summaryrefslogtreecommitdiffstats
path: root/net/bridge
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2016-10-05 10:11:24 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2016-10-05 10:11:24 -0700
commit687ee0ad4e897e29f4b41f7a20c866d74c5e0660 (patch)
treeb31a2af35c24a54823674cdd126993b80daeac67 /net/bridge
parent3ddf40e8c31964b744ff10abb48c8e36a83ec6e7 (diff)
parent03a1eabc3f54469abd4f1784182851b2e29630cc (diff)
downloadlinux-687ee0ad4e897e29f4b41f7a20c866d74c5e0660.tar.gz
linux-687ee0ad4e897e29f4b41f7a20c866d74c5e0660.tar.bz2
linux-687ee0ad4e897e29f4b41f7a20c866d74c5e0660.zip
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller: 1) BBR TCP congestion control, from Neal Cardwell, Yuchung Cheng and co. at Google. https://lwn.net/Articles/701165/ 2) Do TCP Small Queues for retransmits, from Eric Dumazet. 3) Support collect_md mode for all IPV4 and IPV6 tunnels, from Alexei Starovoitov. 4) Allow cls_flower to classify packets in ip tunnels, from Amir Vadai. 5) Support DSA tagging in older mv88e6xxx switches, from Andrew Lunn. 6) Support GMAC protocol in iwlwifi mwm, from Ayala Beker. 7) Support ndo_poll_controller in mlx5, from Calvin Owens. 8) Move VRF processing to an output hook and allow l3mdev to be loopback, from David Ahern. 9) Support SOCK_DESTROY for UDP sockets. Also from David Ahern. 10) Congestion control in RXRPC, from David Howells. 11) Support geneve RX offload in ixgbe, from Emil Tantilov. 12) When hitting pressure for new incoming TCP data SKBs, perform a partial rathern than a full purge of the OFO queue (which could be huge). From Eric Dumazet. 13) Convert XFRM state and policy lookups to RCU, from Florian Westphal. 14) Support RX network flow classification to igb, from Gangfeng Huang. 15) Hardware offloading of eBPF in nfp driver, from Jakub Kicinski. 16) New skbmod packet action, from Jamal Hadi Salim. 17) Remove some inefficiencies in snmp proc output, from Jia He. 18) Add FIB notifications to properly propagate route changes to hardware which is doing forwarding offloading. From Jiri Pirko. 19) New dsa driver for qca8xxx chips, from John Crispin. 20) Implement RFC7559 ipv6 router solicitation backoff, from Maciej Żenczykowski. 21) Add L3 mode to ipvlan, from Mahesh Bandewar. 22) Support 802.1ad in mlx4, from Moshe Shemesh. 23) Support hardware LRO in mediatek driver, from Nelson Chang. 24) Add TC offloading to mlx5, from Or Gerlitz. 25) Convert various drivers to ethtool ksettings interfaces, from Philippe Reynes. 26) TX max rate limiting for cxgb4, from Rahul Lakkireddy. 27) NAPI support for ath10k, from Rajkumar Manoharan. 28) Support XDP in mlx5, from Rana Shahout and Saeed Mahameed. 29) UDP replicast support in TIPC, from Richard Alpe. 30) Per-queue statistics for qed driver, from Sudarsana Reddy Kalluru. 31) Support BQL in thunderx driver, from Sunil Goutham. 32) TSO support in alx driver, from Tobias Regnery. 33) Add stream parser engine and use it in kcm. 34) Support async DHCP replies in ipconfig module, from Uwe Kleine-König. 35) DSA port fast aging for mv88e6xxx driver, from Vivien Didelot. * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1715 commits) mlxsw: switchx2: Fix misuse of hard_header_len mlxsw: spectrum: Fix misuse of hard_header_len net/faraday: Stop NCSI device on shutdown net/ncsi: Introduce ncsi_stop_dev() net/ncsi: Rework the channel monitoring net/ncsi: Allow to extend NCSI request properties net/ncsi: Rework request index allocation net/ncsi: Don't probe on the reserved channel ID (0x1f) net/ncsi: Introduce NCSI_RESERVED_CHANNEL net/ncsi: Avoid unused-value build warning from ia64-linux-gcc net: Add netdev all_adj_list refcnt propagation to fix panic net: phy: Add Edge-rate driver for Microsemi PHYs. vmxnet3: Wake queue from reset work i40e: avoid NULL pointer dereference and recursive errors on early PCI error qed: Add RoCE ll2 & GSI support qed: Add support for memory registeration verbs qed: Add support for QP verbs qed: PD,PKEY and CQ verb support qed: Add support for RoCE hw init qede: Add qedr framework ...
