summaryrefslogtreecommitdiff
path: root/net/bridge
diff options
context:
space:
mode:
Diffstat (limited to 'net/bridge')
-rw-r--r--net/bridge/br.c1
-rw-r--r--net/bridge/br_device.c3
-rw-r--r--net/bridge/br_fdb.c71
-rw-r--r--net/bridge/br_input.c2
-rw-r--r--net/bridge/br_mdb.c184
-rw-r--r--net/bridge/br_multicast.c5
-rw-r--r--net/bridge/br_netfilter_hooks.c100
-rw-r--r--net/bridge/br_netfilter_ipv6.c6
-rw-r--r--net/bridge/br_netlink.c17
-rw-r--r--net/bridge/br_private.h26
10 files changed, 331 insertions, 84 deletions
diff --git a/net/bridge/br.c b/net/bridge/br.c
index a6e94ceb7c9a..ac19b797dbec 100644
--- a/net/bridge/br.c
+++ b/net/bridge/br.c
@@ -477,3 +477,4 @@ module_exit(br_deinit)
MODULE_LICENSE("GPL");
MODULE_VERSION(BR_VERSION);
MODULE_ALIAS_RTNL_LINK("bridge");
+MODULE_DESCRIPTION("Ethernet bridge driver");
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 9a5ea06236bd..8f40de3af154 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -92,7 +92,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
goto out;
}
- mdst = br_mdb_get(brmctx, skb, vid);
+ mdst = br_mdb_entry_skb_get(brmctx, skb, vid);
if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) &&
br_multicast_querier_exists(brmctx, eth_hdr(skb), mdst))
br_multicast_flood(mdst, skb, brmctx, false, true);
@@ -472,6 +472,7 @@ static const struct net_device_ops br_netdev_ops = {
.ndo_mdb_add = br_mdb_add,
.ndo_mdb_del = br_mdb_del,
.ndo_mdb_dump = br_mdb_dump,
+ .ndo_mdb_get = br_mdb_get,
.ndo_bridge_getlink = br_getlink,
.ndo_bridge_setlink = br_setlink,
.ndo_bridge_dellink = br_dellink,
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index e69a872bfc1d..c622de5eccd0 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -329,11 +329,18 @@ static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f,
hlist_del_init_rcu(&f->fdb_node);
rhashtable_remove_fast(&br->fdb_hash_tbl, &f->rhnode,
br_fdb_rht_params);
+ if (test_and_clear_bit(BR_FDB_DYNAMIC_LEARNED, &f->flags))
+ atomic_dec(&br->fdb_n_learned);
fdb_notify(br, f, RTM_DELNEIGH, swdev_notify);
call_rcu(&f->rcu, fdb_rcu_free);
}
-/* Delete a local entry if no other port had the same address. */
+/* Delete a local entry if no other port had the same address.
+ *
+ * This function should only be called on entries with BR_FDB_LOCAL set,
+ * so even with BR_FDB_ADDED_BY_USER cleared we never need to increase
+ * the accounting for dynamically learned entries again.
+ */
static void fdb_delete_local(struct net_bridge *br,
const struct net_bridge_port *p,
struct net_bridge_fdb_entry *f)
@@ -388,9 +395,20 @@ static struct net_bridge_fdb_entry *fdb_create(struct net_bridge *br,
__u16 vid,
unsigned long flags)
{
+ bool learned = !test_bit(BR_FDB_ADDED_BY_USER, &flags) &&
+ !test_bit(BR_FDB_LOCAL, &flags);
+ u32 max_learned = READ_ONCE(br->fdb_max_learned);
struct net_bridge_fdb_entry *fdb;
int err;
+ if (likely(learned)) {
+ int n_learned = atomic_read(&br->fdb_n_learned);
+
+ if (unlikely(max_learned && n_learned >= max_learned))
