summaryrefslogtreecommitdiff
path: root/net/bridge
diff options
context:
space:
mode:
Diffstat (limited to 'net/bridge')
-rw-r--r--net/bridge/br.c15
-rw-r--r--net/bridge/br_device.c27
-rw-r--r--net/bridge/br_fdb.c5
-rw-r--r--net/bridge/br_input.c15
-rw-r--r--net/bridge/br_multicast.c2
-rw-r--r--net/bridge/br_netfilter_hooks.c102
-rw-r--r--net/bridge/br_netlink.c3
-rw-r--r--net/bridge/br_private.h1
-rw-r--r--net/bridge/br_vlan.c4
-rw-r--r--net/bridge/netfilter/Kconfig7
-rw-r--r--net/bridge/netfilter/Makefile2
-rw-r--r--net/bridge/netfilter/ebtables.c6
-rw-r--r--net/bridge/netfilter/nf_conntrack_bridge.c36
13 files changed, 181 insertions, 44 deletions
diff --git a/net/bridge/br.c b/net/bridge/br.c
index ac19b797dbec..2cab878e0a39 100644
--- a/net/bridge/br.c
+++ b/net/bridge/br.c
@@ -356,26 +356,21 @@ void br_opt_toggle(struct net_bridge *br, enum net_bridge_opts opt, bool on)
clear_bit(opt, &br->options);
}
-static void __net_exit br_net_exit_batch(struct list_head *net_list)
+static void __net_exit br_net_exit_batch_rtnl(struct list_head *net_list,
+ struct list_head *dev_to_kill)
{
struct net_device *dev;
struct net *net;
- LIST_HEAD(list);
-
- rtnl_lock();
+ ASSERT_RTNL();
list_for_each_entry(net, net_list, exit_list)
for_each_netdev(net, dev)
if (netif_is_bridge_master(dev))
- br_dev_delete(dev, &list);
-
- unregister_netdevice_many(&list);
-
- rtnl_unlock();
+ br_dev_delete(dev, dev_to_kill);
}
static struct pernet_operations br_net_ops = {
- .exit_batch = br_net_exit_batch,
+ .exit_batch_rtnl = br_net_exit_batch_rtnl,
};
static const struct stp_proto br_stp_proto = {
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 65cee0ad3c1b..c366ccc8b3db 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -108,38 +108,23 @@ out:
return NETDEV_TX_OK;
}
-static struct lock_class_key bridge_netdev_addr_lock_key;
-
-static void br_set_lockdep_class(struct net_device *dev)
-{
- lockdep_set_class(&dev->addr_list_lock, &bridge_netdev_addr_lock_key);
-}
-
static int br_dev_init(struct net_device *dev)
{
struct net_bridge *br = netdev_priv(dev);
int err;
- dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
- if (!dev->tstats)
- return -ENOMEM;
-
err = br_fdb_hash_init(br);
- if (err) {
- free_percpu(dev->tstats);
+ if (err)
return err;
- }
err = br_mdb_hash_init(br);
if (err) {
- free_percpu(dev->tstats);
br_fdb_hash_fini(br);
return err;
}
err = br_vlan_init(br);
if (err) {
- free_percpu(dev->tstats);
br_mdb_hash_fini(br);
br_fdb_hash_fini(br);
return err;
@@ -147,14 +132,14 @@ static int br_dev_init(struct net_device *dev)
err = br_multicast_init_stats(br);
if (err) {
- free_percpu(dev->tstats);
br_vlan_flush(br);
br_mdb_hash_fini(br);
br_fdb_hash_fini(br);
+ return err;
}
- br_set_lockdep_class(dev);
- return err;
+ netdev_lockdep_set_classes(dev);
+ return 0;
}
static void br_dev_uninit(struct net_device *dev)
@@ -166,7 +151,6 @@ static void br_dev_uninit(struct net_device *dev)
br_vlan_flush(br);
br_mdb_hash_fini(br);
br_fdb_hash_fini(br);
- free_percpu(dev->tstats);
}
static int br_dev_open(struct net_device *dev)
@@ -481,7 +465,7 @@ static const struct net_device_ops br_netdev_ops = {
.ndo_fill_forward_path = br_fill_forward_path,
};
-static struct device_type br_type = {
+static const struct device_type br_type = {
.name = "bridge",
};
@@ -503,6 +487,7 @@ void br_dev_setup(struct net_device *dev)
dev->hw_features = COMMON_FEATURES | NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_STAG_TX;
dev->vlan_features = COMMON_FEATURES;
+ dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS;
br->dev = dev;
spin_lock_init(&br->lock);