Diffstat (limited to 'net/bridge')
-rw-r--r--net/bridge/Makefile2
-rw-r--r--net/bridge/br.c6
-rw-r--r--net/bridge/br_device.c8
-rw-r--r--net/bridge/br_fdb.c23
-rw-r--r--net/bridge/br_forward.c10
-rw-r--r--net/bridge/br_if.c12
-rw-r--r--net/bridge/br_input.c42
-rw-r--r--net/bridge/br_netfilter_hooks.c53
-rw-r--r--net/bridge/br_netfilter_ipv6.c12
-rw-r--r--net/bridge/br_netlink.c132
-rw-r--r--net/bridge/br_private.h46
-rw-r--r--net/bridge/br_stp_if.c43
-rw-r--r--net/bridge/br_switchdev.c57
-rw-r--r--net/bridge/br_sysfs_if.c1
-rw-r--r--net/bridge/netfilter/ebt_log.c2
-rw-r--r--net/bridge/netfilter/ebt_redirect.c2
-rw-r--r--net/bridge/netfilter/ebtables.c2
-rw-r--r--net/bridge/netfilter/nf_log_bridge.c3
-rw-r--r--net/bridge/netfilter/nf_tables_bridge.c92
-rw-r--r--net/bridge/netfilter/nft_reject_bridge.c44
20 files changed, 363 insertions, 229 deletions
diff --git a/net/bridge/Makefile b/net/bridge/Makefile
index a1cda5d4718d..0aefc011b668 100644
--- a/net/bridge/Makefile
+++ b/net/bridge/Makefile
@@ -20,4 +20,6 @@ bridge-$(CONFIG_BRIDGE_IGMP_SNOOPING) += br_multicast.o br_mdb.o
bridge-$(CONFIG_BRIDGE_VLAN_FILTERING) += br_vlan.o
+bridge-$(CONFIG_NET_SWITCHDEV) += br_switchdev.o
+
obj-$(CONFIG_NETFILTER) += netfilter/
diff --git a/net/bridge/br.c b/net/bridge/br.c
index 3addc05b9a16..889e5640455f 100644
--- a/net/bridge/br.c
+++ b/net/bridge/br.c
@@ -227,9 +227,11 @@ static int __init br_init(void)
br_fdb_test_addr_hook = br_fdb_test_addr;
#endif
- pr_info("bridge: automatic filtering via arp/ip/ip6tables has been "
- "deprecated. Update your scripts to load br_netfilter if you "
+#if IS_MODULE(CONFIG_BRIDGE_NETFILTER)
+ pr_info("bridge: filtering via arp/ip/ip6tables is no longer available "
+ "by default. Update your scripts to load br_netfilter if you "
"need this.\n");
+#endif
return 0;
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 09f26940aba5..89a687f3c0a3 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -62,10 +62,10 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
goto out;
if (is_broadcast_ether_addr(dest)) {
- br_flood(br, skb, false, false, true);
+ br_flood(br, skb, BR_PKT_BROADCAST, false, true);
} else if (is_multicast_ether_addr(dest)) {
if (unlikely(netpoll_tx_running(dev))) {
- br_flood(br, skb, false, false, true);
+ br_flood(br, skb, BR_PKT_MULTICAST, false, true);
goto out;
}
if (br_multicast_rcv(br, NULL, skb, vid)) {
@@ -78,11 +78,11 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
br_multicast_querier_exists(br, eth_hdr(skb)))
br_multicast_flood(mdst, skb, false, true);
else
- br_flood(br, skb, false, false, true);
+ br_flood(br, skb, BR_PKT_MULTICAST, false, true);
} else if ((dst = __br_fdb_get(br, dest, vid)) != NULL) {
br_forward(dst->dst, skb, false, true);
} else {
- br_flood(br, skb, true, false, true);
+ br_flood(br, skb, BR_PKT_UNICAST, false, true);
}
out:
rcu_read_unlock();
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index cd620fab41b0..6b43c8c88f19 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -710,24 +710,27 @@ int br_fdb_dump(struct sk_buff *skb,
struct netlink_callback *cb,
struct net_device *dev,
struct net_device *filter_dev,
- int idx)
+ int *idx)
{
struct net_bridge *br = netdev_priv(dev);
+ int err = 0;
int i;
if (!(dev->priv_flags & IFF_EBRIDGE))
goto out;
- if (!filter_dev)
- idx = ndo_dflt_fdb_dump(skb, cb, dev, NULL, idx);
+ if (!filter_dev) {
+ err = ndo_dflt_fdb_dump(skb, cb, dev, NULL, idx);
+ if (err < 0)
+ 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) {
- int err;
- if (idx < cb->args[0])
+ if (*idx < cb->args[2])
goto skip;
if (filter_dev &&
@@ -750,17 +753,15 @@ int br_fdb_dump(struct sk_buff *skb,
cb->nlh->nlmsg_seq,
RTM_NEWNEIGH,
NLM_F_MULTI);
- if (err < 0) {
- cb->args[1] = err;
- break;
- }
+ if (err < 0)
+ goto out;
skip:
- ++idx;
+ *idx += 1;
}
}
out:
- return idx;
+ return err;
}
/* Update (create or replace) forwarding database entry */
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 63a83d8d7da3..7cb41aee4c82 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -29,7 +29,8 @@ static inline int should_deliver(const struct net_bridge_port *p,
vg = nbp_vlan_group_rcu(p);
return ((p->flags & BR_HAIRPIN_MODE) || skb->dev != p->dev) &&
- br_allowed_egress(vg, skb) && p->state == BR_STATE_FORWARDING;
+ br_allowed_egress(vg, skb) && p->state == BR_STATE_FORWARDING &&
+ nbp_switchdev_allowed_egress(p, skb);
}
int br_dev_queue_push_xmit(struct net *net, struct sock *sk, struct sk_buff *skb)
@@ -175,7 +176,7 @@ out:
/* called under rcu_read_lock */
void br_flood(struct net_bridge *br, struct sk_buff *skb,
- bool unicast, bool local_rcv, bool local_orig)
+ enum br_pkt_type pkt_type, bool local_rcv, bool local_orig)
{
u8 igmp_type = br_multicast_igmp_type(skb);
struct net_bridge_port *prev = NULL;
@@ -183,7 +184,10 @@ void br_flood(struct net_bridge *br, struct sk_buff *skb,
list_for_each_entry_rcu(p, &br->port_list, list) {
/* Do not flood unicast traffic to ports that turn it off */
- if (unicast && !(p->flags & BR_FLOOD))
+ if (pkt_type == BR_PKT_UNICAST && !(p->flags & BR_FLOOD))
