summaryrefslogtreecommitdiffstats
path: root/net/bridge
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2019-07-11 10:55:49 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2019-07-11 10:55:49 -0700
commit237f83dfbe668443b5e31c3c7576125871cca674 (patch)
tree11848a8d0aa414a1d3ce2024e181071b1d9dea08 /net/bridge
parent8f6ccf6159aed1f04c6d179f61f6fb2691261e84 (diff)
parent1ff2f0fa450ea4e4f87793d9ed513098ec6e12be (diff)
downloadlinux-237f83dfbe668443b5e31c3c7576125871cca674.tar.gz
linux-237f83dfbe668443b5e31c3c7576125871cca674.tar.bz2
linux-237f83dfbe668443b5e31c3c7576125871cca674.zip
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller: "Some highlights from this development cycle: 1) Big refactoring of ipv6 route and neigh handling to support nexthop objects configurable as units from userspace. From David Ahern. 2) Convert explored_states in BPF verifier into a hash table, significantly decreased state held for programs with bpf2bpf calls, from Alexei Starovoitov. 3) Implement bpf_send_signal() helper, from Yonghong Song. 4) Various classifier enhancements to mvpp2 driver, from Maxime Chevallier. 5) Add aRFS support to hns3 driver, from Jian Shen. 6) Fix use after free in inet frags by allocating fqdirs dynamically and reworking how rhashtable dismantle occurs, from Eric Dumazet. 7) Add act_ctinfo packet classifier action, from Kevin Darbyshire-Bryant. 8) Add TFO key backup infrastructure, from Jason Baron. 9) Remove several old and unused ISDN drivers, from Arnd Bergmann. 10) Add devlink notifications for flash update status to mlxsw driver, from Jiri Pirko. 11) Lots of kTLS offload infrastructure fixes, from Jakub Kicinski. 12) Add support for mv88e6250 DSA chips, from Rasmus Villemoes. 13) Various enhancements to ipv6 flow label handling, from Eric Dumazet and Willem de Bruijn. 14) Support TLS offload in nfp driver, from Jakub Kicinski, Dirk van der Merwe, and others. 15) Various improvements to axienet driver including converting it to phylink, from Robert Hancock. 16) Add PTP support to sja1105 DSA driver, from Vladimir Oltean. 17) Add mqprio qdisc offload support to dpaa2-eth, from Ioana Radulescu. 18) Add devlink health reporting to mlx5, from Moshe Shemesh. 19) Convert stmmac over to phylink, from Jose Abreu. 20) Add PTP PHC (Physical Hardware Clock) support to mlxsw, from Shalom Toledo. 21) Add nftables SYNPROXY support, from Fernando Fernandez Mancera. 22) Convert tcp_fastopen over to use SipHash, from Ard Biesheuvel. 23) Track spill/fill of constants in BPF verifier, from Alexei Starovoitov. 24) Support bounded loops in BPF, from Alexei Starovoitov. 25) Various page_pool API fixes and improvements, from Jesper Dangaard Brouer. 26) Just like ipv4, support ref-countless ipv6 route handling. From Wei Wang. 27) Support VLAN offloading in aquantia driver, from Igor Russkikh. 28) Add AF_XDP zero-copy support to mlx5, from Maxim Mikityanskiy. 29) Add flower GRE encap/decap support to nfp driver, from Pieter Jansen van Vuuren. 30) Protect against stack overflow when using act_mirred, from John Hurley. 31) Allow devmap map lookups from eBPF, from Toke Høiland-Jørgensen. 32) Use page_pool API in netsec driver, Ilias Apalodimas. 33) Add Google gve network driver, from Catherine Sullivan. 34) More indirect call avoidance, from Paolo Abeni. 35) Add kTLS TX HW offload support to mlx5, from Tariq Toukan. 36) Add XDP_REDIRECT support to bnxt_en, from Andy Gospodarek. 37) Add MPLS manipulation actions to TC, from John Hurley. 38) Add sending a packet to connection tracking from TC actions, and then allow flower classifier matching on conntrack state. From Paul Blakey. 39) Netfilter hw offload support, from Pablo Neira Ayuso" * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2080 commits) net/mlx5e: Return in default case statement in tx_post_resync_params mlx5: Return -EINVAL when WARN_ON_ONCE triggers in mlx5e_tls_resync(). net: dsa: add support for BRIDGE_MROUTER attribute pkt_sched: Include const.h net: netsec: remove static declaration for netsec_set_tx_de() net: netsec: remove superfluous if statement netfilter: nf_tables: add hardware offload support net: flow_offload: rename tc_cls_flower_offload to flow_cls_offload net: flow_offload: add flow_block_cb_is_busy() and use it net: sched: remove tcf block API drivers: net: use flow block API net: sched: use flow block API net: flow_offload: add flow_block_cb_{priv, incref, decref}() net: flow_offload: add list handling functions net: flow_offload: add flow_block_cb_alloc() and flow_block_cb_free() net: flow_offload: rename TCF_BLOCK_BINDER_TYPE_* to FLOW_BLOCK_BINDER_TYPE_* net: flow_offload: rename TC_BLOCK_{UN}BIND to FLOW_BLOCK_{UN}BIND net: flow_offload: add flow_block_cb_setup_simple() net: hisilicon: Add an tx_desc to adapt HI13X1_GMAC net: hisilicon: Add an rx_desc to adapt HI13X1_GMAC ...