+ return NULL;
+ __set_bit(BR_FDB_DYNAMIC_LEARNED, &flags);
+ }
+
fdb = kmem_cache_alloc(br_fdb_cache, GFP_ATOMIC);
if (!fdb)
return NULL;
@@ -407,6 +425,9 @@ static struct net_bridge_fdb_entry *fdb_create(struct net_bridge *br,
return NULL;
}
+ if (likely(learned))
+ atomic_inc(&br->fdb_n_learned);
+
hlist_add_head_rcu(&fdb->fdb_node, &br->fdb_list);
return fdb;
@@ -661,14 +682,30 @@ static int __fdb_flush_validate_ifindex(const struct net_bridge *br,
return 0;
}
-int br_fdb_delete_bulk(struct ndmsg *ndm, struct nlattr *tb[],
- struct net_device *dev, u16 vid,
+static const struct nla_policy br_fdb_del_bulk_policy[NDA_MAX + 1] = {
+ [NDA_VLAN] = NLA_POLICY_RANGE(NLA_U16, 1, VLAN_N_VID - 2),
+ [NDA_IFINDEX] = NLA_POLICY_MIN(NLA_S32, 1),
+ [NDA_NDM_STATE_MASK] = { .type = NLA_U16 },
+ [NDA_NDM_FLAGS_MASK] = { .type = NLA_U8 },
+};
+
+int br_fdb_delete_bulk(struct nlmsghdr *nlh, struct net_device *dev,
struct netlink_ext_ack *extack)
{
- u8 ndm_flags = ndm->ndm_flags & ~FDB_FLUSH_IGNORED_NDM_FLAGS;
- struct net_bridge_fdb_flush_desc desc = { .vlan_id = vid };
+ struct net_bridge_fdb_flush_desc desc = {};
+ struct ndmsg *ndm = nlmsg_data(nlh);
struct net_bridge_port *p = NULL;
+ struct nlattr *tb[NDA_MAX + 1];
struct net_bridge *br;
+ u8 ndm_flags;
+ int err;
+
+ ndm_flags = ndm->ndm_flags & ~FDB_FLUSH_IGNORED_NDM_FLAGS;
+
+ err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX,
+ br_fdb_del_bulk_policy, extack);
+ if (err)
+ return err;
if (netif_is_bridge_master(dev)) {
br = netdev_priv(dev);
@@ -681,6 +718,9 @@ int br_fdb_delete_bulk(struct ndmsg *ndm, struct nlattr *tb[],
br = p->br;
}
+ if (tb[NDA_VLAN])
+ desc.vlan_id = nla_get_u16(tb[NDA_VLAN]);
+
if (ndm_flags & ~FDB_FLUSH_ALLOWED_NDM_FLAGS) {
NL_SET_ERR_MSG(extack, "Unsupported fdb flush ndm flag bits set");
return -EINVAL;
@@ -703,7 +743,7 @@ int br_fdb_delete_bulk(struct ndmsg *ndm, struct nlattr *tb[],
desc.flags_mask |= __ndm_flags_to_fdb_flags(ndm_flags_mask);
}
if (tb[NDA_IFINDEX]) {
- int err, ifidx = nla_get_s32(tb[NDA_IFINDEX]);
+ int ifidx = nla_get_s32(tb[NDA_IFINDEX]);
err = __fdb_flush_validate_ifindex(br, ifidx, extack);
if (err)
@@ -893,8 +933,12 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,
clear_bit(BR_FDB_LOCKED, &fdb->flags);
}
- if (unlikely(test_bit(BR_FDB_ADDED_BY_USER, &flags)))
+ if (unlikely(test_bit(BR_FDB_ADDED_BY_USER, &flags))) {
set_bit(BR_FDB_ADDED_BY_USER, &fdb->flags);
+ if (test_and_clear_bit(BR_FDB_DYNAMIC_LEARNED,
+ &fdb->flags))
+ atomic_dec(&br->fdb_n_learned);
+ }
if (unlikely(fdb_modified)) {
trace_br_fdb_update(br, source, addr, vid, flags);
fdb_notify(br, fdb, RTM_NEWNEIGH, true);
@@ -1056,7 +1100,8 @@ static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source,
if (!(flags & NLM_F_CREATE))
return -ENOENT;
- fdb = fdb_create(br, source, addr, vid, 0);
+ fdb = fdb_create(br, source, addr, vid,
+ BIT(BR_FDB_ADDED_BY_USER));
if (!fdb)
return -ENOMEM;
@@ -1069,6 +1114,10 @@ static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source,