+ continue;
+ if (pkt_type == BR_PKT_MULTICAST &&
+ !(p->flags & BR_MCAST_FLOOD))
continue;
/* Do not flood to ports that enable proxy ARP */
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index f2fede05d32c..ed0dd3340084 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -362,7 +362,7 @@ 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 = BR_LEARNING | BR_FLOOD;
+ p->flags = BR_LEARNING | BR_FLOOD | BR_MCAST_FLOOD;
br_init_port(p);
br_set_state(p, BR_STATE_DISABLED);
br_stp_port_timer_init(p);
@@ -545,6 +545,10 @@ int br_add_if(struct net_bridge *br, struct net_device *dev)
if (err)
goto err5;
+ err = nbp_switchdev_mark_set(p);
+ if (err)
+ goto err6;
+
dev_disable_lro(dev);
list_add_rcu(&p->list, &br->port_list);
@@ -566,7 +570,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev)
err = nbp_vlan_init(p);
if (err) {
netdev_err(dev, "failed to initialize vlan filtering on this port\n");
- goto err6;
+ goto err7;
}
spin_lock_bh(&br->lock);
@@ -589,12 +593,12 @@ int br_add_if(struct net_bridge *br, struct net_device *dev)
return 0;
-err6:
+err7:
list_del_rcu(&p->list);
br_fdb_delete_by_port(br, p, 0, 1);
nbp_update_port_count(br);
+err6:
netdev_upper_dev_unlink(dev, br->dev);
-
err5:
dev->priv_flags &= ~IFF_BRIDGE_PORT;
netdev_rx_handler_unregister(dev);
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index abe11f085479..855b72fbe1da 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -128,11 +128,12 @@ static void br_do_proxy_arp(struct sk_buff *skb, struct net_bridge *br,
/* note: already called with rcu_read_lock */
int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
- bool local_rcv = false, mcast_hit = false, unicast = true;
struct net_bridge_port *p = br_port_get_rcu(skb->dev);
const unsigned char *dest = eth_hdr(skb)->h_dest;
+ enum br_pkt_type pkt_type = BR_PKT_UNICAST;
struct net_bridge_fdb_entry *dst = NULL;
struct net_bridge_mdb_entry *mdst;
+ bool local_rcv, mcast_hit = false;
struct net_bridge *br;
u16 vid = 0;
@@ -142,29 +143,36 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
if (!br_allowed_ingress(p->br, nbp_vlan_group_rcu(p), skb, &vid))
goto out;
+ nbp_switchdev_frame_mark(p, skb);
+
/* insert into forwarding database after filtering to avoid spoofing */
br = p->br;
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;
+ local_rcv = !!(br->dev->flags & IFF_PROMISC);
+ if (is_multicast_ether_addr(dest)) {
+ /* by definition the broadcast is also a multicast address */
+ if (is_broadcast_ether_addr(dest)) {
+ pkt_type = BR_PKT_BROADCAST;
+ local_rcv = true;
+ } else {
+ pkt_type = BR_PKT_MULTICAST;
+ if (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;
- local_rcv = !!(br->dev->flags & IFF_PROMISC);
-
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)) {
- local_rcv = true;
- unicast = false;
- } else if (is_multicast_ether_addr(dest)) {
+ switch (pkt_type) {
+ case BR_PKT_MULTICAST:
mdst = br_mdb_get(br, skb, vid);
if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) &&
br_multicast_querier_exists(br, eth_hdr(skb))) {
@@ -178,18 +186,22 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
local_rcv = true;
br->dev->stats.multicast++;
}
- unicast = false;
- } else if ((dst = __br_fdb_get(br, dest, vid)) && dst->is_local) {
- /* Do not forward the packet since it's local. */
- return br_pass_frame_up(skb);
+ break;
+ case BR_PKT_UNICAST:
+ dst = __br_fdb_get(br, dest, vid);
+ default:
+ break;
}
if (dst) {
+ if (dst->is_local)
+ return br_pass_frame_up(skb);
+
dst->used = jiffies;
br_forward(dst->dst, skb, local_rcv, false);
} else {
if (!mcast_hit)
- br_flood(br, skb, unicast, local_rcv, false);
+ br_flood(br, skb, pkt_type, local_rcv, false);
else
br_multicast_flood(mdst, skb, local_rcv, false);
}
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 77e7f69bf80d..2fe9345c1407 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -30,6 +30,7 @@
#include <linux/netfilter_ipv6.h>
#include <linux/netfilter_arp.h>
#include <linux/in_route.h>
+#include <linux/rculist.h>
#include <linux/inetdevice.h>
#include <net/ip.h>
@@ -395,11 +396,10 @@ bridged_dnat:
skb->dev = nf_bridge->physindev;
nf_bridge_update_protocol(skb);
nf_bridge_push_encap_header(skb);
- NF_HOOK_THRESH(NFPROTO_BRIDGE,
- NF_BR_PRE_ROUTING,
- net, sk, skb, skb->dev, NULL,
- br_nf_pre_routing_finish_bridge,
- 1);
+ br_nf_hook_thresh(NF_BR_PRE_ROUTING,
+ net, sk, skb, skb->dev,
+ NULL,
+ br_nf_pre_routing_finish);
return 0;
}
ether_addr_copy(eth_hdr(skb)->h_dest, dev->dev_addr);
@@ -417,10 +417,8 @@ bridged_dnat:
skb->dev = nf_bridge->physindev;
nf_bridge_update_protocol(skb);
nf_bridge_push_encap_header(skb);
- NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, net, sk, skb,
- skb->dev, NULL,
- br_handle_frame_finish, 1);
-
+ br_nf_hook_thresh(NF_BR_PRE_ROUTING, net, sk, skb, skb->dev, NULL,
+ br_handle_frame_finish);
return 0;
}
@@ -992,6 +990,43 @@ static struct notifier_block brnf_notifier __read_mostly = {
.notifier_call = brnf_device_event,
};
+/* recursively invokes nf_hook_slow (again), skipping already-called
+ * hooks (< NF_BR_PRI_BRNF).
