summaryrefslogtreecommitdiff
path: root/net/bridge
diff options
context:
space:
mode:
authorJakub Kicinski <kuba@kernel.org>2024-02-29 14:17:54 -0800
committerJakub Kicinski <kuba@kernel.org>2024-02-29 14:24:56 -0800
commit65f5dd4f02a89df429b8212b4c2f3ada6c4f3fc1 (patch)
tree4c201974fa7e35e99c530ab3d0429dc894d64cf3 /net/bridge
parent489645d3f1332f65a9337cb31c0ee12a1259a484 (diff)
parent87adedeba51a822533649b143232418b9e26d08b (diff)
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Cross-merge networking fixes after downstream PR. Conflicts: net/mptcp/protocol.c adf1bb78dab5 ("mptcp: fix snd_wnd initialization for passive socket") 9426ce476a70 ("mptcp: annotate lockless access for RX path fields") https://lore.kernel.org/all/20240228103048.19255709@canb.auug.org.au/ Adjacent changes: drivers/dpll/dpll_core.c 0d60d8df6f49 ("dpll: rely on rcu for netdev_dpll_pin()") e7f8df0e81bf ("dpll: move xa_erase() call in to match dpll_pin_alloc() error path order") drivers/net/veth.c 1ce7d306ea63 ("veth: try harder when allocating queue memory") 0bef512012b1 ("net: add netdev_lockdep_set_classes() to virtual drivers") drivers/net/wireless/intel/iwlwifi/mvm/d3.c 8c9bef26e98b ("wifi: iwlwifi: mvm: d3: implement suspend with MLO") 78f65fbf421a ("wifi: iwlwifi: mvm: ensure offloading TID queue exists") net/wireless/nl80211.c f78c1375339a ("wifi: nl80211: reject iftype change with mesh ID change") 414532d8aa89 ("wifi: cfg80211: use IEEE80211_MAX_MESH_ID_LEN appropriately") Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'net/bridge')
-rw-r--r--net/bridge/br_netfilter_hooks.c96
-rw-r--r--net/bridge/netfilter/nf_conntrack_bridge.c30
2 files changed, 126 insertions, 0 deletions
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index ed1720890757..35e10c5a766d 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 +557,90 @@ 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)
+{
+ struct nf_conntrack *nfct = skb_nfct(skb);
+ const struct nf_ct_hook *ct_hook;
+ struct nf_conn *ct;
+ int ret;
+
+ 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 +1052,14 @@ 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/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c
index abb090f94ed2..6f877e31709b 100644
--- a/net/bridge/netfilter/nf_conntrack_bridge.c
+++ b/net/bridge/netfilter/nf_conntrack_bridge.c
@@ -291,6 +291,30 @@ 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)
+{
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn *ct;
+
+ if (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 = nf_ct_get(skb, &ctinfo);
+ if (!ct || 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 +410,12 @@ 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,