[SRU][Vivid][PATCH v2 1/4] netfilter: bridge: don't use nf_bridge_info data to store mac header

[Jay Vosburgh]

From: Florian Westphal <fw at strlen.de>

BugLink: https://bugs.launchpad.net/nova/+bug/1463911

br_netfilter maintains an extra state, nf_bridge_info, which is attached
to skb via skb->nf_bridge pointer.

Amongst other things we use skb->nf_bridge->data to store the original
mac header for every processed skb.

This is required for ip refragmentation when using conntrack
on top of bridge, because ip_fragment doesn't copy it from original skb.

However there is no need anymore to do this unconditionally.

Move this to the one place where its needed -- when br_netfilter calls
ip_fragment().

Also switch to percpu storage for this so we can handle fragmenting
without accessing nf_bridge meta data.

Only user left is neigh resolution when DNAT is detected, to hold
the original source mac address (neigh resolution builds new mac header
using bridge mac), so rename ->data and reduce its size to whats needed.

Signed-off-by: Florian Westphal <fw at strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo at netfilter.org>
(backported from commit e70deecbf8e1562cac0b19f23848919e2f5d65aa)
Signed-off-by: Jay Vosburgh <jay.vosburgh at canonical.com>
---
 net/bridge/br_netfilter.c | 49 +++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 47 insertions(+), 2 deletions(-)

diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index ba2bd0a9a285..ca3ef0e777d9 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -112,6 +112,19 @@ static inline __be16 pppoe_proto(const struct sk_buff *skb)
 	 pppoe_proto(skb) == htons(PPP_IPV6) && \
 	 brnf_filter_pppoe_tagged)
 
+/* largest possible L2 header, see br_nf_dev_queue_xmit() */
+#define NF_BRIDGE_MAX_MAC_HEADER_LENGTH (PPPOE_SES_HLEN + ETH_HLEN)
+
+#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4)
+struct brnf_frag_data {
+	char mac[NF_BRIDGE_MAX_MAC_HEADER_LENGTH];
+	u8 encap_size;
+	u8 size;
+};
+
+static DEFINE_PER_CPU(struct brnf_frag_data, brnf_frag_data_storage);
+#endif
+
 static inline struct rtable *bridge_parent_rtable(const struct net_device *dev)
 {
 	struct net_bridge_port *port;
@@ -777,6 +790,25 @@ static unsigned int br_nf_forward_arp(const struct nf_hook_ops *ops,
 }
 
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4)
+static int br_nf_push_frag_xmit(struct sk_buff *skb)
+{
+	struct brnf_frag_data *data;
+	int err;
+
+	data = this_cpu_ptr(&brnf_frag_data_storage);
+	err = skb_cow_head(skb, data->size);
+
+	if (err) {
+		kfree_skb(skb);
+		return 0;
+	}
+
+	skb_copy_to_linear_data_offset(skb, -data->size, data->mac, data->size);
+	__skb_push(skb, data->encap_size);
+
+	return br_dev_queue_push_xmit(skb);
+}
+
 static int br_nf_dev_queue_xmit(struct sk_buff *skb)
 {
 	int ret;
@@ -788,14 +820,27 @@ static int br_nf_dev_queue_xmit(struct sk_buff *skb)
 	if (skb->protocol == htons(ETH_P_IP) &&
 	    skb->len + nf_bridge_mtu_reduction(skb) > skb->dev->mtu &&
 	    !skb_is_gso(skb)) {
+		struct brnf_frag_data *data;
+
 		frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size;
 		if (br_parse_ip_options(skb))
 			/* Drop invalid packet */
 			return NF_DROP;
 		IPCB(skb)->frag_max_size = frag_max_size;
-		ret = ip_fragment(skb, br_dev_queue_push_xmit);
-	} else
+
+		nf_bridge_update_protocol(skb);
+
+		data = this_cpu_ptr(&brnf_frag_data_storage);
+		data->encap_size = nf_bridge_encap_header_len(skb);
+		data->size = ETH_HLEN + data->encap_size;
+
+		skb_copy_from_linear_data_offset(skb, -data->size, data->mac,
+						 data->size);
+
+		ret = ip_fragment(skb, br_nf_push_frag_xmit);
+	} else {
 		ret = br_dev_queue_push_xmit(skb);
+	}
 
 	return ret;
 }
-- 
1.9.1