+ *
+ * Called with rcu read lock held.
+ */
+int br_nf_hook_thresh(unsigned int hook, struct net *net,
+ struct sock *sk, struct sk_buff *skb,
+ struct net_device *indev,
+ struct net_device *outdev,
+ int (*okfn)(struct net *, struct sock *,
+ struct sk_buff *))
+{
+ struct nf_hook_entry *elem;
+ struct nf_hook_state state;
+ int ret;
+
+ elem = rcu_dereference(net->nf.hooks[NFPROTO_BRIDGE][hook]);
+
+ while (elem && (elem->ops.priority <= NF_BR_PRI_BRNF))
+ elem = rcu_dereference(elem->next);
+
+ if (!elem)
+ return okfn(net, sk, skb);
+
+ /* We may already have this, but read-locks nest anyway */
+ rcu_read_lock();
+ nf_hook_state_init(&state, elem, hook, NF_BR_PRI_BRNF + 1,
+ NFPROTO_BRIDGE, indev, outdev, sk, net, okfn);
+
+ ret = nf_hook_slow(skb, &state);
+ rcu_read_unlock();
+ if (ret == 1)
+ ret = okfn(net, sk, skb);
+
+ return ret;
+}
+
#ifdef CONFIG_SYSCTL
static
int brnf_sysctl_call_tables(struct ctl_table *ctl, int write,
diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c
index 5e59a8457e7b..5989661c659f 100644
--- a/net/bridge/br_netfilter_ipv6.c
+++ b/net/bridge/br_netfilter_ipv6.c
@@ -187,10 +187,9 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc
skb->dev = nf_bridge->physindev;
nf_bridge_update_protocol(skb);
nf_bridge_push_encap_header(skb);
- NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING,
- net, sk, skb, skb->dev, NULL,
- br_nf_pre_routing_finish_bridge,
- 1);
+ br_nf_hook_thresh(NF_BR_PRE_ROUTING,
+ net, sk, skb, skb->dev, NULL,
+ br_nf_pre_routing_finish_bridge);
return 0;
}
ether_addr_copy(eth_hdr(skb)->h_dest, dev->dev_addr);
@@ -207,9 +206,8 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc
skb->dev = nf_bridge->physindev;
nf_bridge_update_protocol(skb);
nf_bridge_push_encap_header(skb);
- NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, net, sk, skb,
- skb->dev, NULL,
- br_handle_frame_finish, 1);
+ br_nf_hook_thresh(NF_BR_PRE_ROUTING, net, sk, skb,
+ skb->dev, NULL, br_handle_frame_finish);
return 0;
}
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index f2a29e467e78..e99037c6f7b7 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -169,10 +169,15 @@ static int br_port_fill_attrs(struct sk_buff *skb,
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_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)) ||
+ nla_put_u8(skb, IFLA_BRPORT_UNICAST_FLOOD,
+ !!(p->flags & BR_FLOOD)) ||
+ nla_put_u8(skb, IFLA_BRPORT_MCAST_FLOOD,
+ !!(p->flags & BR_MCAST_FLOOD)) ||
nla_put_u8(skb, IFLA_BRPORT_PROXYARP, !!(p->flags & BR_PROXYARP)) ||
nla_put_u8(skb, IFLA_BRPORT_PROXYARP_WIFI,
!!(p->flags & BR_PROXYARP_WIFI)) ||
@@ -630,6 +635,7 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[])
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);
+ br_set_port_flag(p, tb, IFLA_BRPORT_MCAST_FLOOD, BR_MCAST_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);
@@ -1245,14 +1251,30 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev)
return 0;
}
-static size_t bridge_get_linkxstats_size(const struct net_device *dev)
+static size_t br_get_linkxstats_size(const struct net_device *dev, int attr)
{
- struct net_bridge *br = netdev_priv(dev);
+ struct net_bridge_port *p = NULL;
struct net_bridge_vlan_group *vg;
struct net_bridge_vlan *v;
+ struct net_bridge *br;
int numvls = 0;
- vg = br_vlan_group(br);
+ switch (attr) {
+ case IFLA_STATS_LINK_XSTATS:
+ br = netdev_priv(dev);
+ vg = br_vlan_group(br);
+ break;
+ case IFLA_STATS_LINK_XSTATS_SLAVE:
+ p = br_port_get_rtnl(dev);
+ if (!p)
+ return 0;
+ br = p->br;
+ vg = nbp_vlan_group(p);
+ break;
+ default:
+ return 0;
+ }
+
if (vg) {
/* we need to count all, even placeholder entries */
list_for_each_entry(v, &vg->vlan_list, vlist)
@@ -1264,45 +1286,42 @@ static size_t bridge_get_linkxstats_size(const struct net_device *dev)
nla_total_size(0);
}
-static size_t brport_get_linkxstats_size(const struct net_device *dev)
-{
- return nla_total_size(sizeof(struct br_mcast_stats)) +
- nla_total_size(0);
-}
-
-static size_t br_get_linkxstats_size(const struct net_device *dev, int attr)
+static int br_fill_linkxstats(struct sk_buff *skb,
+ const struct net_device *dev,
+ int *prividx, int attr)
{