Diffstat (limited to 'net/bridge')
-rw-r--r--net/bridge/br_device.c1
-rw-r--r--net/bridge/br_input.c10
-rw-r--r--net/bridge/br_multicast.c23
-rw-r--r--net/bridge/br_netfilter_hooks.c247
-rw-r--r--net/bridge/br_netfilter_ipv6.c2
-rw-r--r--net/bridge/br_private.h1
-rw-r--r--net/bridge/br_stp_bpdu.c3
-rw-r--r--net/bridge/br_vlan.c29
-rw-r--r--net/bridge/netfilter/Kconfig20
-rw-r--r--net/bridge/netfilter/Makefile4
-rw-r--r--net/bridge/netfilter/ebt_dnat.c2
-rw-r--r--net/bridge/netfilter/ebt_redirect.c2
-rw-r--r--net/bridge/netfilter/ebt_snat.c2
-rw-r--r--net/bridge/netfilter/nf_conntrack_bridge.c435
-rw-r--r--net/bridge/netfilter/nft_meta_bridge.c163
15 files changed, 832 insertions, 112 deletions
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index c05def8fd9cd..681b72862c16 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -52,6 +52,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
br_switchdev_frame_unmark(skb);
BR_INPUT_SKB_CB(skb)->brdev = dev;
+ BR_INPUT_SKB_CB(skb)->frag_max_size = 0;
skb_reset_mac_header(skb);
eth = eth_hdr(skb);
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 21b74e7a7b2f..09b1dd8cd853 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -74,7 +74,6 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
struct net_bridge_fdb_entry *dst = NULL;
struct net_bridge_mdb_entry *mdst;
bool local_rcv, mcast_hit = false;
- const unsigned char *dest;
struct net_bridge *br;
u16 vid = 0;
@@ -92,10 +91,9 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, false);
local_rcv = !!(br->dev->flags & IFF_PROMISC);
- dest = eth_hdr(skb)->h_dest;
- if (is_multicast_ether_addr(dest)) {
+ if (is_multicast_ether_addr(eth_hdr(skb)->h_dest)) {
/* by definition the broadcast is also a multicast address */
- if (is_broadcast_ether_addr(dest)) {
+ if (is_broadcast_ether_addr(eth_hdr(skb)->h_dest)) {
pkt_type = BR_PKT_BROADCAST;
local_rcv = true;
} else {
@@ -145,7 +143,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
}
break;
case BR_PKT_UNICAST:
- dst = br_fdb_find_rcu(br, dest, vid);
+ dst = br_fdb_find_rcu(br, eth_hdr(skb)->h_dest, vid);
default:
break;
}
@@ -234,7 +232,7 @@ static int nf_hook_bridge_pre(struct sk_buff *skb, struct sk_buff **pskb)
kfree_skb(skb);
return RX_HANDLER_CONSUMED;
case NF_QUEUE:
- ret = nf_queue(skb, &state, e, i, verdict);
+ ret = nf_queue(skb, &state, i, verdict);
if (ret == 1)
continue;
return RX_HANDLER_CONSUMED;
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index de22c8fbbb15..3d8deac2353d 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -911,6 +911,7 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br,
int type;
int err = 0;
__be32 group;
+ u16 nsrcs;
ih = igmpv3_report_hdr(skb);
num = ntohs(ih->ngrec);
@@ -924,8 +925,9 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br,
grec = (void *)(skb->data + len - sizeof(*grec));
group = grec->grec_mca;
type = grec->grec_type;
+ nsrcs = ntohs(grec->grec_nsrcs);
- len += ntohs(grec->grec_nsrcs) * 4;
+ len += nsrcs * 4;
if (!ip_mc_may_pull(skb, len))
return -EINVAL;
@@ -946,7 +948,7 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br,
src = eth_hdr(skb)->h_source;
if ((type == IGMPV3_CHANGE_TO_INCLUDE ||
type == IGMPV3_MODE_IS_INCLUDE) &&
- ntohs(grec->grec_nsrcs) == 0) {
+ nsrcs == 0) {
br_ip4_multicast_leave_group(br, port, group, vid, src);
} else {
err = br_ip4_multicast_add_group(br, port, group, vid,
@@ -983,7 +985,8 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br,
len = skb_transport_offset(skb) + sizeof(*icmp6h);
for (i = 0; i < num; i++) {
- __be16 *nsrcs, _nsrcs;
+ __be16 *_nsrcs, __nsrcs;
+ u16 nsrcs;
nsrcs_offset = len + offsetof(struct mld2_grec, grec_nsrcs);
@@ -991,12 +994,13 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br,
nsrcs_offset + sizeof(_nsrcs))
return -EINVAL;
- nsrcs = skb_header_pointer(skb, nsrcs_offset,
- sizeof(_nsrcs), &_nsrcs);
- if (!nsrcs)
+ _nsrcs = skb_header_pointer(skb, nsrcs_offset,
+ sizeof(__nsrcs), &__nsrcs);
+ if (!_nsrcs)
return -EINVAL;
- grec_len = struct_size(grec, grec_src, ntohs(*nsrcs));
+ nsrcs = ntohs(*_nsrcs);
+ grec_len = struct_size(grec, grec_src, nsrcs);
if (!ipv6_mc_may_pull(skb, len + grec_len))
return -EINVAL;
@@ -1021,7 +1025,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br,
src = eth_hdr(skb)->h_source;
if ((grec->grec_type == MLD2_CHANGE_TO_INCLUDE ||
grec->grec_type == MLD2_MODE_IS_INCLUDE) &&
- ntohs(*nsrcs) == 0) {
+ nsrcs == 0) {
br_ip6_multicast_leave_group(br, port, &grec->grec_mca,
vid, src);
} else {
@@ -1275,7 +1279,6 @@ static int br_ip6_multicast_query(struct net_bridge *br,
u16 vid)
{
unsigned int transport_len = ipv6_transport_len(skb);
- const struct ipv6hdr *ip6h = ipv6_hdr(skb);
struct mld_msg *mld;
struct net_bridge_mdb_entry *mp;
struct mld2_query *mld2q;
@@ -1319,7 +1322,7 @@ static int br_ip6_multicast_query(struct net_bridge *br,
if (is_general_query) {
saddr.proto = htons(ETH_P_IPV6);
- saddr.u.ip6 = ip6h->saddr;
+ saddr.u.ip6 = ipv6_hdr(skb)->saddr;
br_multicast_query_received(br, port, &br->ip6_other_query,
&saddr, max_delay);
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 34fa72c72ad8..d3f9592f4ff8 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -47,25 +47,22 @@ static unsigned int brnf_net_id __read_mostly;
struct brnf_net {
bool enabled;
-};
#ifdef CONFIG_SYSCTL
-static struct ctl_table_header *brnf_sysctl_header;
-static int brnf_call_iptables __read_mostly = 1;
-static int brnf_call_ip6tables __read_mostly = 1;