WRITE_ONCE(fdb->dst, source);
modified = true;
}
+
+ set_bit(BR_FDB_ADDED_BY_USER, &fdb->flags);
+ if (test_and_clear_bit(BR_FDB_DYNAMIC_LEARNED, &fdb->flags))
+ atomic_dec(&br->fdb_n_learned);
}
if (fdb_to_nud(br, fdb) != state) {
@@ -1100,8 +1149,6 @@ static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source,
if (fdb_handle_notify(fdb, notify))
modified = true;
- set_bit(BR_FDB_ADDED_BY_USER, &fdb->flags);
-
fdb->used = jiffies;
if (modified) {
if (refresh)
@@ -1445,6 +1492,10 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p,
if (!p)
set_bit(BR_FDB_LOCAL, &fdb->flags);
+ if ((swdev_notify || !p) &&
+ test_and_clear_bit(BR_FDB_DYNAMIC_LEARNED, &fdb->flags))
+ atomic_dec(&br->fdb_n_learned);
+
if (modified)
fdb_notify(br, fdb, RTM_NEWNEIGH, swdev_notify);
}
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index c729528b5e85..f21097e73482 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -175,7 +175,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
switch (pkt_type) {
case BR_PKT_MULTICAST:
- mdst = br_mdb_get(brmctx, skb, vid);
+ mdst = br_mdb_entry_skb_get(brmctx, skb, vid);
if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) &&
br_multicast_querier_exists(brmctx, eth_hdr(skb), mdst)) {
if ((mdst && mdst->host_joined) ||
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index 7305f5f8215c..8cc526067bc2 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -323,9 +323,6 @@ static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb,
struct net_bridge_mdb_entry *mp;
struct nlattr *nest, *nest2;
- if (!br_opt_get(br, BROPT_MULTICAST_ENABLED))
- return 0;
-
nest = nla_nest_start_noflag(skb, MDBA_MDB);
if (nest == NULL)
return -EMSGSIZE;
@@ -453,13 +450,15 @@ cancel:
return -EMSGSIZE;
}
-static size_t rtnl_mdb_nlmsg_size(struct net_bridge_port_group *pg)
+static size_t rtnl_mdb_nlmsg_pg_size(const struct net_bridge_port_group *pg)
{
- size_t nlmsg_size = NLMSG_ALIGN(sizeof(struct br_port_msg)) +
- nla_total_size(sizeof(struct br_mdb_entry)) +
- nla_total_size(sizeof(u32));
struct net_bridge_group_src *ent;
- size_t addr_size = 0;
+ size_t nlmsg_size, addr_size = 0;
+
+ /* MDBA_MDB_ENTRY_INFO */
+ nlmsg_size = nla_total_size(sizeof(struct br_mdb_entry)) +
+ /* MDBA_MDB_EATTR_TIMER */
+ nla_total_size(sizeof(u32));
if (!pg)
goto out;
@@ -507,6 +506,17 @@ out:
return nlmsg_size;
}
+static size_t rtnl_mdb_nlmsg_size(const struct net_bridge_port_group *pg)
+{
+ return NLMSG_ALIGN(sizeof(struct br_port_msg)) +
+ /* MDBA_MDB */
+ nla_total_size(0) +
+ /* MDBA_MDB_ENTRY */
+ nla_total_size(0) +
+ /* Port group entry */
+ rtnl_mdb_nlmsg_pg_size(pg);
+}
+
void br_mdb_notify(struct net_device *dev,
struct net_bridge_mdb_entry *mp,
struct net_bridge_port_group *pg,
@@ -1401,3 +1411,161 @@ int br_mdb_del(struct net_device *dev, struct nlattr *tb[],
br_mdb_config_fini(&cfg);
return err;
}
+
+static const struct nla_policy br_mdbe_attrs_get_pol[MDBE_ATTR_MAX + 1] = {