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index c622de5eccd0..c77591e63841 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -35,10 +35,7 @@ static struct kmem_cache *br_fdb_cache __read_mostly;
int __init br_fdb_init(void)
{
- br_fdb_cache = kmem_cache_create("bridge_fdb_cache",
- sizeof(struct net_bridge_fdb_entry),
- 0,
- SLAB_HWCACHE_ALIGN, NULL);
+ br_fdb_cache = KMEM_CACHE(net_bridge_fdb_entry, SLAB_HWCACHE_ALIGN);
if (!br_fdb_cache)
return -ENOMEM;
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index f21097e73482..ceaa5a89b947 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -30,7 +30,7 @@ br_netif_receive_skb(struct net *net, struct sock *sk, struct sk_buff *skb)
return netif_receive_skb(skb);
}
-static int br_pass_frame_up(struct sk_buff *skb)
+static int br_pass_frame_up(struct sk_buff *skb, bool promisc)
{
struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev;
struct net_bridge *br = netdev_priv(brdev);
@@ -65,6 +65,8 @@ static int br_pass_frame_up(struct sk_buff *skb)
br_multicast_count(br, NULL, skb, br_multicast_igmp_type(skb),
BR_MCAST_DIR_TX);
+ BR_INPUT_SKB_CB(skb)->promisc = promisc;
+
return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN,
dev_net(indev), NULL, skb, indev, NULL,
br_netif_receive_skb);
@@ -82,6 +84,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
struct net_bridge_mcast *brmctx;
struct net_bridge_vlan *vlan;
struct net_bridge *br;
+ bool promisc;
u16 vid = 0;
u8 state;
@@ -137,7 +140,9 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
if (p->flags & BR_LEARNING)
br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, 0);
- local_rcv = !!(br->dev->flags & IFF_PROMISC);
+ promisc = !!(br->dev->flags & IFF_PROMISC);
+ local_rcv = promisc;
+
if (is_multicast_ether_addr(eth_hdr(skb)->h_dest)) {
/* by definition the broadcast is also a multicast address */
if (is_broadcast_ether_addr(eth_hdr(skb)->h_dest)) {
@@ -200,7 +205,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
unsigned long now = jiffies;
if (test_bit(BR_FDB_LOCAL, &dst->flags))
- return br_pass_frame_up(skb);
+ return br_pass_frame_up(skb, false);
if (now != dst->used)
dst->used = now;
@@ -213,7 +218,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
}
if (local_rcv)
- return br_pass_frame_up(skb);
+ return br_pass_frame_up(skb, promisc);
out:
return 0;
@@ -386,6 +391,8 @@ static rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
goto forward;
}
+ BR_INPUT_SKB_CB(skb)->promisc = false;
+
/* The else clause should be hit when nf_hook():
* - returns < 0 (drop/error)
* - returns = 0 (stolen/nf_queue)
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 2d7b73242958..9a1cb5079a7a 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -5053,7 +5053,7 @@ void br_multicast_uninit_stats(struct net_bridge *br)
free_percpu(br->mcast_stats);
}
-/* noinline for https://bugs.llvm.org/show_bug.cgi?id=45802#c9 */
+/* noinline for https://llvm.org/pr45802#c9 */
static noinline_for_stack void mcast_stats_add_dir(u64 *dst, u64 *src)
{
dst[BR_MCAST_DIR_RX] += src[BR_MCAST_DIR_RX];
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index ed1720890757..22e35623c148 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -43,6 +43,10 @@
#include <linux/sysctl.h>
#endif
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+#include <net/netfilter/nf_conntrack_core.h>
+#endif
+
static unsigned int brnf_net_id __read_mostly;
struct brnf_net {
@@ -553,6 +557,96 @@ static unsigned int br_nf_pre_routing(void *priv,
return NF_STOLEN;
}
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+/* conntracks' nf_confirm logic cannot handle cloned skbs referencing
+ * the same nf_conn entry, which will happen for multicast (broadcast)
+ * Frames on bridges.