- size_t retsize = 0;
+ struct nlattr *nla __maybe_unused;
+ struct net_bridge_port *p = NULL;
+ struct net_bridge_vlan_group *vg;
+ struct net_bridge_vlan *v;
+ struct net_bridge *br;
+ struct nlattr *nest;
+ int vl_idx = 0;
switch (attr) {
case IFLA_STATS_LINK_XSTATS:
- retsize = bridge_get_linkxstats_size(dev);
+ br = netdev_priv(dev);
+ vg = br_vlan_group(br);
break;
case IFLA_STATS_LINK_XSTATS_SLAVE:
- retsize = brport_get_linkxstats_size(dev);
+ p = br_port_get_rtnl(dev);
+ if (!p)
+ return 0;
+ br = p->br;
+ vg = nbp_vlan_group(p);
break;
+ default:
+ return -EINVAL;
}
- return retsize;
-}
-
-static int bridge_fill_linkxstats(struct sk_buff *skb,
- const struct net_device *dev,
- int *prividx)
-{
- struct net_bridge *br = netdev_priv(dev);
- struct nlattr *nla __maybe_unused;
- struct net_bridge_vlan_group *vg;
- struct net_bridge_vlan *v;
- struct nlattr *nest;
- int vl_idx = 0;
-
nest = nla_nest_start(skb, LINK_XSTATS_TYPE_BRIDGE);
if (!nest)
return -EMSGSIZE;
- vg = br_vlan_group(br);
if (vg) {
+ u16 pvid;
+
+ pvid = br_get_pvid(vg);
list_for_each_entry(v, &vg->vlan_list, vlist) {
struct bridge_vlan_xstats vxi;
struct br_vlan_stats stats;
@@ -1311,6 +1330,9 @@ static int bridge_fill_linkxstats(struct sk_buff *skb,
continue;
memset(&vxi, 0, sizeof(vxi));
vxi.vid = v->vid;
+ vxi.flags = v->flags;
+ if (v->vid == pvid)
+ vxi.flags |= BRIDGE_VLAN_INFO_PVID;
br_vlan_get_stats(v, &stats);
vxi.rx_bytes = stats.rx_bytes;
vxi.rx_packets = stats.rx_packets;
@@ -1329,7 +1351,7 @@ static int bridge_fill_linkxstats(struct sk_buff *skb,
BRIDGE_XSTATS_PAD);
if (!nla)
goto nla_put_failure;
- br_multicast_get_stats(br, NULL, nla_data(nla));
+ br_multicast_get_stats(br, p, nla_data(nla));
}
#endif
nla_nest_end(skb, nest);
@@ -1344,52 +1366,6 @@ nla_put_failure:
return -EMSGSIZE;
}
-static int brport_fill_linkxstats(struct sk_buff *skb,
- const struct net_device *dev,
- int *prividx)
-{
- struct net_bridge_port *p = br_port_get_rtnl(dev);
- struct nlattr *nla __maybe_unused;
- struct nlattr *nest;
-
- if (!p)
- return 0;
-
- nest = nla_nest_start(skb, LINK_XSTATS_TYPE_BRIDGE);
- if (!nest)
- return -EMSGSIZE;
-#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
- nla = nla_reserve_64bit(skb, BRIDGE_XSTATS_MCAST,
- sizeof(struct br_mcast_stats),
- BRIDGE_XSTATS_PAD);
- if (!nla) {
- nla_nest_end(skb, nest);
- return -EMSGSIZE;
- }
- br_multicast_get_stats(p->br, p, nla_data(nla));
-#endif
- nla_nest_end(skb, nest);
-
- return 0;
-}
-
-static int br_fill_linkxstats(struct sk_buff *skb, const struct net_device *dev,
- int *prividx, int attr)
-{
- int ret = -EINVAL;
-
- switch (attr) {
- case IFLA_STATS_LINK_XSTATS:
- ret = bridge_fill_linkxstats(skb, dev, prividx);
- break;
- case IFLA_STATS_LINK_XSTATS_SLAVE:
- ret = brport_fill_linkxstats(skb, dev, prividx);
- break;
- }
-
- return ret;
-}
-
static struct rtnl_af_ops br_af_ops __read_mostly = {
.family = AF_BRIDGE,
.get_link_af_size = br_get_link_af_size_filtered,
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index aac2a6e6b008..1b63177e0ccd 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -251,6 +251,9 @@ struct net_bridge_port
#ifdef CONFIG_BRIDGE_VLAN_FILTERING
struct net_bridge_vlan_group __rcu *vlgrp;
#endif
+#ifdef CONFIG_NET_SWITCHDEV
+ int offload_fwd_mark;
+#endif
};
#define br_auto_port(p) ((p)->flags & BR_AUTO_MASK)
@@ -359,6 +362,11 @@ struct net_bridge
struct timer_list gc_timer;
struct kobject *ifobj;
u32 auto_cnt;
+
+#ifdef CONFIG_NET_SWITCHDEV
+ int offload_fwd_mark;
+#endif
+
#ifdef CONFIG_BRIDGE_VLAN_FILTERING
struct net_bridge_vlan_group __rcu *vlgrp;
u8 vlan_enabled;
@@ -381,6 +389,10 @@ struct br_input_skb_cb {
#ifdef CONFIG_BRIDGE_VLAN_FILTERING
bool vlan_filtered;
#endif
+
+#ifdef CONFIG_NET_SWITCHDEV
+ int offload_fwd_mark;
+#endif
};
#define BR_INPUT_SKB_CB(__skb) ((struct br_input_skb_cb *)(__skb)->cb)
@@ -496,7 +508,7 @@ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
int br_fdb_add(struct ndmsg *nlh, struct nlattr *tb[], struct net_device *dev,
const unsigned char *addr, u16 vid, u16 nlh_flags);
int br_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
- struct net_device *dev, struct net_device *fdev, int idx);