-static int brnf_call_arptables __read_mostly = 1;
-static int brnf_filter_vlan_tagged __read_mostly;
-static int brnf_filter_pppoe_tagged __read_mostly;
-static int brnf_pass_vlan_indev __read_mostly;
-#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
+ struct ctl_table_header *ctl_hdr;
#endif
+ /* default value is 1 */
+ int call_iptables;
+ int call_ip6tables;
+ int call_arptables;
+
+ /* default value is 0 */
+ int filter_vlan_tagged;
+ int filter_pppoe_tagged;
+ int pass_vlan_indev;
+};
+
#define IS_IP(skb) \
(!skb_vlan_tag_present(skb) && skb->protocol == htons(ETH_P_IP))
@@ -85,17 +82,28 @@ static inline __be16 vlan_proto(const struct sk_buff *skb)
return 0;
}
-#define IS_VLAN_IP(skb) \
- (vlan_proto(skb) == htons(ETH_P_IP) && \
- brnf_filter_vlan_tagged)
+static inline bool is_vlan_ip(const struct sk_buff *skb, const struct net *net)
+{
+ struct brnf_net *brnet = net_generic(net, brnf_net_id);
+
+ return vlan_proto(skb) == htons(ETH_P_IP) && brnet->filter_vlan_tagged;
+}
-#define IS_VLAN_IPV6(skb) \
- (vlan_proto(skb) == htons(ETH_P_IPV6) && \
- brnf_filter_vlan_tagged)
+static inline bool is_vlan_ipv6(const struct sk_buff *skb,
+ const struct net *net)
+{
+ struct brnf_net *brnet = net_generic(net, brnf_net_id);
-#define IS_VLAN_ARP(skb) \
- (vlan_proto(skb) == htons(ETH_P_ARP) && \
- brnf_filter_vlan_tagged)
+ return vlan_proto(skb) == htons(ETH_P_IPV6) &&
+ brnet->filter_vlan_tagged;
+}
+
+static inline bool is_vlan_arp(const struct sk_buff *skb, const struct net *net)
+{
+ struct brnf_net *brnet = net_generic(net, brnf_net_id);
+
+ return vlan_proto(skb) == htons(ETH_P_ARP) && brnet->filter_vlan_tagged;
+}
static inline __be16 pppoe_proto(const struct sk_buff *skb)
{
@@ -103,15 +111,23 @@ static inline __be16 pppoe_proto(const struct sk_buff *skb)
sizeof(struct pppoe_hdr)));
}
-#define IS_PPPOE_IP(skb) \
- (skb->protocol == htons(ETH_P_PPP_SES) && \
- pppoe_proto(skb) == htons(PPP_IP) && \
- brnf_filter_pppoe_tagged)
+static inline bool is_pppoe_ip(const struct sk_buff *skb, const struct net *net)
+{
+ struct brnf_net *brnet = net_generic(net, brnf_net_id);
+
+ return skb->protocol == htons(ETH_P_PPP_SES) &&
+ pppoe_proto(skb) == htons(PPP_IP) && brnet->filter_pppoe_tagged;
+}
+
+static inline bool is_pppoe_ipv6(const struct sk_buff *skb,
+ const struct net *net)
+{
+ struct brnf_net *brnet = net_generic(net, brnf_net_id);
-#define IS_PPPOE_IPV6(skb) \
- (skb->protocol == htons(ETH_P_PPP_SES) && \
- pppoe_proto(skb) == htons(PPP_IPV6) && \
- brnf_filter_pppoe_tagged)
+ return skb->protocol == htons(ETH_P_PPP_SES) &&
+ pppoe_proto(skb) == htons(PPP_IPV6) &&
+ brnet->filter_pppoe_tagged;
+}
/* largest possible L2 header, see br_nf_dev_queue_xmit() */
#define NF_BRIDGE_MAX_MAC_HEADER_LENGTH (PPPOE_SES_HLEN + ETH_HLEN)
@@ -408,12 +424,16 @@ bridged_dnat:
return 0;
}
-static struct net_device *brnf_get_logical_dev(struct sk_buff *skb, const struct net_device *dev)
+static struct net_device *brnf_get_logical_dev(struct sk_buff *skb,
+ const struct net_device *dev,
+ const struct net *net)
{
struct net_device *vlan, *br;
+ struct brnf_net *brnet = net_generic(net, brnf_net_id);
br = bridge_parent(dev);
- if (brnf_pass_vlan_indev == 0 || !skb_vlan_tag_present(skb))
+
+ if (brnet->pass_vlan_indev == 0 || !skb_vlan_tag_present(skb))
return br;
vlan = __vlan_find_dev_deep_rcu(br, skb->vlan_proto,
@@ -423,7 +443,7 @@ static struct net_device *brnf_get_logical_dev(struct sk_buff *skb, const struct
}
/* Some common code for IPv4/IPv6 */
-struct net_device *setup_pre_routing(struct sk_buff *skb)
+struct net_device *setup_pre_routing(struct sk_buff *skb, const struct net *net)
{
struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
@@ -434,7 +454,7 @@ struct net_device *setup_pre_routing(struct sk_buff *skb)
nf_bridge->in_prerouting = 1;
nf_bridge->physindev = skb->dev;
- skb->dev = brnf_get_logical_dev(skb, skb->dev);
+ skb->dev = brnf_get_logical_dev(skb, skb->dev, net);
if (skb->protocol == htons(ETH_P_8021Q))
nf_bridge->orig_proto = BRNF_PROTO_8021Q;
@@ -460,6 +480,7 @@ static unsigned int br_nf_pre_routing(void *priv,
struct net_bridge_port *p;
struct net_bridge *br;
__u32 len = nf_bridge_encap_header_len(skb);
+ struct brnf_net *brnet;
if (unlikely(!pskb_may_pull(skb, len)))
return NF_DROP;
@@ -469,8 +490,10 @@ static unsigned int br_nf_pre_routing(void *priv,
return NF_DROP;
br = p->br;
- if (IS_IPV6(skb) || IS_VLAN_IPV6(skb) || IS_PPPOE_IPV6(skb)) {
- if (!brnf_call_ip6tables &&
+ brnet = net_generic(state->net, brnf_net_id);
+ if (IS_IPV6(skb) || is_vlan_ipv6(skb, state->net) ||
+ is_pppoe_ipv6(skb, state->net)) {
+ if (!brnet->call_ip6tables &&
!br_opt_get(br, BROPT_NF_CALL_IP6TABLES))
return NF_ACCEPT;
@@ -478,10 +501,11 @@ static unsigned int br_nf_pre_routing(void *priv,
return br_nf_pre_routing_ipv6(priv, skb, state);
}
- if (!brnf_call_iptables && !br_opt_get(br, BROPT_NF_CALL_IPTABLES))
+ if (!brnet->call_iptables && !br_opt_get(br, BROPT_NF_CALL_IPTABLES))
return NF_ACCEPT;
- if (!IS_IP(skb) && !IS_VLAN_IP(skb) && !IS_PPPOE_IP(skb))
+ if (!IS_IP(skb) && !is_vlan_ip(skb, state->net) &&
+ !is_pppoe_ip(skb, state->net))
return NF_ACCEPT;
nf_bridge_pull_encap_header_rcsum(skb);
@@ -491,7 +515,7 @@ static unsigned int br_nf_pre_routing(void *priv,
if (!nf_bridge_alloc(skb))
return NF_DROP;
- if (!setup_pre_routing(skb))
+ if (!setup_pre_routing(skb, state->net))
return NF_DROP;
nf_bridge = nf_bridge_info_get(skb);
