Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Pull networking fixes from David Miller:1) Use after free in __dev_map_entry_free(), from Eric Dumazet.

 1) Use after free in __dev_map_entry_free(), from Eric Dumazet.

 2) Fix TCP retransmission timestamps on passive Fast Open, from Yuchung
    Cheng.

 3) Orphan NFC, we'll take the patches directly into my tree. From
    Johannes Berg.

 4) We can't recycle cloned TCP skbs, from Eric Dumazet.

 5) Some flow dissector bpf test fixes, from Stanislav Fomichev.

 6) Fix RCU marking and warnings in rhashtable, from Herbert Xu.

 7) Fix some potential fib6 leaks, from Eric Dumazet.

 8) Fix a _decode_session4 uninitialized memory read bug fix that got
    lost in a merge. From Florian Westphal.

 9) Fix ipv6 source address routing wrt. exception route entries, from
    Wei Wang.

10) The netdev_xmit_more() conversion was not done %100 properly in mlx5
    driver, fix from Tariq Toukan.

11) Clean up botched merge on netfilter kselftest, from Florian
    Westphal.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (74 commits)
  of_net: fix of_get_mac_address retval if compiled without CONFIG_OF
  net: fix kernel-doc warnings for socket.c
  net: Treat sock->sk_drops as an unsigned int when printing
  kselftests: netfilter: fix leftover net/net-next merge conflict
  mlxsw: core: Prevent reading unsupported slave address from SFP EEPROM
  mlxsw: core: Prevent QSFP module initialization for old hardware
  vsock/virtio: Initialize core virtio vsock before registering the driver
  net/mlx5e: Fix possible modify header actions memory leak
  net/mlx5e: Fix no rewrite fields with the same match
  net/mlx5e: Additional check for flow destination comparison
  net/mlx5e: Add missing ethtool driver info for representors
  net/mlx5e: Fix number of vports for ingress ACL configuration
  net/mlx5e: Fix ethtool rxfh commands when CONFIG_MLX5_EN_RXNFC is disabled
  net/mlx5e: Fix wrong xmit_more application
  net/mlx5: Fix peer pf disable hca command
  net/mlx5: E-Switch, Correct type to u16 for vport_num and int for vport_index
  net/mlx5: Add meaningful return codes to status_to_err function
  net/mlx5: Imply MLXFW in mlx5_core
  Revert "tipc: fix modprobe tipc failed after switch order of device registration"
  vsock/virtio: free packets during the socket release
  ...

1 files changed, 34 insertions, 24 deletions

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 23a20d62daac..7a014ca877ed 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -111,8 +111,8 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 			 int iif, int type, u32 portid, u32 seq,
 			 unsigned int flags);
 static struct rt6_info *rt6_find_cached_rt(const struct fib6_result *res,
-					   struct in6_addr *daddr,
-					   struct in6_addr *saddr);
+					   const struct in6_addr *daddr,
+					   const struct in6_addr *saddr);
 
 #ifdef CONFIG_IPV6_ROUTE_INFO
 static struct fib6_info *rt6_add_route_info(struct net *net,
@@ -1295,6 +1295,13 @@ static struct rt6_info *rt6_make_pcpu_route(struct net *net,
 	prev = cmpxchg(p, NULL, pcpu_rt);
 	BUG_ON(prev);
 
+	if (res->f6i->fib6_destroying) {
+		struct fib6_info *from;
+
+		from = xchg((__force struct fib6_info **)&pcpu_rt->from, NULL);
+		fib6_info_release(from);
+	}
+
 	return pcpu_rt;
 }
 
@@ -1566,31 +1573,44 @@ out:
  * Caller has to hold rcu_read_lock()
  */
 static struct rt6_info *rt6_find_cached_rt(const struct fib6_result *res,
-					   struct in6_addr *daddr,
-					   struct in6_addr *saddr)
+					   const struct in6_addr *daddr,
+					   const struct in6_addr *saddr)
 {
+	const struct in6_addr *src_key = NULL;
 	struct rt6_exception_bucket *bucket;
-	struct in6_addr *src_key = NULL;
 	struct rt6_exception *rt6_ex;
 	struct rt6_info *ret = NULL;
 
-	bucket = rcu_dereference(res->f6i->rt6i_exception_bucket);
-
 #ifdef CONFIG_IPV6_SUBTREES
 	/* fib6i_src.plen != 0 indicates f6i is in subtree
 	 * and exception table is indexed by a hash of
 	 * both fib6_dst and fib6_src.
-	 * Otherwise, the exception table is indexed by
-	 * a hash of only fib6_dst.
+	 * However, the src addr used to create the hash
+	 * might not be exactly the passed in saddr which
+	 * is a /128 addr from the flow.
+	 * So we need to use f6i->fib6_src to redo lookup
+	 * if the passed in saddr does not find anything.
+	 * (See the logic in ip6_rt_cache_alloc() on how
+	 * rt->rt6i_src is updated.)
 	 */
 	if (res->f6i->fib6_src.plen)
 		src_key = saddr;
+find_ex:
 #endif
+	bucket = rcu_dereference(res->f6i->rt6i_exception_bucket);
 	rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key);
 
 	if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i))
 		ret = rt6_ex->rt6i;
 
+#ifdef CONFIG_IPV6_SUBTREES
+	/* Use fib6_src as src_key and redo lookup */
+	if (!ret && src_key && src_key != &res->f6i->fib6_src.addr) {
+		src_key = &res->f6i->fib6_src.addr;
+		goto find_ex;
+	}
+#endif
+
 	return ret;
 }
 
@@ -2665,12 +2685,10 @@ u32 ip6_mtu_from_fib6(const struct fib6_result *res,
 		      const struct in6_addr *daddr,
 		      const struct in6_addr *saddr)
 {
-	struct rt6_exception_bucket *bucket;
 	const struct fib6_nh *nh = res->nh;
 	struct fib6_info *f6i = res->f6i;
-	const struct in6_addr *src_key;
-	struct rt6_exception *rt6_ex;
 	struct inet6_dev *idev;
+	struct rt6_info *rt;
 	u32 mtu = 0;
 
 	if (unlikely(fib6_metric_locked(f6i, RTAX_MTU))) {
@@ -2679,18 +2697,10 @@ u32 ip6_mtu_from_fib6(const struct fib6_result *res,
 			goto out;
 	}
 
-	src_key = NULL;
-#ifdef CONFIG_IPV6_SUBTREES
-	if (f6i->fib6_src.plen)
-		src_key = saddr;
-#endif
-
-	bucket = rcu_dereference(f6i->rt6i_exception_bucket);
-	rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key);
-	if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i))
-		mtu = dst_metric_raw(&rt6_ex->rt6i->dst, RTAX_MTU);
-
-	if (likely(!mtu)) {
+	rt = rt6_find_cached_rt(res, daddr, saddr);
+	if (unlikely(rt)) {
+		mtu = dst_metric_raw(&rt->dst, RTAX_MTU);
+	} else {
 		struct net_device *dev = nh->fib_nh_dev;
 
 		mtu = IPV6_MIN_MTU;