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

Pull networking updates from David Miller:

 1) Add BQL support to via-rhine, from Tino Reichardt.

 2) Integrate SWITCHDEV layer support into the DSA layer, so DSA drivers
    can support hw switch offloading.  From Floria Fainelli.

 3) Allow 'ip address' commands to initiate multicast group join/leave,
    from Madhu Challa.

 4) Many ipv4 FIB lookup optimizations from Alexander Duyck.

 5) Support EBPF in cls_bpf classifier and act_bpf action, from Daniel
    Borkmann.

 6) Remove the ugly compat support in ARP for ugly layers like ax25,
    rose, etc.  And use this to clean up the neigh layer, then use it to
    implement MPLS support.  All from Eric Biederman.

 7) Support L3 forwarding offloading in switches, from Scott Feldman.

 8) Collapse the LOCAL and MAIN ipv4 FIB tables when possible, to speed
    up route lookups even further.  From Alexander Duyck.

 9) Many improvements and bug fixes to the rhashtable implementation,
    from Herbert Xu and Thomas Graf.  In particular, in the case where
    an rhashtable user bulk adds a large number of items into an empty
    table, we expand the table much more sanely.

10) Don't make the tcp_metrics hash table per-namespace, from Eric
    Biederman.

11) Extend EBPF to access SKB fields, from Alexei Starovoitov.

12) Split out new connection request sockets so that they can be
    established in the main hash table.  Much less false sharing since
    hash lookups go direct to the request sockets instead of having to
    go first to the listener then to the request socks hashed
    underneath.  From Eric Dumazet.

13) Add async I/O support for crytpo AF_ALG sockets, from Tadeusz Struk.

14) Support stable privacy address generation for RFC7217 in IPV6.  From
    Hannes Frederic Sowa.

15) Hash network namespace into IP frag IDs, also from Hannes Frederic
    Sowa.

16) Convert PTP get/set methods to use 64-bit time, from Richard
    Cochran.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1816 commits)
  fm10k: Bump driver version to 0.15.2
  fm10k: corrected VF multicast update
  fm10k: mbx_update_max_size does not drop all oversized messages
  fm10k: reset head instead of calling update_max_size
  fm10k: renamed mbx_tx_dropped to mbx_tx_oversized
  fm10k: update xcast mode before synchronizing multicast addresses
  fm10k: start service timer on probe
  fm10k: fix function header comment
  fm10k: comment next_vf_mbx flow
  fm10k: don't handle mailbox events in iov_event path and always process mailbox
  fm10k: use separate workqueue for fm10k driver
  fm10k: Set PF queues to unlimited bandwidth during virtualization
  fm10k: expose tx_timeout_count as an ethtool stat
  fm10k: only increment tx_timeout_count in Tx hang path
  fm10k: remove extraneous "Reset interface" message
  fm10k: separate PF only stats so that VF does not display them
  fm10k: use hw->mac.max_queues for stats
  fm10k: only show actual queues, not the maximum in hardware
  fm10k: allow creation of VLAN on default vid
  fm10k: fix unused warnings
  ...

1 files changed, 39 insertions, 31 deletions

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 5bd120e4bc0a..54271ed0ed45 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -136,7 +136,7 @@ struct fib_result {
 	u32		tclassid;
 	struct fib_info *fi;
 	struct fib_table *table;
-	struct list_head *fa_head;
+	struct hlist_head *fa_head;
 };
 
 struct fib_result_nl {
@@ -185,7 +185,9 @@ struct fib_table {
 	u32			tb_id;
 	int			tb_default;
 	int			tb_num_default;
-	unsigned long		tb_data[0];
+	struct rcu_head		rcu;
+	unsigned long 		*tb_data;
+	unsigned long		__data[0];
 };
 
 int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp,
@@ -195,10 +197,10 @@ int fib_table_delete(struct fib_table *, struct fib_config *);
 int fib_table_dump(struct fib_table *table, struct sk_buff *skb,
 		   struct netlink_callback *cb);
 int fib_table_flush(struct fib_table *table);
+struct fib_table *fib_trie_unmerge(struct fib_table *main_tb);
+void fib_table_flush_external(struct fib_table *table);
 void fib_free_table(struct fib_table *tb);
 