@@ -514,7 +538,7 @@ static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff
struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
struct net_device *in;
- if (!IS_ARP(skb) && !IS_VLAN_ARP(skb)) {
+ if (!IS_ARP(skb) && !is_vlan_arp(skb, net)) {
if (skb->protocol == htons(ETH_P_IP))
nf_bridge->frag_max_size = IPCB(skb)->frag_max_size;
@@ -569,9 +593,11 @@ static unsigned int br_nf_forward_ip(void *priv,
if (!parent)
return NF_DROP;
- if (IS_IP(skb) || IS_VLAN_IP(skb) || IS_PPPOE_IP(skb))
+ if (IS_IP(skb) || is_vlan_ip(skb, state->net) ||
+ is_pppoe_ip(skb, state->net))
pf = NFPROTO_IPV4;
- else if (IS_IPV6(skb) || IS_VLAN_IPV6(skb) || IS_PPPOE_IPV6(skb))
+ else if (IS_IPV6(skb) || is_vlan_ipv6(skb, state->net) ||
+ is_pppoe_ipv6(skb, state->net))
pf = NFPROTO_IPV6;
else
return NF_ACCEPT;
@@ -602,7 +628,7 @@ static unsigned int br_nf_forward_ip(void *priv,
skb->protocol = htons(ETH_P_IPV6);
NF_HOOK(pf, NF_INET_FORWARD, state->net, NULL, skb,
- brnf_get_logical_dev(skb, state->in),
+ brnf_get_logical_dev(skb, state->in, state->net),
parent, br_nf_forward_finish);
return NF_STOLEN;
@@ -615,23 +641,25 @@ static unsigned int br_nf_forward_arp(void *priv,
struct net_bridge_port *p;
struct net_bridge *br;
struct net_device **d = (struct net_device **)(skb->cb);
+ struct brnf_net *brnet;
p = br_port_get_rcu(state->out);
if (p == NULL)
return NF_ACCEPT;
br = p->br;
- if (!brnf_call_arptables && !br_opt_get(br, BROPT_NF_CALL_ARPTABLES))
+ brnet = net_generic(state->net, brnf_net_id);
+ if (!brnet->call_arptables && !br_opt_get(br, BROPT_NF_CALL_ARPTABLES))
return NF_ACCEPT;
if (!IS_ARP(skb)) {
- if (!IS_VLAN_ARP(skb))
+ if (!is_vlan_arp(skb, state->net))
return NF_ACCEPT;
nf_bridge_pull_encap_header(skb);
}
if (arp_hdr(skb)->ar_pln != 4) {
- if (IS_VLAN_ARP(skb))
+ if (is_vlan_arp(skb, state->net))
nf_bridge_push_encap_header(skb);
return NF_ACCEPT;
}
@@ -791,9 +819,11 @@ static unsigned int br_nf_post_routing(void *priv,
if (!realoutdev)
return NF_DROP;
- if (IS_IP(skb) || IS_VLAN_IP(skb) || IS_PPPOE_IP(skb))
+ if (IS_IP(skb) || is_vlan_ip(skb, state->net) ||
+ is_pppoe_ip(skb, state->net))
pf = NFPROTO_IPV4;
- else if (IS_IPV6(skb) || IS_VLAN_IPV6(skb) || IS_PPPOE_IPV6(skb))
+ else if (IS_IPV6(skb) || is_vlan_ipv6(skb, state->net) ||
+ is_pppoe_ipv6(skb, state->net))
pf = NFPROTO_IPV6;
else
return NF_ACCEPT;
@@ -946,23 +976,6 @@ static int brnf_device_event(struct notifier_block *unused, unsigned long event,
return NOTIFY_OK;
}
-static void __net_exit brnf_exit_net(struct net *net)
-{
- struct brnf_net *brnet = net_generic(net, brnf_net_id);
-
- if (!brnet->enabled)
- return;
-
- nf_unregister_net_hooks(net, br_nf_ops, ARRAY_SIZE(br_nf_ops));
- brnet->enabled = false;
-}
-
-static struct pernet_operations brnf_net_ops __read_mostly = {
- .exit = brnf_exit_net,
- .id = &brnf_net_id,
- .size = sizeof(struct brnf_net),
-};
-
static struct notifier_block brnf_notifier __read_mostly = {
.notifier_call = brnf_device_event,
};
@@ -1021,49 +1034,124 @@ int brnf_sysctl_call_tables(struct ctl_table *ctl, int write,
static struct ctl_table brnf_table[] = {
{
.procname = "bridge-nf-call-arptables",
- .data = &brnf_call_arptables,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = brnf_sysctl_call_tables,
},
{
.procname = "bridge-nf-call-iptables",
- .data = &brnf_call_iptables,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = brnf_sysctl_call_tables,
},
{
.procname = "bridge-nf-call-ip6tables",
- .data = &brnf_call_ip6tables,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = brnf_sysctl_call_tables,
},
{
.procname = "bridge-nf-filter-vlan-tagged",
- .data = &brnf_filter_vlan_tagged,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = brnf_sysctl_call_tables,
},
{
.procname = "bridge-nf-filter-pppoe-tagged",
- .data = &brnf_filter_pppoe_tagged,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = brnf_sysctl_call_tables,
},
{
.procname = "bridge-nf-pass-vlan-input-dev",
- .data = &brnf_pass_vlan_indev,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = brnf_sysctl_call_tables,
},
{ }
};
+
+static inline void br_netfilter_sysctl_default(struct brnf_net *brnf)
+{
+ brnf->call_iptables = 1;
+ brnf->call_ip6tables = 1;
+ brnf->call_arptables = 1;
+ brnf->filter_vlan_tagged = 0;
+ brnf->filter_pppoe_tagged = 0;
+ brnf->pass_vlan_indev = 0;
+}
+
+static int br_netfilter_sysctl_init_net(struct net *net)
+{
+ struct ctl_table *table = brnf_table;
+ struct brnf_net *brnet;
+
+ if (!net_eq(net, &init_net)) {
+ table = kmemdup(table, sizeof(brnf_table), GFP_KERNEL);
+ if (!table)
+ return -ENOMEM;
+ }
+
+ brnet = net_generic(net, brnf_net_id);
+ table[0].data = &brnet->call_arptables;
+ table[1].data = &brnet->call_iptables;
+ table[2].data = &brnet->call_ip6tables;
+ table[3].data = &brnet->filter_vlan_tagged;
+ table[4].data = &brnet->filter_pppoe_tagged;
+ table[5].data = &brnet->pass_vlan_indev;
+
+ br_netfilter_sysctl_default(brnet);
+
+ brnet->ctl_hdr = register_net_sysctl(net, "net/bridge", table);
+ if (!brnet->ctl_hdr) {
+ if (!net_eq(net, &init_net))
+ kfree(table);
+
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+static void br_netfilter_sysctl_exit_net(struct net *net,
+ struct brnf_net *brnet)
+{
+ struct ctl_table *table = brnet->ctl_hdr->ctl_table_arg;
+
+ unregister_net_sysctl_table(brnet->ctl_hdr);
+ if (!net_eq(net, &init_net))
+ kfree(table);
+}
+
+static int __net_init brnf_init_net(struct net *net)
+{
+ return br_netfilter_sysctl_init_net(net);