+ [MDBE_ATTR_SOURCE] = NLA_POLICY_RANGE(NLA_BINARY,
+ sizeof(struct in_addr),
+ sizeof(struct in6_addr)),
+};
+
+static int br_mdb_get_parse(struct net_device *dev, struct nlattr *tb[],
+ struct br_ip *group, struct netlink_ext_ack *extack)
+{
+ struct br_mdb_entry *entry = nla_data(tb[MDBA_GET_ENTRY]);
+ struct nlattr *mdbe_attrs[MDBE_ATTR_MAX + 1];
+ int err;
+
+ if (!tb[MDBA_GET_ENTRY_ATTRS]) {
+ __mdb_entry_to_br_ip(entry, group, NULL);
+ return 0;
+ }
+
+ err = nla_parse_nested(mdbe_attrs, MDBE_ATTR_MAX,
+ tb[MDBA_GET_ENTRY_ATTRS], br_mdbe_attrs_get_pol,
+ extack);
+ if (err)
+ return err;
+
+ if (mdbe_attrs[MDBE_ATTR_SOURCE] &&
+ !is_valid_mdb_source(mdbe_attrs[MDBE_ATTR_SOURCE],
+ entry->addr.proto, extack))
+ return -EINVAL;
+
+ __mdb_entry_to_br_ip(entry, group, mdbe_attrs);
+
+ return 0;
+}
+
+static struct sk_buff *
+br_mdb_get_reply_alloc(const struct net_bridge_mdb_entry *mp)
+{
+ struct net_bridge_port_group *pg;
+ size_t nlmsg_size;
+
+ nlmsg_size = NLMSG_ALIGN(sizeof(struct br_port_msg)) +
+ /* MDBA_MDB */
+ nla_total_size(0) +
+ /* MDBA_MDB_ENTRY */
+ nla_total_size(0);
+
+ if (mp->host_joined)
+ nlmsg_size += rtnl_mdb_nlmsg_pg_size(NULL);
+
+ for (pg = mlock_dereference(mp->ports, mp->br); pg;
+ pg = mlock_dereference(pg->next, mp->br))
+ nlmsg_size += rtnl_mdb_nlmsg_pg_size(pg);
+
+ return nlmsg_new(nlmsg_size, GFP_ATOMIC);
+}
+
+static int br_mdb_get_reply_fill(struct sk_buff *skb,
+ struct net_bridge_mdb_entry *mp, u32 portid,
+ u32 seq)
+{
+ struct nlattr *mdb_nest, *mdb_entry_nest;
+ struct net_bridge_port_group *pg;
+ struct br_port_msg *bpm;
+ struct nlmsghdr *nlh;
+ int err;
+
+ nlh = nlmsg_put(skb, portid, seq, RTM_NEWMDB, sizeof(*bpm), 0);
+ if (!nlh)
+ return -EMSGSIZE;
+
+ bpm = nlmsg_data(nlh);
+ memset(bpm, 0, sizeof(*bpm));
+ bpm->family = AF_BRIDGE;
+ bpm->ifindex = mp->br->dev->ifindex;
+ mdb_nest = nla_nest_start_noflag(skb, MDBA_MDB);
+ if (!mdb_nest) {
+ err = -EMSGSIZE;
+ goto cancel;
+ }
+ mdb_entry_nest = nla_nest_start_noflag(skb, MDBA_MDB_ENTRY);
+ if (!mdb_entry_nest) {
+ err = -EMSGSIZE;
+ goto cancel;
+ }
+
+ if (mp->host_joined) {
+ err = __mdb_fill_info(skb, mp, NULL);
+ if (err)
+ goto cancel;
+ }
+
+ for (pg = mlock_dereference(mp->ports, mp->br); pg;
+ pg = mlock_dereference(pg->next, mp->br)) {
+ err = __mdb_fill_info(skb, mp, pg);
+ if (err)
+ goto cancel;
+ }
+
+ nla_nest_end(skb, mdb_entry_nest);
+ nla_nest_end(skb, mdb_nest);
+ nlmsg_end(skb, nlh);
+
+ return 0;
+
+cancel:
+ nlmsg_cancel(skb, nlh);
+ return err;
+}
+
+int br_mdb_get(struct net_device *dev, struct nlattr *tb[], u32 portid, u32 seq,
+ struct netlink_ext_ack *extack)
+{
+ struct net_bridge *br = netdev_priv(dev);
+ struct net_bridge_mdb_entry *mp;
+ struct sk_buff *skb;
+ struct br_ip group;
+ int err;
+
+ err = br_mdb_get_parse(dev, tb, &group, extack);
+ if (err)
+ return err;
+
+ /* Hold the multicast lock to ensure that the MDB entry does not change
+ * between the time the reply size is determined and when the reply is
+ * filled in.
