set fake_rtable's dst to NULL to avoid kernel Oops

bridge: set fake_rtable's dst to NULL to avoid kernel Oops

when bridge is deleted before tap/vif device's delete, kernel may
encounter an oops because of NULL reference to fake_rtable's dst.
Set fake_rtable's dst to NULL before sending packets out can solve
this problem.

v4 reformat, change br_drop_fake_rtable(skb) to {}

v3 enrich commit header

v2 introducing new flag DST_FAKE_RTABLE to dst_entry struct.

[ Use "do { } while (0)" for nop br_drop_fake_rtable()
  implementation -DaveM ]

Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Peter Huang <peter.huangpeng@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 13 insertions, 6 deletions

diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h
index 0ddd161f3b0..31d2844e657 100644
--- a/include/linux/netfilter_bridge.h
+++ b/include/linux/netfilter_bridge.h
@@ -104,9 +104,18 @@ struct bridge_skb_cb {
         } daddr;
 };
 
+static inline void br_drop_fake_rtable(struct sk_buff *skb)
+{
+        struct dst_entry *dst = skb_dst(skb);
+
+        if (dst && (dst->flags & DST_FAKE_RTABLE))
+                skb_dst_drop(skb);
+}
+
 #else
 #define nf_bridge_maybe_copy_header(skb)        (0)
 #define nf_bridge_pad(skb)                      (0)
+#define br_drop_fake_rtable(skb)                do { } while (0)
 #endif /* CONFIG_BRIDGE_NETFILTER */
 
 #endif /* __KERNEL__ */
diff --git a/include/net/dst.h b/include/net/dst.h
index ff4da42fcfc..bed833d9796 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -59,6 +59,7 @@ struct dst_entry {
 #define DST_NOCACHE             0x0010
 #define DST_NOCOUNT             0x0020
 #define DST_NOPEER              0x0040
+#define DST_FAKE_RTABLE         0x0080
 
         short                   error;
         short                   obsolete;
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 61f65344e71..a2098e3de50 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -47,6 +47,7 @@ int br_dev_queue_push_xmit(struct sk_buff *skb)
                 kfree_skb(skb);
         } else {
                 skb_push(skb, ETH_HLEN);
+                br_drop_fake_rtable(skb);
                 dev_queue_xmit(skb);
         }
 
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index dec4f381713..d7f49b63ab0 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -156,7 +156,7 @@ void br_netfilter_rtable_init(struct net_bridge *br)
         rt->dst.dev = br->dev;
         rt->dst.path = &rt->dst;
         dst_init_metrics(&rt->dst, br_dst_default_metrics, true);
-        rt->dst.flags   = DST_NOXFRM | DST_NOPEER;
+        rt->dst.flags   = DST_NOXFRM | DST_NOPEER | DST_FAKE_RTABLE;
         rt->dst.ops = &fake_dst_ops;
 }
 
@@ -694,11 +694,7 @@ static unsigned int br_nf_local_in(unsigned int hook, struct sk_buff *skb,
                                    const struct net_device *out,
                                    int (*okfn)(struct sk_buff *))
 {
-        struct rtable *rt = skb_rtable(skb);
-
-        if (rt && rt == bridge_parent_rtable(in))
-                skb_dst_drop(skb);
-
+        br_drop_fake_rtable(skb);
         return NF_ACCEPT;
 }