+}
+#endif
+
+static void __net_exit brnf_exit_net(struct net *net)
+{
+ struct brnf_net *brnet;
+
+ brnet = net_generic(net, brnf_net_id);
+ if (brnet->enabled) {
+ nf_unregister_net_hooks(net, br_nf_ops, ARRAY_SIZE(br_nf_ops));
+ brnet->enabled = false;
+ }
+
+#ifdef CONFIG_SYSCTL
+ br_netfilter_sysctl_exit_net(net, brnet);
#endif
+}
+
+static struct pernet_operations brnf_net_ops __read_mostly = {
+#ifdef CONFIG_SYSCTL
+ .init = brnf_init_net,
+#endif
+ .exit = brnf_exit_net,
+ .id = &brnf_net_id,
+ .size = sizeof(struct brnf_net),
+};
static int __init br_netfilter_init(void)
{
@@ -1079,16 +1167,6 @@ static int __init br_netfilter_init(void)
return ret;
}
-#ifdef CONFIG_SYSCTL
- 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");
- unregister_netdevice_notifier(&brnf_notifier);
- unregister_pernet_subsys(&brnf_net_ops);
- return -ENOMEM;
- }
-#endif
RCU_INIT_POINTER(nf_br_ops, &br_ops);
printk(KERN_NOTICE "Bridge firewalling registered\n");
return 0;
@@ -1099,9 +1177,6 @@ static void __exit br_netfilter_fini(void)
RCU_INIT_POINTER(nf_br_ops, NULL);
unregister_netdevice_notifier(&brnf_notifier);
unregister_pernet_subsys(&brnf_net_ops);
-#ifdef CONFIG_SYSCTL
- unregister_net_sysctl_table(brnf_sysctl_header);
-#endif
}
module_init(br_netfilter_init);
diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c
index 0e63e5dc5ac4..e4e0c836c3f5 100644
--- a/net/bridge/br_netfilter_ipv6.c
+++ b/net/bridge/br_netfilter_ipv6.c
@@ -224,7 +224,7 @@ unsigned int br_nf_pre_routing_ipv6(void *priv,
nf_bridge = nf_bridge_alloc(skb);
if (!nf_bridge)
return NF_DROP;
- if (!setup_pre_routing(skb))
+ if (!setup_pre_routing(skb, state->net))
return NF_DROP;
nf_bridge = nf_bridge_info_get(skb);
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 159a0e2cb0f6..e8cf03b43b7d 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -421,6 +421,7 @@ struct net_bridge {
struct br_input_skb_cb {
struct net_device *brdev;
+ u16 frag_max_size;
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
u8 igmp;
u8 mrouters_only:1;
diff --git a/net/bridge/br_stp_bpdu.c b/net/bridge/br_stp_bpdu.c
index 68a6922b4141..7796dd9d42d7 100644
--- a/net/bridge/br_stp_bpdu.c
+++ b/net/bridge/br_stp_bpdu.c
@@ -143,7 +143,6 @@ void br_send_tcn_bpdu(struct net_bridge_port *p)
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;
struct net_bridge *br;
const unsigned char *buf;
@@ -172,7 +171,7 @@ void br_stp_rcv(const struct stp_proto *proto, struct sk_buff *skb,
if (p->state == BR_STATE_DISABLED)
goto out;
- if (!ether_addr_equal(dest, br->group_addr))
+ if (!ether_addr_equal(eth_hdr(skb)->h_dest, br->group_addr))
goto out;
if (p->flags & BR_BPDU_GUARD) {
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index f47f526b4f19..021cc9f66804 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -797,6 +797,16 @@ bool br_vlan_enabled(const struct net_device *dev)
}
EXPORT_SYMBOL_GPL(br_vlan_enabled);
+int br_vlan_get_proto(const struct net_device *dev, u16 *p_proto)
+{
+ struct net_bridge *br = netdev_priv(dev);
+
+ *p_proto = ntohs(br->vlan_proto);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(br_vlan_get_proto);
+
int __br_vlan_set_proto(struct net_bridge *br, __be16 proto)
{
int err = 0;
@@ -1227,13 +1237,11 @@ void br_vlan_get_stats(const struct net_bridge_vlan *v,
}
}
-int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid)
+static int __br_vlan_get_pvid(const struct net_device *dev,
+ struct net_bridge_port *p, u16 *p_pvid)
{
struct net_bridge_vlan_group *vg;
- struct net_bridge_port *p;
- ASSERT_RTNL();
- p = br_port_get_check_rtnl(dev);
if (p)
vg = nbp_vlan_group(p);
else if (netif_is_bridge_master(dev))
@@ -1244,8 +1252,21 @@ int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid)
*p_pvid = br_get_pvid(vg);
return 0;
}
+
+int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid)
+{
+ ASSERT_RTNL();
+
+ return __br_vlan_get_pvid(dev, br_port_get_check_rtnl(dev), p_pvid);
+}
EXPORT_SYMBOL_GPL(br_vlan_get_pvid);
+int br_vlan_get_pvid_rcu(const struct net_device *dev, u16 *p_pvid)
+{
+ return __br_vlan_get_pvid(dev, br_port_get_check_rcu(dev), p_pvid);
+}
+EXPORT_SYMBOL_GPL(br_vlan_get_pvid_rcu);
+
int br_vlan_get_info(const struct net_device *dev, u16 vid,
struct bridge_vlan_info *p_vinfo)
{
diff --git a/net/bridge/netfilter/Kconfig b/net/bridge/netfilter/Kconfig
index 36a98d36d339..154fa558bb90 100644
--- a/net/bridge/netfilter/Kconfig
+++ b/net/bridge/netfilter/Kconfig
@@ -9,6 +9,12 @@ menuconfig NF_TABLES_BRIDGE
bool "Ethernet Bridge nf_tables support"
if NF_TABLES_BRIDGE
+
+config NFT_BRIDGE_META
+ tristate "Netfilter nf_table bridge meta support"
+ help
+ Add support for bridge dedicated meta key.
+
config NFT_BRIDGE_REJECT
tristate "Netfilter nf_tables bridge reject support"
depends on NFT_REJECT && NFT_REJECT_IPV4 && NFT_REJECT_IPV6
@@ -19,6 +25,20 @@ config NF_LOG_BRIDGE
tristate "Bridge packet logging"
select NF_LOG_COMMON
+config NF_CONNTRACK_BRIDGE
+ tristate "IPv4/IPV6 bridge connection tracking support"
+ depends on NF_CONNTRACK
+ default n
+ help
+ Connection tracking keeps a record of what packets have passed
+ through your machine, in order to figure out how they are related
+ into connections. This is used to enhance packet filtering via
+ stateful policies. Enable this if you want native tracking from
+ the bridge. This provides a replacement for the `br_netfilter'
+ infrastructure.
+
+ To compile it as a module, choose M here. If unsure, say N.