+ */
+ spin_lock_bh(&br->multicast_lock);
+
+ mp = br_mdb_ip_get(br, &group);
+ if (!mp) {
+ NL_SET_ERR_MSG_MOD(extack, "MDB entry not found");
+ err = -ENOENT;
+ goto unlock;
+ }
+
+ skb = br_mdb_get_reply_alloc(mp);
+ if (!skb) {
+ err = -ENOMEM;
+ goto unlock;
+ }
+
+ err = br_mdb_get_reply_fill(skb, mp, portid, seq);
+ if (err) {
+ NL_SET_ERR_MSG_MOD(extack, "Failed to fill MDB get reply");
+ goto free;
+ }
+
+ spin_unlock_bh(&br->multicast_lock);
+
+ return rtnl_unicast(skb, dev_net(dev), portid);
+
+free:
+ kfree_skb(skb);
+unlock:
+ spin_unlock_bh(&br->multicast_lock);
+ return err;
+}
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 96d1fc78dd39..d7d021af1029 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -145,8 +145,9 @@ static struct net_bridge_mdb_entry *br_mdb_ip6_get(struct net_bridge *br,
}
#endif
-struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge_mcast *brmctx,
- struct sk_buff *skb, u16 vid)
+struct net_bridge_mdb_entry *
+br_mdb_entry_skb_get(struct net_bridge_mcast *brmctx, struct sk_buff *skb,
+ u16 vid)
{
struct net_bridge *br = brmctx->br;
struct br_ip ip;
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 15186247b59a..6adcb45bca75 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -294,7 +294,7 @@ int br_nf_pre_routing_finish_bridge(struct net *net, struct sock *sk, struct sk_
/* tell br_dev_xmit to continue with forwarding */
nf_bridge->bridged_dnat = 1;
/* FIXME Need to refragment */
- ret = neigh->output(neigh, skb);
+ ret = READ_ONCE(neigh->output)(neigh, skb);
}
neigh_release(neigh);
return ret;
@@ -486,11 +486,11 @@ static unsigned int br_nf_pre_routing(void *priv,
struct brnf_net *brnet;
if (unlikely(!pskb_may_pull(skb, len)))
- return NF_DROP;
+ return NF_DROP_REASON(skb, SKB_DROP_REASON_PKT_TOO_SMALL, 0);
p = br_port_get_rcu(state->in);
if (p == NULL)
- return NF_DROP;
+ return NF_DROP_REASON(skb, SKB_DROP_REASON_DEV_READY, 0);
br = p->br;
brnet = net_generic(state->net, brnf_net_id);
@@ -501,7 +501,7 @@ static unsigned int br_nf_pre_routing(void *priv,
return NF_ACCEPT;
if (!ipv6_mod_enabled()) {
pr_warn_once("Module ipv6 is disabled, so call_ip6tables is not supported.");
- return NF_DROP;
+ return NF_DROP_REASON(skb, SKB_DROP_REASON_IPV6DISABLED, 0);
}
nf_bridge_pull_encap_header_rcsum(skb);
@@ -518,12 +518,12 @@ static unsigned int br_nf_pre_routing(void *priv,
nf_bridge_pull_encap_header_rcsum(skb);
if (br_validate_ipv4(state->net, skb))
- return NF_DROP;
+ return NF_DROP_REASON(skb, SKB_DROP_REASON_IP_INHDR, 0);
if (!nf_bridge_alloc(skb))
- return NF_DROP;
+ return NF_DROP_REASON(skb, SKB_DROP_REASON_NOMEM, 0);
if (!setup_pre_routing(skb, state->net))
- return NF_DROP;
+ return NF_DROP_REASON(skb, SKB_DROP_REASON_DEV_READY, 0);
nf_bridge = nf_bridge_info_get(skb);
nf_bridge->ipv4_daddr = ip_hdr(skb)->daddr;
@@ -570,18 +570,12 @@ static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff
}
-/* This is the 'purely bridged' case. For IP, we pass the packet to
- * netfilter with indev and outdev set to the bridge device,
- * but we are still able to filter on the 'real' indev/outdev