+ struct net_device *dev, struct net_device *fdev, 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);
int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p,
@@ -505,12 +517,17 @@ int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p,
const unsigned char *addr, u16 vid);
/* br_forward.c */
+enum br_pkt_type {
+ BR_PKT_UNICAST,
+ BR_PKT_MULTICAST,
+ BR_PKT_BROADCAST
+};
int br_dev_queue_push_xmit(struct net *net, struct sock *sk, struct sk_buff *skb);
void br_forward(const struct net_bridge_port *to, struct sk_buff *skb,
bool local_rcv, bool local_orig);
int br_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb);
void br_flood(struct net_bridge *br, struct sk_buff *skb,
- bool unicast, bool local_rcv, bool local_orig);
+ enum br_pkt_type pkt_type, bool local_rcv, bool local_orig);
/* br_if.c */
void br_port_carrier_check(struct net_bridge_port *p);
@@ -1034,4 +1051,29 @@ 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 */
+/* br_switchdev.c */
+#ifdef CONFIG_NET_SWITCHDEV
+int nbp_switchdev_mark_set(struct net_bridge_port *p);
+void nbp_switchdev_frame_mark(const struct net_bridge_port *p,
+ struct sk_buff *skb);
+bool nbp_switchdev_allowed_egress(const struct net_bridge_port *p,
+ const struct sk_buff *skb);
+#else
+static inline int nbp_switchdev_mark_set(struct net_bridge_port *p)
+{
+ return 0;
+}
+
+static inline void nbp_switchdev_frame_mark(const struct net_bridge_port *p,
+ struct sk_buff *skb)
+{
+}
+
+static inline bool nbp_switchdev_allowed_egress(const struct net_bridge_port *p,
+ const struct sk_buff *skb)
+{
+ return true;
+}
+#endif /* CONFIG_NET_SWITCHDEV */
+
#endif
diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c
index 341caa0ca63a..d8ad73b38de2 100644
--- a/net/bridge/br_stp_if.c
+++ b/net/bridge/br_stp_if.c
@@ -134,17 +134,36 @@ void br_stp_disable_port(struct net_bridge_port *p)
br_become_root_bridge(br);
}
-static void br_stp_start(struct net_bridge *br)
+static int br_stp_call_user(struct net_bridge *br, char *arg)
{
- int r;
- char *argv[] = { BR_STP_PROG, br->dev->name, "start", NULL };
+ char *argv[] = { BR_STP_PROG, br->dev->name, arg, NULL };
char *envp[] = { NULL };
+ int rc;
+
+ /* call userspace STP and report program errors */
+ rc = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC);
+ if (rc > 0) {
+ if (rc & 0xff)
+ br_debug(br, BR_STP_PROG " received signal %d\n",
+ rc & 0x7f);
+ else
+ br_debug(br, BR_STP_PROG " exited with code %d\n",
+ (rc >> 8) & 0xff);
+ }
+
+ return rc;
+}
+
+static void br_stp_start(struct net_bridge *br)
+{
struct net_bridge_port *p;
+ int err = -ENOENT;
if (net_eq(dev_net(br->dev), &init_net))
- r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC);
- else
- r = -ENOENT;
+ err = br_stp_call_user(br, "start");
+
+ if (err && err != -ENOENT)
+ br_err(br, "failed to start userspace STP (%d)\n", err);
spin_lock_bh(&br->lock);
@@ -153,9 +172,10 @@ static void br_stp_start(struct net_bridge *br)
else if (br->bridge_forward_delay > BR_MAX_FORWARD_DELAY)
__br_set_forward_delay(br, BR_MAX_FORWARD_DELAY);
- if (r == 0) {
+ if (!err) {
br->stp_enabled = BR_USER_STP;
br_debug(br, "userspace STP started\n");
+
/* Stop hello and hold timers */
del_timer(&br->hello_timer);
list_for_each_entry(p, &br->port_list, list)
@@ -173,14 +193,13 @@ static void br_stp_start(struct net_bridge *br)
static void br_stp_stop(struct net_bridge *br)
{
- int r;
- char *argv[] = { BR_STP_PROG, br->dev->name, "stop", NULL };
- char *envp[] = { NULL };
struct net_bridge_port *p;
+ int err;
if (br->stp_enabled == BR_USER_STP) {
- r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC);
- br_info(br, "userspace STP stopped, return code %d\n", r);
+ err = br_stp_call_user(br, "stop");
+ if (err)
+ br_err(br, "failed to stop userspace STP (%d)\n", err);
/* To start timers on any ports left in blocking */
mod_timer(&br->hello_timer, jiffies + br->hello_time);
diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c
new file mode 100644
index 000000000000..f4097b900de1
--- /dev/null
+++ b/net/bridge/br_switchdev.c
@@ -0,0 +1,57 @@
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/netdevice.h>
+#include <linux/rtnetlink.h>
+#include <linux/skbuff.h>