+
endif # NF_TABLES_BRIDGE
menuconfig BRIDGE_NF_EBTABLES
diff --git a/net/bridge/netfilter/Makefile b/net/bridge/netfilter/Makefile
index 9b868861f21a..8e2c5759d964 100644
--- a/net/bridge/netfilter/Makefile
+++ b/net/bridge/netfilter/Makefile
@@ -3,8 +3,12 @@
# Makefile for the netfilter modules for Link Layer filtering on a bridge.
#
+obj-$(CONFIG_NFT_BRIDGE_META) += nft_meta_bridge.o
obj-$(CONFIG_NFT_BRIDGE_REJECT) += nft_reject_bridge.o
+# connection tracking
+obj-$(CONFIG_NF_CONNTRACK_BRIDGE) += nf_conntrack_bridge.o
+
# packet logging
obj-$(CONFIG_NF_LOG_BRIDGE) += nf_log_bridge.o
diff --git a/net/bridge/netfilter/ebt_dnat.c b/net/bridge/netfilter/ebt_dnat.c
index eeae23a73c6a..ed91ea31978a 100644
--- a/net/bridge/netfilter/ebt_dnat.c
+++ b/net/bridge/netfilter/ebt_dnat.c
@@ -22,7 +22,7 @@ ebt_dnat_tg(struct sk_buff *skb, const struct xt_action_param *par)
const struct ebt_nat_info *info = par->targinfo;
struct net_device *dev;
- if (!skb_make_writable(skb, 0))
+ if (skb_ensure_writable(skb, ETH_ALEN))
return EBT_DROP;
ether_addr_copy(eth_hdr(skb)->h_dest, info->mac);
diff --git a/net/bridge/netfilter/ebt_redirect.c b/net/bridge/netfilter/ebt_redirect.c
index 53ef08e6765f..0cad62a4052b 100644
--- a/net/bridge/netfilter/ebt_redirect.c
+++ b/net/bridge/netfilter/ebt_redirect.c
@@ -21,7 +21,7 @@ ebt_redirect_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct ebt_redirect_info *info = par->targinfo;
- if (!skb_make_writable(skb, 0))
+ if (skb_ensure_writable(skb, ETH_ALEN))
return EBT_DROP;
if (xt_hooknum(par) != NF_BR_BROUTING)
diff --git a/net/bridge/netfilter/ebt_snat.c b/net/bridge/netfilter/ebt_snat.c
index 700d338d5ddb..27443bf229a3 100644
--- a/net/bridge/netfilter/ebt_snat.c
+++ b/net/bridge/netfilter/ebt_snat.c
@@ -22,7 +22,7 @@ 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))
+ if (skb_ensure_writable(skb, ETH_ALEN * 2))
return EBT_DROP;
ether_addr_copy(eth_hdr(skb)->h_source, info->mac);
diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c
new file mode 100644
index 000000000000..4f5444d2a526
--- /dev/null
+++ b/net/bridge/netfilter/nf_conntrack_bridge.c
@@ -0,0 +1,435 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/types.h>
+#include <linux/ip.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv6.h>
+#include <linux/netfilter_bridge.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/icmp.h>
+#include <linux/sysctl.h>
+#include <net/route.h>
+#include <net/ip.h>
+
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_helper.h>
+#include <net/netfilter/nf_conntrack_bridge.h>
+
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
+#include <net/netfilter/nf_tables.h>
+
+#include "../br_private.h"
+
+/* Best effort variant of ip_do_fragment which preserves geometry, unless skbuff
+ * has been linearized or cloned.
+ */
+static int nf_br_ip_fragment(struct net *net, struct sock *sk,
+ struct sk_buff *skb,
+ struct nf_ct_bridge_frag_data *data,
+ int (*output)(struct net *, struct sock *sk,
+ const struct nf_ct_bridge_frag_data *data,
+ struct sk_buff *))
+{
+ int frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size;
+ unsigned int hlen, ll_rs, mtu;
+ struct ip_frag_state state;
+ struct iphdr *iph;
+ int err;
+
+ /* for offloaded checksums cleanup checksum before fragmentation */
+ if (skb->ip_summed == CHECKSUM_PARTIAL &&
+ (err = skb_checksum_help(skb)))
+ goto blackhole;
+
+ iph = ip_hdr(skb);
+
+ /*
+ * Setup starting values
+ */
+
+ hlen = iph->ihl * 4;
+ frag_max_size -= hlen;
+ ll_rs = LL_RESERVED_SPACE(skb->dev);
+ mtu = skb->dev->mtu;
+
+ if (skb_has_frag_list(skb)) {
+ unsigned int first_len = skb_pagelen(skb);
+ struct ip_fraglist_iter iter;
+ struct sk_buff *frag;
+
+ if (first_len - hlen > mtu ||
+ skb_headroom(skb) < ll_rs)
+ goto blackhole;
+
+ if (skb_cloned(skb))
+ goto slow_path;
+
+ skb_walk_frags(skb, frag) {
+ if (frag->len > mtu ||
+ skb_headroom(frag) < hlen + ll_rs)
+ goto blackhole;
+
+ if (skb_shared(frag))
+ goto slow_path;
+ }
+
+ ip_fraglist_init(skb, iph, hlen, &iter);
+
+ for (;;) {
+ if (iter.frag)
+ ip_fraglist_prepare(skb, &iter);
+
+ err = output(net, sk, data, skb);
+ if (err || !iter.frag)
+ break;
+
+ skb = ip_fraglist_next(&iter);
+ }
+ return err;
+ }
+slow_path:
+ /* This is a linearized skbuff, the original geometry is lost for us.
+ * This may also be a clone skbuff, we could preserve the geometry for
+ * the copies but probably not worth the effort.