+ *
+ * Example:
+ * macvlan0
+ * br0
+ * ethX ethY
+ *
+ * ethX (or Y) receives multicast or broadcast packet containing
+ * an IP packet, not yet in conntrack table.
+ *
+ * 1. skb passes through bridge and fake-ip (br_netfilter)Prerouting.
+ * -> skb->_nfct now references a unconfirmed entry
+ * 2. skb is broad/mcast packet. bridge now passes clones out on each bridge
+ * interface.
+ * 3. skb gets passed up the stack.
+ * 4. In macvlan case, macvlan driver retains clone(s) of the mcast skb
+ * and schedules a work queue to send them out on the lower devices.
+ *
+ * The clone skb->_nfct is not a copy, it is the same entry as the
+ * original skb. The macvlan rx handler then returns RX_HANDLER_PASS.
+ * 5. Normal conntrack hooks (in NF_INET_LOCAL_IN) confirm the orig skb.
+ *
+ * The Macvlan broadcast worker and normal confirm path will race.
+ *
+ * This race will not happen if step 2 already confirmed a clone. In that
+ * case later steps perform skb_clone() with skb->_nfct already confirmed (in
+ * hash table). This works fine.
+ *
+ * But such confirmation won't happen when eb/ip/nftables rules dropped the
+ * packets before they reached the nf_confirm step in postrouting.
+ *
+ * Work around this problem by explicit confirmation of the entry at
+ * LOCAL_IN time, before upper layer has a chance to clone the unconfirmed
+ * entry.
+ *
+ */
+static unsigned int br_nf_local_in(void *priv,
+ struct sk_buff *skb,
+ const struct nf_hook_state *state)
+{
+ bool promisc = BR_INPUT_SKB_CB(skb)->promisc;
+ struct nf_conntrack *nfct = skb_nfct(skb);
+ const struct nf_ct_hook *ct_hook;
+ struct nf_conn *ct;
+ int ret;
+
+ if (promisc) {
+ nf_reset_ct(skb);
+ return NF_ACCEPT;
+ }
+
+ if (!nfct || skb->pkt_type == PACKET_HOST)
+ return NF_ACCEPT;
+
+ ct = container_of(nfct, struct nf_conn, ct_general);
+ if (likely(nf_ct_is_confirmed(ct)))
+ return NF_ACCEPT;
+
+ WARN_ON_ONCE(skb_shared(skb));
+ WARN_ON_ONCE(refcount_read(&nfct->use) != 1);
+
+ /* We can't call nf_confirm here, it would create a dependency
+ * on nf_conntrack module.
