[PATCH nf v3] netfilter: disable br_netfilter in user namespaces

[Florian Westphal <fw@strlen.de>]

br_netfilter has way too many bugs, schedule for removal and disable
the feature in user namespaces.

In particular, we get more and more gadgets to have bridge ports escape
rcu_read_lock() protection, then underlying device gets reconfigured
(macvlan or something else), then reinject into network stack causes
crash because net_device is assumed to still have bridge rx data
associated with it.

br_netfilter is an ancient kludge that emulates ip stack from within the
bridge and then calls into ipv4/ipv6 netfilter hooks to have bridged
frames processed via iptables/ip6tables by setting the 'call-iptables'
sysctls to 1. It is NOT related to ebtables or nftables 'bridge' family
at all.

Note that in addition to call-iptables, sysctls, the bridge also exposes
call-iptables per bridge device via netlink and sysfs
('BROPT_NF_CALL_IPTABLES') toggles.

Those are still available, the brnet structure is scoped to br_netfilter;
exposing it bridge-wide is a big no-no.

This relies on brnf_device_event() no longer registering the base
br_netfilter hooks, so while BROPT_NF_CALL_IPTABLES can be set, it
has no effect because the hooks that evaluate this feature bit
are never registered.

brnf_init_net can no longer depend on CONFIG_SYSCTL, else such builds
never disable support in user namespaces.

Cc: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 v3: also update Documentation, correct changelog: toggle is
 per bridge device, not per bridge port (Nik)

 Documentation/networking/bridge.rst |  5 +++--
 net/bridge/br_netfilter_hooks.c     | 33 ++++++++++++++++++++---------
 2 files changed, 26 insertions(+), 12 deletions(-)

diff --git a/Documentation/networking/bridge.rst b/Documentation/networking/bridge.rst
index c1e6ea52c9e5..dded1a6edd60 100644
--- a/Documentation/networking/bridge.rst
+++ b/Documentation/networking/bridge.rst
@@ -277,8 +277,9 @@ Netfilter
 =========
 
 The bridge netfilter module is a legacy feature that allows to filter bridged
-packets with iptables and ip6tables. Its use is discouraged. Users should
-consider using nftables for packet filtering.
+packets with iptables and ip6tables. This feature is scheduled for removal and
+not available in user namespaces. Consider using nftables for packet filtering
+instead.
 
 The older ebtables tool is more feature-limited compared to nftables, but
 just like nftables it doesn't need this module either to function.
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 0a394e5f4391..e15355ff215a 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -54,6 +54,7 @@ static unsigned int brnf_net_id __read_mostly;
 
 struct brnf_net {
 	bool enabled;
+	bool in_userns;
 
 #ifdef CONFIG_SYSCTL
 	struct ctl_table_header *ctl_hdr;
@@ -1100,7 +1101,7 @@ static int brnf_device_event(struct notifier_block *unused, unsigned long event,
 
 	net = dev_net(dev);
 	brnet = net_generic(net, brnf_net_id);
-	if (brnet->enabled)
+	if (brnet->enabled || brnet->in_userns)
 		return NOTIFY_OK;
 
 	ret = nf_register_net_hooks(net, br_nf_ops, ARRAY_SIZE(br_nf_ops));
@@ -1229,9 +1230,11 @@ static inline void br_netfilter_sysctl_default(struct brnf_net *brnf)
 	brnf->filter_pppoe_tagged = 0;
 	brnf->pass_vlan_indev = 0;
 }
+#endif
 
 static int br_netfilter_sysctl_init_net(struct net *net)
 {
+#ifdef CONFIG_SYSCTL
 	struct ctl_table *table = brnf_table;
 	struct brnf_net *brnet;
 
@@ -1259,25 +1262,39 @@ static int br_netfilter_sysctl_init_net(struct net *net)
 
 		return -ENOMEM;
 	}
-
+#endif
 	return 0;
 }
 
 static void br_netfilter_sysctl_exit_net(struct net *net,
 					 struct brnf_net *brnet)
 {
-	const struct ctl_table *table = brnet->ctl_hdr->ctl_table_arg;
+#ifdef CONFIG_SYSCTL
+	struct ctl_table_header *header = brnet->ctl_hdr;
+	const struct ctl_table *table;
 
-	unregister_net_sysctl_table(brnet->ctl_hdr);
+	if (!header)
+		return;
+
+	table = header->ctl_table_arg;
+	unregister_net_sysctl_table(header);
 	if (!net_eq(net, &init_net))
 		kfree(table);
+#endif
 }
 
 static int __net_init brnf_init_net(struct net *net)
 {
+	if (net->user_ns != &init_user_ns) {
+		struct brnf_net *brnet = net_generic(net, brnf_net_id);
+
+		brnet->in_userns = true;
+		pr_warn_once("br_netfilter no longer supported in user namespaces\n");
+		return 0;
+	}
+
 	return br_netfilter_sysctl_init_net(net);
 }
-#endif
 
 static void __net_exit brnf_exit_net(struct net *net)
 {
@@ -1289,15 +1306,11 @@ static void __net_exit brnf_exit_net(struct net *net)
 		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),
@@ -1318,7 +1331,7 @@ static int __init br_netfilter_init(void)
 	}
 
 	RCU_INIT_POINTER(nf_br_ops, &br_ops);
-	printk(KERN_NOTICE "Bridge firewalling registered\n");
+	pr_warn("br_netfilter is slated for removal in 2027.\n");
 	return 0;
 }
 
-- 
2.55.0