-
-
 #ifndef CONFIG_IP_MULTIPLE_TABLES
 
 #define TABLE_LOCAL_INDEX	(RT_TABLE_LOCAL & (FIB_TABLE_HASHSZ - 1))
@@ -206,12 +208,16 @@ void fib_free_table(struct fib_table *tb);
 
 static inline struct fib_table *fib_get_table(struct net *net, u32 id)
 {
+	struct hlist_node *tb_hlist;
 	struct hlist_head *ptr;
 
 	ptr = id == RT_TABLE_LOCAL ?
 		&net->ipv4.fib_table_hash[TABLE_LOCAL_INDEX] :
 		&net->ipv4.fib_table_hash[TABLE_MAIN_INDEX];
-	return hlist_entry(ptr->first, struct fib_table, tb_hlist);
+
+	tb_hlist = rcu_dereference_rtnl(hlist_first_rcu(ptr));
+
+	return hlist_entry(tb_hlist, struct fib_table, tb_hlist);
 }
 
 static inline struct fib_table *fib_new_table(struct net *net, u32 id)
@@ -222,14 +228,13 @@ static inline struct fib_table *fib_new_table(struct net *net, u32 id)
 static inline int fib_lookup(struct net *net, const struct flowi4 *flp,
 			     struct fib_result *res)
 {
+	struct fib_table *tb;
 	int err = -ENETUNREACH;
 
 	rcu_read_lock();
 
-	if (!fib_table_lookup(fib_get_table(net, RT_TABLE_LOCAL), flp, res,
-			      FIB_LOOKUP_NOREF) ||
-	    !fib_table_lookup(fib_get_table(net, RT_TABLE_MAIN), flp, res,
-			      FIB_LOOKUP_NOREF))
+	tb = fib_get_table(net, RT_TABLE_MAIN);
+	if (tb && !fib_table_lookup(tb, flp, res, FIB_LOOKUP_NOREF))
 		err = 0;
 
 	rcu_read_unlock();
@@ -249,28 +254,29 @@ int __fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res);
 static inline int fib_lookup(struct net *net, struct flowi4 *flp,
 			     struct fib_result *res)
 {
-	if (!net->ipv4.fib_has_custom_rules) {
-		int err = -ENETUNREACH;
-
-		rcu_read_lock();
-
-		res->tclassid = 0;
-		if ((net->ipv4.fib_local &&
-		     !fib_table_lookup(net->ipv4.fib_local, flp, res,
-				       FIB_LOOKUP_NOREF)) ||
-		    (net->ipv4.fib_main &&
-		     !fib_table_lookup(net->ipv4.fib_main, flp, res,
-				       FIB_LOOKUP_NOREF)) ||
-		    (net->ipv4.fib_default &&
-		     !fib_table_lookup(net->ipv4.fib_default, flp, res,
-				       FIB_LOOKUP_NOREF)))
-			err = 0;
-
-		rcu_read_unlock();
-
-		return err;
+	struct fib_table *tb;
+	int err;
+
+	if (net->ipv4.fib_has_custom_rules)
+		return __fib_lookup(net, flp, res);
+
+	rcu_read_lock();
+
+	res->tclassid = 0;
+
+	for (err = 0; !err; err = -ENETUNREACH) {
+		tb = rcu_dereference_rtnl(net->ipv4.fib_main);
+		if (tb && !fib_table_lookup(tb, flp, res, FIB_LOOKUP_NOREF))
+			break;
+
+		tb = rcu_dereference_rtnl(net->ipv4.fib_default);
+		if (tb && !fib_table_lookup(tb, flp, res, FIB_LOOKUP_NOREF))
+			break;
 	}
-	return __fib_lookup(net, flp, res);
+
+	rcu_read_unlock();
+
+	return err;
 }
 
 #endif /* CONFIG_IP_MULTIPLE_TABLES */
@@ -294,6 +300,8 @@ static inline int fib_num_tclassid_users(struct net *net)
 	return 0;
 }
 #endif
+int fib_unmerge(struct net *net);
+void fib_flush_external(struct net *net);
 
 /* Exported by fib_semantics.c */
 int ip_fib_check_default(__be32 gw, struct net_device *dev);
@@ -304,7 +312,7 @@ void fib_select_multipath(struct fib_result *res);
 
 /* Exported by fib_trie.c */
 void fib_trie_init(void);
-struct fib_table *fib_trie_table(u32 id);
+struct fib_table *fib_trie_table(u32 id, struct fib_table *alias);
 
 static inline void fib_combine_itag(u32 *itag, const struct fib_result *res)
 {