+ */
+ ip_frag_init(skb, hlen, ll_rs, frag_max_size, &state);
+
+ while (state.left > 0) {
+ struct sk_buff *skb2;
+
+ skb2 = ip_frag_next(skb, &state);
+ if (IS_ERR(skb2)) {
+ err = PTR_ERR(skb2);
+ goto blackhole;
+ }
+
+ err = output(net, sk, data, skb2);
+ if (err)
+ goto blackhole;
+ }
+ consume_skb(skb);
+ return err;
+
+blackhole:
+ kfree_skb(skb);
+ return 0;
+}
+
+/* ip_defrag() expects IPCB() in place. */
+static void br_skb_cb_save(struct sk_buff *skb, struct br_input_skb_cb *cb,
+ size_t inet_skb_parm_size)
+{
+ memcpy(cb, skb->cb, sizeof(*cb));
+ memset(skb->cb, 0, inet_skb_parm_size);
+}
+
+static void br_skb_cb_restore(struct sk_buff *skb,
+ const struct br_input_skb_cb *cb,
+ u16 fragsz)
+{
+ memcpy(skb->cb, cb, sizeof(*cb));
+ BR_INPUT_SKB_CB(skb)->frag_max_size = fragsz;
+}
+
+static unsigned int nf_ct_br_defrag4(struct sk_buff *skb,
+ const struct nf_hook_state *state)
+{
+ u16 zone_id = NF_CT_DEFAULT_ZONE_ID;
+ enum ip_conntrack_info ctinfo;
+ struct br_input_skb_cb cb;
+ const struct nf_conn *ct;
+ int err;
+
+ if (!ip_is_fragment(ip_hdr(skb)))
+ return NF_ACCEPT;
+
+ ct = nf_ct_get(skb, &ctinfo);
+ if (ct)
+ zone_id = nf_ct_zone_id(nf_ct_zone(ct), CTINFO2DIR(ctinfo));
+
+ br_skb_cb_save(skb, &cb, sizeof(struct inet_skb_parm));
+ local_bh_disable();
+ err = ip_defrag(state->net, skb,
+ IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone_id);
+ local_bh_enable();
+ if (!err) {
+ br_skb_cb_restore(skb, &cb, IPCB(skb)->frag_max_size);
+ skb->ignore_df = 1;
+ return NF_ACCEPT;
+ }
+
+ return NF_STOLEN;
+}
+
+static unsigned int nf_ct_br_defrag6(struct sk_buff *skb,
+ const struct nf_hook_state *state)
+{
+ u16 zone_id = NF_CT_DEFAULT_ZONE_ID;
+ enum ip_conntrack_info ctinfo;
+ struct br_input_skb_cb cb;
+ const struct nf_conn *ct;
+ int err;
+
+ ct = nf_ct_get(skb, &ctinfo);
+ if (ct)
+ zone_id = nf_ct_zone_id(nf_ct_zone(ct), CTINFO2DIR(ctinfo));
+
+ br_skb_cb_save(skb, &cb, sizeof(struct inet6_skb_parm));
+
+ err = nf_ipv6_br_defrag(state->net, skb,
+ IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone_id);
+ /* queued */
+ if (err == -EINPROGRESS)
+ return NF_STOLEN;
+
+ br_skb_cb_restore(skb, &cb, IP6CB(skb)->frag_max_size);
+ return err == 0 ? NF_ACCEPT : NF_DROP;
+}
+
+static int nf_ct_br_ip_check(const struct sk_buff *skb)
+{
+ const struct iphdr *iph;
+ int nhoff, len;
+
+ nhoff = skb_network_offset(skb);
+ iph = ip_hdr(skb);
+ if (iph->ihl < 5 ||
+ iph->version != 4)
+ return -1;
+
+ len = ntohs(iph->tot_len);
+ if (skb->len < nhoff + len ||
+ len < (iph->ihl * 4))
+ return -1;
+
+ return 0;
+}
+
+static int nf_ct_br_ipv6_check(const struct sk_buff *skb)
+{
+ const struct ipv6hdr *hdr;
+ int nhoff, len;
+
+ nhoff = skb_network_offset(skb);
+ hdr = ipv6_hdr(skb);
+ if (hdr->version != 6)
+ return -1;
+
+ len = ntohs(hdr->payload_len) + sizeof(struct ipv6hdr) + nhoff;
+ if (skb->len < len)
+ return -1;
+
+ return 0;
+}
+
+static unsigned int nf_ct_bridge_pre(void *priv, struct sk_buff *skb,
+ const struct nf_hook_state *state)
+{
+ struct nf_hook_state bridge_state = *state;
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn *ct;
+ u32 len;
+ int ret;
+
+ ct = nf_ct_get(skb, &ctinfo);
+ if ((ct && !nf_ct_is_template(ct)) ||
+ ctinfo == IP_CT_UNTRACKED)
+ return NF_ACCEPT;
+
+ switch (skb->protocol) {
+ case htons(ETH_P_IP):
+ if (!pskb_may_pull(skb, sizeof(struct iphdr)))
+ return NF_ACCEPT;
+
+ len = ntohs(ip_hdr(skb)->tot_len);
+ if (pskb_trim_rcsum(skb, len))
+ return NF_ACCEPT;
+
+ if (nf_ct_br_ip_check(skb))
+ return NF_ACCEPT;
+
+ bridge_state.pf = NFPROTO_IPV4;
+ ret = nf_ct_br_defrag4(skb, &bridge_state);
+ break;
+ case htons(ETH_P_IPV6):
+ if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
+ return NF_ACCEPT;
+
+ len = sizeof(struct ipv6hdr) + ntohs(ipv6_hdr(skb)->payload_len);
+ if (pskb_trim_rcsum(skb, len))
+ return NF_ACCEPT;
+
+ if (nf_ct_br_ipv6_check(skb))
+ return NF_ACCEPT;
+
+ bridge_state.pf = NFPROTO_IPV6;
+ ret = nf_ct_br_defrag6(skb, &bridge_state);
+ break;
+ default:
+ nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
+ return NF_ACCEPT;
+ }
+
+ if (ret != NF_ACCEPT)
+ return ret;
+
+ return nf_conntrack_in(skb, &bridge_state);
+}
+
+static void nf_ct_bridge_frag_save(struct sk_buff *skb,
+ struct nf_ct_bridge_frag_data *data)
+{
+ if (skb_vlan_tag_present(skb)) {
+ data->vlan_present = true;
+ data->vlan_tci = skb->vlan_tci;
+ data->vlan_proto = skb->vlan_proto;
+ } else {
+ data->vlan_present = false;
+ }
+ skb_copy_from_linear_data_offset(skb, -ETH_HLEN, data->mac, ETH_HLEN);
+}
+
+static unsigned int
+nf_ct_bridge_refrag(struct sk_buff *skb, const struct nf_hook_state *state,
+ int (*output)(struct net *, struct sock *sk,
+ const struct nf_ct_bridge_frag_data *data,
+ struct sk_buff *))
+{
+ struct nf_ct_bridge_frag_data data;
+
+ if (!BR_INPUT_SKB_CB(skb)->frag_max_size)
+ return NF_ACCEPT;
+
+ nf_ct_bridge_frag_save(skb, &data);
+ switch (skb->protocol) {
+ case htons(ETH_P_IP):
+ nf_br_ip_fragment(state->net, state->sk, skb, &data, output);
+ break;
+ case htons(ETH_P_IPV6):
+ nf_br_ip6_fragment(state->net, state->sk, skb, &data, output);
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ return NF_DROP;
+ }
+
+ return NF_STOLEN;
+}
+
+/* Actually only slow path refragmentation needs this. */