+#include <net/switchdev.h>
+
+#include "br_private.h"
+
+static int br_switchdev_mark_get(struct net_bridge *br, struct net_device *dev)
+{
+ struct net_bridge_port *p;
+
+ /* dev is yet to be added to the port list. */
+ list_for_each_entry(p, &br->port_list, list) {
+ if (switchdev_port_same_parent_id(dev, p->dev))
+ return p->offload_fwd_mark;
+ }
+
+ return ++br->offload_fwd_mark;
+}
+
+int nbp_switchdev_mark_set(struct net_bridge_port *p)
+{
+ struct switchdev_attr attr = {
+ .orig_dev = p->dev,
+ .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID,
+ };
+ int err;
+
+ ASSERT_RTNL();
+
+ err = switchdev_port_attr_get(p->dev, &attr);
+ if (err) {
+ if (err == -EOPNOTSUPP)
+ return 0;
+ return err;
+ }
+
+ p->offload_fwd_mark = br_switchdev_mark_get(p->br, p->dev);
+
+ return 0;
+}
+
+void nbp_switchdev_frame_mark(const struct net_bridge_port *p,
+ struct sk_buff *skb)
+{
+ if (skb->offload_fwd_mark && !WARN_ON_ONCE(!p->offload_fwd_mark))
+ BR_INPUT_SKB_CB(skb)->offload_fwd_mark = p->offload_fwd_mark;
+}
+
+bool nbp_switchdev_allowed_egress(const struct net_bridge_port *p,
+ const struct sk_buff *skb)
+{
+ return !skb->offload_fwd_mark ||
+ BR_INPUT_SKB_CB(skb)->offload_fwd_mark != p->offload_fwd_mark;
+}
diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c
index 1e04d4d44273..e657258e1f2c 100644
--- a/net/bridge/br_sysfs_if.c
+++ b/net/bridge/br_sysfs_if.c
@@ -171,6 +171,7 @@ 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);
+BRPORT_ATTR_FLAG(multicast_flood, BR_MCAST_FLOOD);
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
static ssize_t show_multicast_router(struct net_bridge_port *p, char *buf)
diff --git a/net/bridge/netfilter/ebt_log.c b/net/bridge/netfilter/ebt_log.c
index 152300d164ac..9a11086ba6ff 100644
--- a/net/bridge/netfilter/ebt_log.c
+++ b/net/bridge/netfilter/ebt_log.c
@@ -91,7 +91,7 @@ ebt_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum,
if (loginfo->type == NF_LOG_TYPE_LOG)
bitmask = loginfo->u.log.logflags;
else
- bitmask = NF_LOG_MASK;
+ bitmask = NF_LOG_DEFAULT_MASK;
if ((bitmask & EBT_LOG_IP) && eth_hdr(skb)->h_proto ==
htons(ETH_P_IP)) {
diff --git a/net/bridge/netfilter/ebt_redirect.c b/net/bridge/netfilter/ebt_redirect.c
index 203964997a51..2e7c4f974340 100644
--- a/net/bridge/netfilter/ebt_redirect.c
+++ b/net/bridge/netfilter/ebt_redirect.c
@@ -24,7 +24,7 @@ ebt_redirect_tg(struct sk_buff *skb, const struct xt_action_param *par)
return EBT_DROP;
if (par->hooknum != NF_BR_BROUTING)
- /* rcu_read_lock()ed by nf_hook_slow */
+ /* rcu_read_lock()ed by nf_hook_thresh */
ether_addr_copy(eth_hdr(skb)->h_dest,
br_port_get_rcu(par->in)->br->dev->dev_addr);
else
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 0833c251aef7..f5c11bbe27db 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -146,7 +146,7 @@ ebt_basic_match(const struct ebt_entry *e, const struct sk_buff *skb,
return 1;
if (NF_INVF(e, EBT_IOUT, ebt_dev_check(e->out, out)))
return 1;
- /* rcu_read_lock()ed by nf_hook_slow */
+ /* rcu_read_lock()ed by nf_hook_thresh */
if (in && (p = br_port_get_rcu(in)) != NULL &&
NF_INVF(e, EBT_ILOGICALIN,
ebt_dev_check(e->logical_in, p->br->dev)))
diff --git a/net/bridge/netfilter/nf_log_bridge.c b/net/bridge/netfilter/nf_log_bridge.c
index 5d9953a90929..1663df598545 100644
--- a/net/bridge/netfilter/nf_log_bridge.c
+++ b/net/bridge/netfilter/nf_log_bridge.c
@@ -50,8 +50,7 @@ static struct nf_logger nf_bridge_logger __read_mostly = {
static int __net_init nf_log_bridge_net_init(struct net *net)
{
- nf_log_set(net, NFPROTO_BRIDGE, &nf_bridge_logger);
- return 0;
+ return nf_log_set(net, NFPROTO_BRIDGE, &nf_bridge_logger);
}
static void __net_exit nf_log_bridge_net_exit(struct net *net)
diff --git a/net/bridge/netfilter/nf_tables_bridge.c b/net/bridge/netfilter/nf_tables_bridge.c
index a78c4e2826e5..97afdc0744e6 100644
--- a/net/bridge/netfilter/nf_tables_bridge.c
+++ b/net/bridge/netfilter/nf_tables_bridge.c
@@ -13,79 +13,11 @@
#include <linux/module.h>
#include <linux/netfilter_bridge.h>
#include <net/netfilter/nf_tables.h>
-#include <net/netfilter/nf_tables_bridge.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <net/netfilter/nf_tables_ipv4.h>
