter/nf_tables_bridge.c +++ b/net/bridge/netfilter/nf_tables_bridge.c @@ -67,47 +67,43 @@ EXPORT_SYMBOL_GPL(nft_bridge_ip6hdr_validate); static inline void nft_bridge_set_pktinfo_ipv4(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out) + const struct nf_hook_state *state) { if (nft_bridge_iphdr_validate(skb)) - nft_set_pktinfo_ipv4(pkt, ops, skb, in, out); + nft_set_pktinfo_ipv4(pkt, ops, skb, state); else - nft_set_pktinfo(pkt, ops, skb, in, out); + nft_set_pktinfo(pkt, ops, skb, state); } static inline void nft_bridge_set_pktinfo_ipv6(struct nft_pktinfo *pkt, - const struct nf_hook_ops *ops, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out) + const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct nf_hook_state *state) { #if IS_ENABLED(CONFIG_IPV6) if (nft_bridge_ip6hdr_validate(skb) && - nft_set_pktinfo_ipv6(pkt, ops, skb, in, out) == 0) + nft_set_pktinfo_ipv6(pkt, ops, skb, state) == 0) return; #endif - nft_set_pktinfo(pkt, ops, skb, in, out); + nft_set_pktinfo(pkt, ops, skb, state); } 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 *)) + const struct nf_hook_state *state) { struct nft_pktinfo pkt; switch (eth_hdr(skb)->h_proto) { case htons(ETH_P_IP): - nft_bridge_set_pktinfo_ipv4(&pkt, ops, skb, in, out); + nft_bridge_set_pktinfo_ipv4(&pkt, ops, skb, state); break; case htons(ETH_P_IPV6): - nft_bridge_set_pktinfo_ipv6(&pkt, ops, skb, in, out); + nft_bridge_set_pktinfo_ipv6(&pkt, ops, skb, state); break; default: - nft_set_pktinfo(&pkt, ops, skb, in, out); + nft_set_pktinfo(&pkt, ops, skb, state); break; } diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c index 3244aead0926..54a2fdf0f457 100644 --- a/net/bridge/netfilter/nft_reject_bridge.c +++ b/net/bridge/netfilter/nft_reject_bridge.c @@ -21,6 +21,7 @@ #include <net/ip.h> #include <net/ip6_checksum.h> #include <linux/netfilter_bridge.h> +#include <linux/netfilter_ipv6.h> #include "../br_private.h" static void nft_reject_br_push_etherhdr(struct sk_buff *oldskb, @@ -36,7 +37,12 @@ static void nft_reject_br_push_etherhdr(struct sk_buff *oldskb, skb_pull(nskb, ETH_HLEN); } -static void nft_reject_br_send_v4_tcp_reset(struct sk_buff *oldskb, int hook) +/* We cannot use oldskb->dev, it can be either bridge device (NF_BRIDGE INPUT) + * or the bridge port (NF_BRIDGE PREROUTING). + */ +static void nft_reject_br_send_v4_tcp_reset(struct sk_buff *oldskb, + const struct net_device *dev, + int hook) { struct sk_buff *nskb; struct iphdr *niph; @@ -65,11 +71,12 @@ static void nft_reject_br_send_v4_tcp_reset(struct sk_buff *oldskb, int hook) nft_reject_br_push_etherhdr(oldskb, nskb); - br_deliver(br_port_get_rcu(oldskb->dev), nskb); + br_deliver(br_port_get_rcu(dev), nskb); } -static void nft_reject_br_send_v4_unreach(struct sk_buff *oldskb, int hook, - u8 code) +static void nft_reject_br_send_v4_unreach(struct sk_buff *oldskb, + const struct net_device *dev, + int hook, u8 code) { struct sk_buff *nskb; struct iphdr *niph; @@ -77,8 +84,9 @@ static void nft_reject_br_send_v4_unreach(struct sk_buff *oldskb, int hook, unsigned int len; void *payload; __wsum csum; + u8 proto; - if (!nft_bridge_iphdr_validate(oldskb)) + if (oldskb->csum_bad || !nft_bridge_iphdr_validate(oldskb)) return; /* IP header checks: fragment. */ @@ -91,7 +99,17 @@ static void nft_reject_br_send_v4_unreach(struct sk_buff *oldskb, int hook, if (!pskb_may_pull(oldskb, len)) return; - if (nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), 0)) + if (pskb_trim_rcsum(oldskb, ntohs(ip_hdr(oldskb)->tot_len))) + return; + + if (ip_hdr(oldskb)->protocol == IPPROTO_TCP || + ip_hdr(oldskb)->protocol == IPPROTO_UDP) + proto = ip_hdr(oldskb)->protocol; + else + proto = 0; + + if (!skb_csum_unnecessary(oldskb) && + nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), proto)) return; nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct icmphdr) + @@ -120,11 +138,13 @@ static void nft_reject_br_send_v4_unreach(struct sk_buff *oldskb, int hook, nft_reject_br_push_etherhdr(oldskb, nskb); - br_deliver(br_port_get_rcu(oldskb->dev), nskb); + br_deliver(br_port_get_rcu(dev), nskb); } static void nft_reject_br_send_v6_tcp_reset(struct net *net, - struct sk_buff *oldskb, int hook) + struct sk_buff *oldskb, + const struct net_device *dev, + int hook) { struct sk_buff *nskb; const struct tcphdr *oth; @@ -152,12 +172,37 @@ static void nft_reject_br_send_v6_tcp_reset(struct net *net, nft_reject_br_push_etherhdr(oldskb, nskb); - br_deliver(br_port_get_rcu(oldskb->dev), nskb); + br_deliver(br_port_get_rcu(dev), nskb); +} + +static bool reject6_br_csum_ok(struct sk_buff *skb, int hook) +{ + const struct ipv6hdr *ip6h = ipv6_hdr(skb); + int thoff; + __be16 fo; + u8 proto = ip6h->nexthdr; + + if (skb->csum_bad) + return false; + + if (skb_csum_unnecessary(skb)) + return true; + + if (ip6h->payload_len && + pskb_trim_rcsum(skb, ntohs(ip6h->payload_len) + sizeof(*ip6h))) + return false; + + thoff = ipv6_skip_exthdr(skb, ((u8*)(ip6h+1) - skb->data), &proto, &fo); + if (thoff < 0 || thoff >= skb->len || (fo & htons(~0x7)) != 0) + return false; + + return nf_ip6_checksum(skb, hook, thoff, proto) == 0; } static void nft_reject_br_send_v6_unreach(struct net *net, - struct sk_buff *oldskb, int hook, - u8 code) + struct sk_buff *oldskb, + const struct net_device *dev, + int hook, u8 code) { struct sk_buff *nskb; struct ipv6hdr *nip6h; @@ -176,6 +221,9 @@ static void nft_reject_br_send_v6_unreach(struct net *net, if (!pskb_may_pull(oldskb, len)) return; + if (!reject6_br_csum_ok(oldskb, hook)) + return; + nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct icmp6hdr) + LL_MAX_HEADER + len, GFP_ATOMIC); if (!nskb) @@ -205,7 +253,7 @@ static void nft_reject_br_send_v6_unreach(struct net *net, nft_reject_br_push_etherhdr(oldskb, nskb); - br_deliver(br_port_get_rcu(oldskb->dev), nskb); + br_deliver(br_port_get_rcu(dev), nskb); } static void nft_reject_bridge_eval(const struct nft_expr *expr, @@ -224,16 +272,16 @@ static void nft_reject_bridge_eval(const struct nft_expr *expr, case htons(ETH_P_IP): switch (priv->type) { case NFT_REJECT_ICMP_UNREACH: - nft_reject_br_send_v4_unreach(pkt->skb, + nft_reject_br_send_v4_unreach(pkt->skb, pkt->in, pkt->ops->hooknum, priv->icmp_code); break; case NFT_REJECT_TCP_RST: - nft_reject_br_send_v4_tcp_reset(pkt->skb, + nft_reject_br_send_v4_tcp_reset(pkt->skb, pkt->in, pkt->ops->hooknum); break; case NFT_REJECT_ICMPX_UNREACH: - nft_reject_br_send_v4_unreach(pkt->skb, + nft_reject_br_send_v4_unreach(pkt->skb, pkt->in, pkt->ops->hooknum, nft_reject_icmp_code(priv->icmp_code)); break; @@ -242,16 +290,16 @@ static void nft_reject_bridge_eval(const struct nft_expr *expr, case htons(ETH_P_IPV6): switch (priv->type) { case NFT_REJECT_ICMP_UNREACH: - nft_reject_br_send_v6_unreach(net, pkt->skb, + nft_reject_br_send_v6_unreach(net, pkt->skb, pkt->in, pkt->ops->hooknum, priv->icmp_code); break; case NFT_REJECT_TCP_RST: - nft_reject_br_send_v6_tcp_reset(net, pkt->skb, + nft_reject_br_send_v6_tcp_reset(net, pkt->skb, pkt->in, pkt->ops->hooknum); break; case NFT_REJECT_ICMPX_UNREACH: - nft_reject_br_send_v6_unreach(net, pkt->skb, + nft_reject_br_send_v6_unreach(net, pkt->skb, pkt->in, pkt->ops->hooknum, nft_reject_icmpv6_code(priv->icmp_code)); break; |