+static int nf_ct_bridge_frag_restore(struct sk_buff *skb,
+ const struct nf_ct_bridge_frag_data *data)
+{
+ int err;
+
+ err = skb_cow_head(skb, ETH_HLEN);
+ if (err) {
+ kfree_skb(skb);
+ return -ENOMEM;
+ }
+ if (data->vlan_present)
+ __vlan_hwaccel_put_tag(skb, data->vlan_proto, data->vlan_tci);
+ else if (skb_vlan_tag_present(skb))
+ __vlan_hwaccel_clear_tag(skb);
+
+ skb_copy_to_linear_data_offset(skb, -ETH_HLEN, data->mac, ETH_HLEN);
+ skb_reset_mac_header(skb);
+
+ return 0;
+}
+
+static int nf_ct_bridge_refrag_post(struct net *net, struct sock *sk,
+ const struct nf_ct_bridge_frag_data *data,
+ struct sk_buff *skb)
+{
+ int err;
+
+ err = nf_ct_bridge_frag_restore(skb, data);
+ if (err < 0)
+ return err;
+
+ return br_dev_queue_push_xmit(net, sk, skb);
+}
+
+static unsigned int nf_ct_bridge_confirm(struct sk_buff *skb)
+{
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn *ct;
+ int protoff;
+
+ ct = nf_ct_get(skb, &ctinfo);
+ if (!ct || ctinfo == IP_CT_RELATED_REPLY)
+ return nf_conntrack_confirm(skb);
+
+ switch (skb->protocol) {
+ case htons(ETH_P_IP):
+ protoff = skb_network_offset(skb) + ip_hdrlen(skb);
+ break;
+ case htons(ETH_P_IPV6): {
+ unsigned char pnum = ipv6_hdr(skb)->nexthdr;
+ __be16 frag_off;
+
+ protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum,
+ &frag_off);
+ if (protoff < 0 || (frag_off & htons(~0x7)) != 0)
+ return nf_conntrack_confirm(skb);
+ }
+ break;
+ default:
+ return NF_ACCEPT;
+ }
+ return nf_confirm(skb, protoff, ct, ctinfo);
+}
+
+static unsigned int nf_ct_bridge_post(void *priv, struct sk_buff *skb,
+ const struct nf_hook_state *state)
+{
+ int ret;
+
+ ret = nf_ct_bridge_confirm(skb);
+ if (ret != NF_ACCEPT)
+ return ret;
+
+ return nf_ct_bridge_refrag(skb, state, nf_ct_bridge_refrag_post);
+}
+
+static struct nf_hook_ops nf_ct_bridge_hook_ops[] __read_mostly = {
+ {
+ .hook = nf_ct_bridge_pre,
+ .pf = NFPROTO_BRIDGE,
+ .hooknum = NF_BR_PRE_ROUTING,
+ .priority = NF_IP_PRI_CONNTRACK,
+ },
+ {
+ .hook = nf_ct_bridge_post,
+ .pf = NFPROTO_BRIDGE,
+ .hooknum = NF_BR_POST_ROUTING,
+ .priority = NF_IP_PRI_CONNTRACK_CONFIRM,
+ },
+};
+
+static struct nf_ct_bridge_info bridge_info = {
+ .ops = nf_ct_bridge_hook_ops,
+ .ops_size = ARRAY_SIZE(nf_ct_bridge_hook_ops),
+ .me = THIS_MODULE,
+};
+
+static int __init nf_conntrack_l3proto_bridge_init(void)
+{
+ nf_ct_bridge_register(&bridge_info);
+
+ return 0;
+}
+
+static void __exit nf_conntrack_l3proto_bridge_fini(void)
+{
+ nf_ct_bridge_unregister(&bridge_info);
+}
+
+module_init(nf_conntrack_l3proto_bridge_init);
+module_exit(nf_conntrack_l3proto_bridge_fini);
+
+MODULE_ALIAS("nf_conntrack-" __stringify(AF_BRIDGE));
+MODULE_LICENSE("GPL");
diff --git a/net/bridge/netfilter/nft_meta_bridge.c b/net/bridge/netfilter/nft_meta_bridge.c
new file mode 100644
index 000000000000..bed66f536b34
--- /dev/null
+++ b/net/bridge/netfilter/nft_meta_bridge.c
@@ -0,0 +1,163 @@
+// SPDX-License-Identifier: GPL-2.0
+#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 <linux/if_bridge.h>
+
+static const struct net_device *
+nft_meta_get_bridge(const struct net_device *dev)
+{
+ if (dev && netif_is_bridge_port(dev))
+ return netdev_master_upper_dev_get_rcu((struct net_device *)dev);
+
+ return NULL;
+}
+
+static void nft_meta_bridge_get_eval(const struct nft_expr *expr,
+ struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
+{
+ const struct nft_meta *priv = nft_expr_priv(expr);
+ const struct net_device *in = nft_in(pkt), *out = nft_out(pkt);
+ u32 *dest = &regs->data[priv->dreg];
+ const struct net_device *br_dev;
+
+ switch (priv->key) {
+ case NFT_META_BRI_IIFNAME:
+ br_dev = nft_meta_get_bridge(in);
+ if (!br_dev)
+ goto err;
+ break;
+ case NFT_META_BRI_OIFNAME:
+ br_dev = nft_meta_get_bridge(out);
+ if (!br_dev)
+ goto err;
+ break;
+ case NFT_META_BRI_IIFPVID: {
+ u16 p_pvid;
+
+ br_dev = nft_meta_get_bridge(in);
+ if (!br_dev || !br_vlan_enabled(br_dev))
+ goto err;
+
+ br_vlan_get_pvid_rcu(in, &p_pvid);
+ nft_reg_store16(dest, p_pvid);
+ return;
+ }
+ case NFT_META_BRI_IIFVPROTO: {
+ u16 p_proto;
+
+ br_dev = nft_meta_get_bridge(in);
+ if (!br_dev || !br_vlan_enabled(br_dev))
+ goto err;
+
+ br_vlan_get_proto(br_dev, &p_proto);
+ nft_reg_store16(dest, p_proto);
+ return;
+ }
+ default:
+ goto out;
+ }
+
+ strncpy((char *)dest, br_dev->name, IFNAMSIZ);
+ return;
+out:
+ return nft_meta_get_eval(expr, regs, pkt);
+err:
+ regs->verdict.code = 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);
+ unsigned int len;
+
+ priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY]));
+ switch (priv->key) {
+ case NFT_META_BRI_IIFNAME:
+ case NFT_META_BRI_OIFNAME:
+ len = IFNAMSIZ;
+ break;
+ case NFT_META_BRI_IIFPVID:
+ case NFT_META_BRI_IIFVPROTO:
+ len = sizeof(u16);
+ break;
+ default:
+ return nft_meta_get_init(ctx, expr, tb);
+ }
+
+ priv->dreg = nft_parse_register(tb[NFTA_META_DREG]);
+ return nft_validate_register_store(ctx, priv->dreg, NULL,
+ NFT_DATA_VALUE, len);
+}
+
+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,
+ .destroy = nft_meta_set_destroy,
+ .dump = nft_meta_set_dump,
+ .validate = nft_meta_set_validate,
+};
+
+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("wenxu <wenxu@ucloud.cn>");
+MODULE_ALIAS_NFT_AF_EXPR(AF_BRIDGE, "meta");