- * because of the physdev module. For ARP, indev and outdev are the
- * bridge ports. */
-static unsigned int br_nf_forward_ip(void *priv,
- struct sk_buff *skb,
- const struct nf_hook_state *state)
+static unsigned int br_nf_forward_ip(struct sk_buff *skb,
+ const struct nf_hook_state *state,
+ u8 pf)
{
struct nf_bridge_info *nf_bridge;
struct net_device *parent;
- u_int8_t pf;
nf_bridge = nf_bridge_info_get(skb);
if (!nf_bridge)
@@ -590,24 +584,15 @@ static unsigned int br_nf_forward_ip(void *priv,
/* Need exclusive nf_bridge_info since we might have multiple
* different physoutdevs. */
if (!nf_bridge_unshare(skb))
- return NF_DROP;
+ return NF_DROP_REASON(skb, SKB_DROP_REASON_NOMEM, 0);
nf_bridge = nf_bridge_info_get(skb);
if (!nf_bridge)
- return NF_DROP;
+ return NF_DROP_REASON(skb, SKB_DROP_REASON_NOMEM, 0);
parent = bridge_parent(state->out);
if (!parent)
- return NF_DROP;
-
- 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, state->net) ||
- is_pppoe_ipv6(skb, state->net))
- pf = NFPROTO_IPV6;
- else
- return NF_ACCEPT;
+ return NF_DROP_REASON(skb, SKB_DROP_REASON_DEV_READY, 0);
nf_bridge_pull_encap_header(skb);
@@ -618,21 +603,20 @@ static unsigned int br_nf_forward_ip(void *priv,
if (pf == NFPROTO_IPV4) {
if (br_validate_ipv4(state->net, skb))
- return NF_DROP;
+ return NF_DROP_REASON(skb, SKB_DROP_REASON_IP_INHDR, 0);
IPCB(skb)->frag_max_size = nf_bridge->frag_max_size;
- }
-
- if (pf == NFPROTO_IPV6) {
+ skb->protocol = htons(ETH_P_IP);
+ } else if (pf == NFPROTO_IPV6) {
if (br_validate_ipv6(state->net, skb))
- return NF_DROP;
+ return NF_DROP_REASON(skb, SKB_DROP_REASON_IP_INHDR, 0);
IP6CB(skb)->frag_max_size = nf_bridge->frag_max_size;
+ skb->protocol = htons(ETH_P_IPV6);
+ } else {
+ WARN_ON_ONCE(1);
+ return NF_DROP;
}
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, state->net, NULL, skb,
brnf_get_logical_dev(skb, state->in, state->net),
@@ -641,8 +625,7 @@ static unsigned int br_nf_forward_ip(void *priv,
return NF_STOLEN;
}
-static unsigned int br_nf_forward_arp(void *priv,
- struct sk_buff *skb,
+static unsigned int br_nf_forward_arp(struct sk_buff *skb,
const struct nf_hook_state *state)
{
struct net_bridge_port *p;
@@ -659,14 +642,11 @@ static unsigned int br_nf_forward_arp(void *priv,
if (!brnet->call_arptables && !br_opt_get(br, BROPT_NF_CALL_ARPTABLES))
return NF_ACCEPT;
- if (!IS_ARP(skb)) {
- if (!is_vlan_arp(skb, state->net))
- return NF_ACCEPT;
+ if (is_vlan_arp(skb, state->net))
nf_bridge_pull_encap_header(skb);
- }
if (unlikely(!pskb_may_pull(skb, sizeof(struct arphdr))))
- return NF_DROP;
+ return NF_DROP_REASON(skb, SKB_DROP_REASON_PKT_TOO_SMALL, 0);
if (arp_hdr(skb)->ar_pln != 4) {
if (is_vlan_arp(skb, state->net))
@@ -680,6 +660,28 @@ static unsigned int br_nf_forward_arp(void *priv,
return NF_STOLEN;
}
+/* This is the 'purely bridged' case. For IP, we pass the packet to
+ * netfilter with indev and outdev set to the bridge device,
+ * but we are still able to filter on the 'real' indev/outdev
+ * because of the physdev module. For ARP, indev and outdev are the
+ * bridge ports.