+ */
+ ct_hook = rcu_dereference(nf_ct_hook);
+ if (!ct_hook) {
+ skb->_nfct = 0ul;
+ nf_conntrack_put(nfct);
+ return NF_ACCEPT;
+ }
+
+ nf_bridge_pull_encap_header(skb);
+ ret = ct_hook->confirm(skb);
+ switch (ret & NF_VERDICT_MASK) {
+ case NF_STOLEN:
+ return NF_STOLEN;
+ default:
+ nf_bridge_push_encap_header(skb);
+ break;
+ }
+
+ ct = container_of(nfct, struct nf_conn, ct_general);
+ WARN_ON_ONCE(!nf_ct_is_confirmed(ct));
+
+ return ret;
+}
+#endif
/* PF_BRIDGE/FORWARD *************************************************/
static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
@@ -964,6 +1058,14 @@ static const struct nf_hook_ops br_nf_ops[] = {
.hooknum = NF_BR_PRE_ROUTING,
.priority = NF_BR_PRI_BRNF,
},
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+ {
+ .hook = br_nf_local_in,
+ .pf = NFPROTO_BRIDGE,
+ .hooknum = NF_BR_LOCAL_IN,
+ .priority = NF_BR_PRI_LAST,
+ },
+#endif
{
.hook = br_nf_forward,
.pf = NFPROTO_BRIDGE,
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 5ad4abfcb7ba..2cf4fc756263 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -455,7 +455,8 @@ static int br_fill_ifinfo(struct sk_buff *skb,
u32 filter_mask, const struct net_device *dev,
bool getlink)
{
- u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN;
+ u8 operstate = netif_running(dev) ? READ_ONCE(dev->operstate) :
+ IF_OPER_DOWN;
struct nlattr *af = NULL;
struct net_bridge *br;
struct ifinfomsg *hdr;
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 86ea5e6689b5..d4bedc87b1d8 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -589,6 +589,7 @@ struct br_input_skb_cb {
#endif
u8 proxyarp_replied:1;
u8 src_port_isolated:1;
+ u8 promisc:1;
#ifdef CONFIG_BRIDGE_VLAN_FILTERING
u8 vlan_filtered:1;
#endif
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 15f44d026e75..9c2fffb827ab 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -841,7 +841,7 @@ void br_vlan_flush(struct net_bridge *br)
vg = br_vlan_group(br);
__vlan_flush(br, NULL, vg);
RCU_INIT_POINTER(br->vlgrp, NULL);
- synchronize_rcu();
+ synchronize_net();
__vlan_group_free(vg);
}
@@ -1372,7 +1372,7 @@ void nbp_vlan_flush(struct net_bridge_port *port)
vg = nbp_vlan_group(port);
__vlan_flush(port->br, port, vg);
RCU_INIT_POINTER(port->vlgrp, NULL);
- synchronize_rcu();
+ synchronize_net();
__vlan_group_free(vg);
}
diff --git a/net/bridge/netfilter/Kconfig b/net/bridge/netfilter/Kconfig
index 7f304a19ac1b..104c0125e32e 100644
--- a/net/bridge/netfilter/Kconfig
+++ b/net/bridge/netfilter/Kconfig
@@ -39,6 +39,10 @@ config NF_CONNTRACK_BRIDGE
To compile it as a module, choose M here. If unsure, say N.
+# old sockopt interface and eval loop
+config BRIDGE_NF_EBTABLES_LEGACY
+ tristate
+
menuconfig BRIDGE_NF_EBTABLES
tristate "Ethernet Bridge tables (ebtables) support"
depends on BRIDGE && NETFILTER && NETFILTER_XTABLES
@@ -55,6 +59,7 @@ if BRIDGE_NF_EBTABLES
#
config BRIDGE_EBT_BROUTE
tristate "ebt: broute table support"
+ select BRIDGE_NF_EBTABLES_LEGACY
help
The ebtables broute table is used to define rules that decide between
bridging and routing frames, giving Linux the functionality of a
@@ -65,6 +70,7 @@ config BRIDGE_EBT_BROUTE
config BRIDGE_EBT_T_FILTER
tristate "ebt: filter table support"
+ select BRIDGE_NF_EBTABLES_LEGACY
help
The ebtables filter table is used to define frame filtering rules at
local input, forwarding and local output. See the man page for
@@ -74,6 +80,7 @@ config BRIDGE_EBT_T_FILTER
config BRIDGE_EBT_T_NAT
tristate "ebt: nat table support"
+ select BRIDGE_NF_EBTABLES_LEGACY
help
The ebtables nat table is used to define rules that alter the MAC
source address (MAC SNAT) or the MAC destination address (MAC DNAT).
