[PATCH] bridge: netfilter: work around shared nfct struct

[Florian Westphal <fw@strlen.de>]

When incoking iptables hooks from bridge netfilter, the assumption
that non-confirmed skb->nfct is never shared does no longer hold,
as bridge code clones skbs when e.g. forwarding packets to multiple
bridge ports.

When NFQUEUE is used, we can BUG because nf_nat_setup_info can be
invoked simultaneously for the same conntrack:

[ 3196.798768] kernel BUG at net/ipv4/netfilter/nf_nat_core.c:300!
[..]
[ 3196.798768]  [<ffffffff8120d73e>] ? nf_hook_slow+0x21a/0x282
[ 3196.798768]  [<ffffffffa03207e4>] ? br_handle_frame_finish+0x0/0x13b [bridge]
[ 3196.798768]  [<ffffffffa02a61a5>] ? alloc_null_binding+0x47/0x4c [iptable_nat]
[ 3196.798768]  [<ffffffffa02a64eb>] ? nf_nat_fn+0x193/0x1fb [iptable_nat]
[ 3196.798768]  [<ffffffff8120d4c5>] ? nf_iterate+0x40/0x9f
[ 3196.798768]  [<ffffffff8120d73e>] ? nf_hook_slow+0x21a/0x282
[ 3196.798768]  [<ffffffff81213c94>] ? ip_local_deliver_finish+0x0/0x1f1
[ 3196.798768]  [<ffffffff81213c94>] ? ip_local_deliver_finish+0x0/0x1f1
[ 3196.798768]  [<ffffffff8120d73e>] ? nf_hook_slow+0x21a/0x282
[ 3196.798768]  [<ffffffff8121369c>] ? ip_rcv_finish+0x0/0x340
[ 3196.798768]  [<ffffffff81213ed7>] ? ip_local_deliver+0x52/0x6c
[ 3196.798768]  [<ffffffff812139c2>] ? ip_rcv_finish+0x326/0x340
[ 3196.798768]  [<ffffffff81213c4f>] ? ip_rcv+0x273/0x2b8
[ 3196.798768]  [<ffffffff811f1384>] ? process_backlog+0x8d/0xc6
[ 3196.798768]  [<ffffffff811f2f85>] ? net_rx_action+0xa2/0x1cf
[ 3196.798768]  [<ffffffff8103d3c2>] ? __do_softirq+0x8b/0x10b
[ 3196.798768]  [<ffffffff8100c9dc>] ? call_softirq+0x1c/0x28
[ 3196.798768]  [<ffffffff8100dd15>] ? do_softirq+0x31/0x66
[ 3196.798768]  [<ffffffff8103d267>] ? irq_exit+0x36/0x78
[ 3196.798768]  [<ffffffff8100d41a>] ? do_IRQ+0xa0/0xb6
[ 3196.798768]  [<ffffffff8100c253>] ? ret_from_intr+0x0/0xa
[..]
[ 3196.798768] Code: be 2b 01 00 00 48 c7 c7 e8 cd 29 a0 e8 e8 d7 d9 e0 45 85 ff 49 8b 45 78 75 06 48 c1 e8 07 eb 04 48 c1 e8 08 83 e0 01 85 c0 74 04 <0f> 0b eb fe 49 8d 75 50 48 8d bc 24 80 00 00 00 e8 83 38 f7 ff
[ 3196.798768] RIP  [<ffffffffa029b68f>] nf_nat_setup_info+0x8a/0x564 [nf_nat]
[ 3196.798768]  RSP <ffff880001603bf0>

Fix this by changing ->nfct of all clones to untracked.

This should be OK, because if we do a full copy of ->nfct we'd
end up trying to confirm the same tuples multiple times, which results in
NF_DROP for the cloned skbs.

Also, we only need to do this if the conntrack is unconfirmed.

Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/bridge/br_netfilter.c |   34 ++++++++++++++++++++++++++++++++++
 1 files changed, 34 insertions(+), 0 deletions(-)

 I have one alternate patch that changes nf_nat_setup_info
 to detect conflicts by forcing serialization via ct->lock spinlock.

 But it is silly to do this for the sake of bridge netfilter only...

 Any other ideas?
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index 3fa1231..7d47f34 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -42,6 +42,10 @@
 #include <linux/sysctl.h>
 #endif
 
+#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+#include <net/netfilter/nf_conntrack.h>
+#endif
+
 #define skb_origaddr(skb)	 (((struct bridge_skb_cb *) \
 				 (skb->nf_bridge->data))->daddr.ipv4)
 #define store_orig_dstaddr(skb)	 (skb_origaddr(skb) = ip_hdr(skb)->daddr)
@@ -158,10 +162,40 @@ static inline struct nf_bridge_info *nf_bridge_alloc(struct sk_buff *skb)
 	return skb->nf_bridge;
 }
 
+
+/* conntrack assumes exclusive ownership of skb->nfct
+ * if conntrack has not yet been confirmed.
+ *
+ * Without this, we may BUG because we might try to set up
+ * NAT bindings for the same conntrack struct simultaneously.
+ *
+ * Work around this by forcing untracked state.
+ */
+static inline void nf_bridge_unshare_nfct(struct sk_buff *skb)
+{
+#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+	struct nf_conn *ct, *ct_orig = (void *) skb->nfct;
+
+	if (!ct_orig || nf_ct_is_untracked(ct_orig))
+		return;
+
+	if (likely(nf_ct_is_confirmed(ct_orig)) ||
+	    atomic_read(&ct_orig->ct_general.use) == 1)
+		return;
+
+	ct = nf_ct_untracked_get();
+	atomic_inc(&ct->ct_general.use);
+	nf_conntrack_put(skb->nfct);
+	skb->nfct = &ct->ct_general;
+#endif
+}
+
 static inline struct nf_bridge_info *nf_bridge_unshare(struct sk_buff *skb)
 {
 	struct nf_bridge_info *nf_bridge = skb->nf_bridge;
 
+	nf_bridge_unshare_nfct(skb);
+
 	if (atomic_read(&nf_bridge->use) > 1) {
 		struct nf_bridge_info *tmp = nf_bridge_alloc(skb);
 
-- 
1.7.3.4