+ */
+static unsigned int br_nf_forward(void *priv,
+ struct sk_buff *skb,
+ const struct nf_hook_state *state)
+{
+ if (IS_IP(skb) || is_vlan_ip(skb, state->net) ||
+ is_pppoe_ip(skb, state->net))
+ return br_nf_forward_ip(skb, state, NFPROTO_IPV4);
+ if (IS_IPV6(skb) || is_vlan_ipv6(skb, state->net) ||
+ is_pppoe_ipv6(skb, state->net))
+ return br_nf_forward_ip(skb, state, NFPROTO_IPV6);
+ if (IS_ARP(skb) || is_vlan_arp(skb, state->net))
+ return br_nf_forward_arp(skb, state);
+
+ return NF_ACCEPT;
+}
+
static int br_nf_push_frag_xmit(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct brnf_frag_data *data;
@@ -831,7 +833,7 @@ static unsigned int br_nf_post_routing(void *priv,
return NF_ACCEPT;
if (!realoutdev)
- return NF_DROP;
+ return NF_DROP_REASON(skb, SKB_DROP_REASON_DEV_READY, 0);
if (IS_IP(skb) || is_vlan_ip(skb, state->net) ||
is_pppoe_ip(skb, state->net))
@@ -937,13 +939,7 @@ static const struct nf_hook_ops br_nf_ops[] = {
.priority = NF_BR_PRI_BRNF,
},
{
- .hook = br_nf_forward_ip,
- .pf = NFPROTO_BRIDGE,
- .hooknum = NF_BR_FORWARD,
- .priority = NF_BR_PRI_BRNF - 1,
- },
- {
- .hook = br_nf_forward_arp,
+ .hook = br_nf_forward,
.pf = NFPROTO_BRIDGE,
.hooknum = NF_BR_FORWARD,
.priority = NF_BR_PRI_BRNF,
diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c
index 550039dfc31a..2e24a743f917 100644
--- a/net/bridge/br_netfilter_ipv6.c
+++ b/net/bridge/br_netfilter_ipv6.c
@@ -161,13 +161,13 @@ unsigned int br_nf_pre_routing_ipv6(void *priv,
struct nf_bridge_info *nf_bridge;
if (br_validate_ipv6(state->net, skb))
- return NF_DROP;
+ return NF_DROP_REASON(skb, SKB_DROP_REASON_IP_INHDR, 0);
nf_bridge = nf_bridge_alloc(skb);
if (!nf_bridge)
- return NF_DROP;
+ return NF_DROP_REASON(skb, SKB_DROP_REASON_NOMEM, 0);
if (!setup_pre_routing(skb, state->net))
- return NF_DROP;
+ return NF_DROP_REASON(skb, SKB_DROP_REASON_DEV_READY, 0);
nf_bridge = nf_bridge_info_get(skb);
nf_bridge->ipv6_daddr = ipv6_hdr(skb)->daddr;
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 10f0d33d8ccf..5ad4abfcb7ba 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -1229,6 +1229,8 @@ static size_t br_port_get_slave_size(const struct net_device *brdev,
}
static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = {
+ [IFLA_BR_UNSPEC] = { .strict_start_type =
+ IFLA_BR_FDB_N_LEARNED },
[IFLA_BR_FORWARD_DELAY] = { .type = NLA_U32 },
[IFLA_BR_HELLO_TIME] = { .type = NLA_U32 },
[IFLA_BR_MAX_AGE] = { .type = NLA_U32 },
@@ -1265,6 +1267,8 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = {
[IFLA_BR_VLAN_STATS_PER_PORT] = { .type = NLA_U8 },
[IFLA_BR_MULTI_BOOLOPT] =
NLA_POLICY_EXACT_LEN(sizeof(struct br_boolopt_multi)),
+ [IFLA_BR_FDB_N_LEARNED] = { .type = NLA_REJECT },
+ [IFLA_BR_FDB_MAX_LEARNED] = { .type = NLA_U32 },
};
static int br_changelink(struct net_device *brdev, struct nlattr *tb[],
@@ -1539,6 +1543,12 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[],
return err;
}
+ if (data[IFLA_BR_FDB_MAX_LEARNED]) {
+ u32 val = nla_get_u32(data[IFLA_BR_FDB_MAX_LEARNED]);
+
+ WRITE_ONCE(br->fdb_max_learned, val);
+ }
+
return 0;
}
@@ -1593,6 +1603,8 @@ static size_t br_get_size(const struct net_device *brdev)
nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_TOPOLOGY_CHANGE_TIMER */
nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_GC_TIMER */
nla_total_size(ETH_ALEN) + /* IFLA_BR_GROUP_ADDR */
+ nla_total_size(sizeof(u32)) + /* IFLA_BR_FDB_N_LEARNED */
+ nla_total_size(sizeof(u32)) + /* IFLA_BR_FDB_MAX_LEARNED */
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_ROUTER */
nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_SNOOPING */
@@ -1668,7 +1680,10 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev)
nla_put_u8(skb, IFLA_BR_TOPOLOGY_CHANGE_DETECTED,
br->topology_change_detected) ||
nla_put(skb, IFLA_BR_GROUP_ADDR, ETH_ALEN, br->group_addr) ||
- nla_put(skb, IFLA_BR_MULTI_BOOLOPT, sizeof(bm), &bm))
+ nla_put(skb, IFLA_BR_MULTI_BOOLOPT, sizeof(bm), &bm) ||
+ nla_put_u32(skb, IFLA_BR_FDB_N_LEARNED,
+ atomic_read(&br->fdb_n_learned)) ||
+ nla_put_u32(skb, IFLA_BR_FDB_MAX_LEARNED, br->fdb_max_learned))
return -EMSGSIZE;
#ifdef CONFIG_BRIDGE_VLAN_FILTERING
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index a1f4acfa6994..6b7f36769d03 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -274,6 +274,7 @@ enum {
BR_FDB_NOTIFY,
BR_FDB_NOTIFY_INACTIVE,
BR_FDB_LOCKED,
+ BR_FDB_DYNAMIC_LEARNED,
};
struct net_bridge_fdb_key {
@@ -555,6 +556,9 @@ struct net_bridge {
struct kobject *ifobj;
u32 auto_cnt;
+ atomic_t fdb_n_learned;
+ u32 fdb_max_learned;
+
#ifdef CONFIG_NET_SWITCHDEV
/* Counter used to make sure that hardware domains get unique
* identifiers in case a bridge spans multiple switchdev instances.
@@ -847,8 +851,7 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,
int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
struct net_device *dev, const unsigned char *addr, u16 vid,
struct netlink_ext_ack *extack);
-int br_fdb_delete_bulk(struct ndmsg *ndm, struct nlattr *tb[],
- struct net_device *dev, u16 vid,
+int br_fdb_delete_bulk(struct nlmsghdr *nlh, struct net_device *dev,
struct netlink_ext_ack *extack);
int br_fdb_add(struct ndmsg *nlh, struct nlattr *tb[], struct net_device *dev,
const unsigned char *addr, u16 vid, u16 nlh_flags,
@@ -952,8 +955,9 @@ int br_multicast_rcv(struct net_bridge_mcast **brmctx,
struct net_bridge_mcast_port **pmctx,
struct net_bridge_vlan *vlan,
struct sk_buff *skb, u16 vid);
-struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge_mcast *brmctx,
- struct sk_buff *skb, u16 vid);
+struct net_bridge_mdb_entry *
+br_mdb_entry_skb_get(struct net_bridge_mcast *brmctx, struct sk_buff *skb,
+ u16 vid);
int br_multicast_add_port(struct net_bridge_port *port);
void br_multicast_del_port(struct net_bridge_port *port);
void br_multicast_enable_port(struct net_bridge_port *port);
@@ -1018,6 +1022,8 @@ int br_mdb_del(struct net_device *dev, struct nlattr *tb[],
struct netlink_ext_ack *extack);
int br_mdb_dump(struct net_device *dev, struct sk_buff *skb,
struct netlink_callback *cb);
+int br_mdb_get(struct net_device *dev, struct nlattr *tb[], u32 portid, u32 seq,
+ struct netlink_ext_ack *extack);
void br_multicast_host_join(const struct net_bridge_mcast *brmctx,
struct net_bridge_mdb_entry *mp, bool notify);
void br_multicast_host_leave(struct net_bridge_mdb_entry *mp, bool notify);
@@ -1342,8 +1348,9 @@ static inline int br_multicast_rcv(struct net_bridge_mcast **brmctx,
return 0;
}
-static inline struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge_mcast *brmctx,
- struct sk_buff *skb, u16 vid)
+static inline struct net_bridge_mdb_entry *
+br_mdb_entry_skb_get(struct net_bridge_mcast *brmctx, struct sk_buff *skb,
+ u16 vid)
{
return NULL;
}
@@ -1427,6 +1434,13 @@ static inline int br_mdb_dump(struct net_device *dev, struct sk_buff *skb,
return 0;
}
+static inline int br_mdb_get(struct net_device *dev, struct nlattr *tb[],
+ u32 portid, u32 seq,
+ struct netlink_ext_ack *extack)
+{
+ return -EOPNOTSUPP;
+}
+
static inline int br_mdb_hash_init(struct net_bridge *br)
{
return 0;
generated by cgit v1.2.3 (git 2.0.4) at 2026-01-06 11:26:25 +0000