diff --git a/net/bridge/netfilter/Makefile b/net/bridge/netfilter/Makefile
index 1c9ce49ab651..b9a1303da977 100644
--- a/net/bridge/netfilter/Makefile
+++ b/net/bridge/netfilter/Makefile
@@ -9,7 +9,7 @@ obj-$(CONFIG_NFT_BRIDGE_REJECT) += nft_reject_bridge.o
# connection tracking
obj-$(CONFIG_NF_CONNTRACK_BRIDGE) += nf_conntrack_bridge.o
-obj-$(CONFIG_BRIDGE_NF_EBTABLES) += ebtables.o
+obj-$(CONFIG_BRIDGE_NF_EBTABLES_LEGACY) += ebtables.o
# tables
obj-$(CONFIG_BRIDGE_EBT_BROUTE) += ebtable_broute.o
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 99d82676f780..cbd0e3586c3f 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -1111,6 +1111,8 @@ static int do_replace(struct net *net, sockptr_t arg, unsigned int len)
struct ebt_table_info *newinfo;
struct ebt_replace tmp;
+ if (len < sizeof(tmp))
+ return -EINVAL;
if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0)
return -EFAULT;
@@ -1423,6 +1425,8 @@ static int update_counters(struct net *net, sockptr_t arg, unsigned int len)
{
struct ebt_replace hlp;
+ if (len < sizeof(hlp))
+ return -EINVAL;
if (copy_from_sockptr(&hlp, arg, sizeof(hlp)))
return -EFAULT;
@@ -2352,6 +2356,8 @@ static int compat_update_counters(struct net *net, sockptr_t arg,
{
struct compat_ebt_replace hlp;
+ if (len < sizeof(hlp))
+ return -EINVAL;
if (copy_from_sockptr(&hlp, arg, sizeof(hlp)))
return -EFAULT;
diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c
index abb090f94ed2..c3c51b9a6826 100644
--- a/net/bridge/netfilter/nf_conntrack_bridge.c
+++ b/net/bridge/netfilter/nf_conntrack_bridge.c
@@ -291,6 +291,36 @@ static unsigned int nf_ct_bridge_pre(void *priv, struct sk_buff *skb,
return nf_conntrack_in(skb, &bridge_state);
}
+static unsigned int nf_ct_bridge_in(void *priv, struct sk_buff *skb,
+ const struct nf_hook_state *state)
+{
+ bool promisc = BR_INPUT_SKB_CB(skb)->promisc;
+ struct nf_conntrack *nfct = skb_nfct(skb);
+ struct nf_conn *ct;
+
+ if (promisc) {
+ nf_reset_ct(skb);
+ return NF_ACCEPT;
+ }
+
+ if (!nfct || skb->pkt_type == PACKET_HOST)
+ return NF_ACCEPT;
+
+ /* nf_conntrack_confirm() cannot handle concurrent clones,
+ * this happens for broad/multicast frames with e.g. macvlan on top
+ * of the bridge device.
+ */
+ ct = container_of(nfct, struct nf_conn, ct_general);
+ if (nf_ct_is_confirmed(ct) || nf_ct_is_template(ct))
+ return NF_ACCEPT;
+
+ /* let inet prerouting call conntrack again */
+ skb->_nfct = 0;
+ nf_ct_put(ct);
+
+ return NF_ACCEPT;
+}
+
static void nf_ct_bridge_frag_save(struct sk_buff *skb,
struct nf_bridge_frag_data *data)
{
@@ -386,6 +416,12 @@ static struct nf_hook_ops nf_ct_bridge_hook_ops[] __read_mostly = {
.priority = NF_IP_PRI_CONNTRACK,
},
{
+ .hook = nf_ct_bridge_in,
+ .pf = NFPROTO_BRIDGE,
+ .hooknum = NF_BR_LOCAL_IN,
+ .priority = NF_IP_PRI_CONNTRACK_CONFIRM,
+ },
+ {
.hook = nf_ct_bridge_post,
.pf = NFPROTO_BRIDGE,
.hooknum = NF_BR_POST_ROUTING,
generated by cgit (git 2.34.1) at 2025-04-19 02:08:32 +0000