#include <net/netfilter/nf_tables_ipv6.h>
-int nft_bridge_iphdr_validate(struct sk_buff *skb)
-{
- struct iphdr *iph;
- u32 len;
-
- if (!pskb_may_pull(skb, sizeof(struct iphdr)))
- return 0;
-
- iph = ip_hdr(skb);
- if (iph->ihl < 5 || iph->version != 4)
- return 0;
-
- len = ntohs(iph->tot_len);
- if (skb->len < len)
- return 0;
- else if (len < (iph->ihl*4))
- return 0;
-
- if (!pskb_may_pull(skb, iph->ihl*4))
- return 0;
-
- return 1;
-}
-EXPORT_SYMBOL_GPL(nft_bridge_iphdr_validate);
-
-int nft_bridge_ip6hdr_validate(struct sk_buff *skb)
-{
- struct ipv6hdr *hdr;
- u32 pkt_len;
-
- if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
- return 0;
-
- hdr = ipv6_hdr(skb);
- if (hdr->version != 6)
- return 0;
-
- pkt_len = ntohs(hdr->payload_len);
- if (pkt_len + sizeof(struct ipv6hdr) > skb->len)
- return 0;
-
- return 1;
-}
-EXPORT_SYMBOL_GPL(nft_bridge_ip6hdr_validate);
-
-static inline void nft_bridge_set_pktinfo_ipv4(struct nft_pktinfo *pkt,
- struct sk_buff *skb,
- const struct nf_hook_state *state)
-{
- if (nft_bridge_iphdr_validate(skb))
- nft_set_pktinfo_ipv4(pkt, skb, state);
- else
- nft_set_pktinfo(pkt, skb, state);
-}
-
-static inline void nft_bridge_set_pktinfo_ipv6(struct nft_pktinfo *pkt,
- 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, skb, state) == 0)
- return;
-#endif
- nft_set_pktinfo(pkt, skb, state);
-}
-
static unsigned int
nft_do_chain_bridge(void *priv,
struct sk_buff *skb,
@@ -95,13 +27,13 @@ nft_do_chain_bridge(void *priv,
switch (eth_hdr(skb)->h_proto) {
case htons(ETH_P_IP):
- nft_bridge_set_pktinfo_ipv4(&pkt, skb, state);
+ nft_set_pktinfo_ipv4_validate(&pkt, skb, state);
break;
case htons(ETH_P_IPV6):
- nft_bridge_set_pktinfo_ipv6(&pkt, skb, state);
+ nft_set_pktinfo_ipv6_validate(&pkt, skb, state);
break;
default:
- nft_set_pktinfo(&pkt, skb, state);
+ nft_set_pktinfo_unspec(&pkt, skb, state);
break;
}
@@ -207,12 +139,20 @@ static int __init nf_tables_bridge_init(void)
int ret;
nf_register_afinfo(&nf_br_afinfo);
- nft_register_chain_type(&filter_bridge);
+ ret = nft_register_chain_type(&filter_bridge);
+ if (ret < 0)
+ goto err1;
+
ret = register_pernet_subsys(&nf_tables_bridge_net_ops);
- if (ret < 0) {
- nft_unregister_chain_type(&filter_bridge);
- nf_unregister_afinfo(&nf_br_afinfo);
- }
+ if (ret < 0)
+ goto err2;
+
+ return ret;
+
+err2:
+ nft_unregister_chain_type(&filter_bridge);
+err1:
+ nf_unregister_afinfo(&nf_br_afinfo);
return ret;
}
diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c
index 0b77ffbc27d6..4b3df6b0e3b9 100644
--- a/net/bridge/netfilter/nft_reject_bridge.c
+++ b/net/bridge/netfilter/nft_reject_bridge.c
@@ -14,7 +14,6 @@
#include <linux/netfilter/nf_tables.h>
#include <net/netfilter/nf_tables.h>
#include <net/netfilter/nft_reject.h>
-#include <net/netfilter/nf_tables_bridge.h>
#include <net/netfilter/ipv4/nf_reject.h>
#include <net/netfilter/ipv6/nf_reject.h>
#include <linux/ip.h>
@@ -37,6 +36,30 @@ static void nft_reject_br_push_etherhdr(struct sk_buff *oldskb,
skb_pull(nskb, ETH_HLEN);
}
+static int nft_bridge_iphdr_validate(struct sk_buff *skb)
+{
+ struct iphdr *iph;
+ u32 len;
+
+ if (!pskb_may_pull(skb, sizeof(struct iphdr)))
+ return 0;
+
+ iph = ip_hdr(skb);
+ if (iph->ihl < 5 || iph->version != 4)
+ return 0;
+
+ len = ntohs(iph->tot_len);
+ if (skb->len < len)
+ return 0;
+ else if (len < (iph->ihl*4))
+ return 0;
+
+ if (!pskb_may_pull(skb, iph->ihl*4))
+ return 0;
+
+ return 1;
+}
+
/* We cannot use oldskb->dev, it can be either bridge device (NF_BRIDGE INPUT)
* or the bridge port (NF_BRIDGE PREROUTING).
*/
@@ -143,6 +166,25 @@ static void nft_reject_br_send_v4_unreach(struct net *net,
br_forward(br_port_get_rcu(dev), nskb, false, true);
}
+static int nft_bridge_ip6hdr_validate(struct sk_buff *skb)
+{
+ struct ipv6hdr *hdr;
+ u32 pkt_len;
+
+ if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
+ return 0;
+
+ hdr = ipv6_hdr(skb);
+ if (hdr->version != 6)
+ return 0;
+
+ pkt_len = ntohs(hdr->payload_len);
+ if (pkt_len + sizeof(struct ipv6hdr) > skb->len)
+ return 0;
+
+ return 1;
+}
+
static void nft_reject_br_send_v6_tcp_reset(struct net *net,
struct sk_buff *oldskb,
const struct net_device *dev,