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, 59 insertions, 36 deletions

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 05919bf..19909d0 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -116,6 +116,8 @@ static ATOMIC_NOTIFIER_HEAD(netlink_chain);
 static DEFINE_SPINLOCK(netlink_tap_lock);
 static struct list_head netlink_tap_all __read_mostly;
 
+static const struct rhashtable_params netlink_rhashtable_params;
+
 static inline u32 netlink_group_mask(u32 group)
 {
 	return group ? 1 << (group - 1) : 0;
@@ -970,41 +972,50 @@ netlink_unlock_table(void)
 
 struct netlink_compare_arg
 {
-	struct net *net;
+	possible_net_t pnet;
 	u32 portid;
 };
 
-static bool netlink_compare(void *ptr, void *arg)
+/* Doing sizeof directly may yield 4 extra bytes on 64-bit. */
+#define netlink_compare_arg_len \
+	(offsetof(struct netlink_compare_arg, portid) + sizeof(u32))
+
+static inline int netlink_compare(struct rhashtable_compare_arg *arg,
+				  const void *ptr)
 {
-	struct netlink_compare_arg *x = arg;
-	struct sock *sk = ptr;
+	const struct netlink_compare_arg *x = arg->key;
+	const struct netlink_sock *nlk = ptr;
 
-	return nlk_sk(sk)->portid == x->portid &&
-	       net_eq(sock_net(sk), x->net);
+	return nlk->portid != x->portid ||
+	       !net_eq(sock_net(&nlk->sk), read_pnet(&x->pnet));
+}
+
+static void netlink_compare_arg_init(struct netlink_compare_arg *arg,
+				     struct net *net, u32 portid)
+{
+	memset(arg, 0, sizeof(*arg));
+	write_pnet(&arg->pnet, net);
+	arg->portid = portid;
 }
 
 static struct sock *__netlink_lookup(struct netlink_table *table, u32 portid,
 				     struct net *net)
 {
-	struct netlink_compare_arg arg = {
-		.net = net,
-		.portid = portid,
-	};
+	struct netlink_compare_arg arg;
 
-	return rhashtable_lookup_compare(&table->hash, &portid,
-					 &netlink_compare, &arg);
+	netlink_compare_arg_init(&arg, net, portid);
+	return rhashtable_lookup_fast(&table->hash, &arg,
+				      netlink_rhashtable_params);
 }
 
-static bool __netlink_insert(struct netlink_table *table, struct sock *sk)
+static int __netlink_insert(struct netlink_table *table, struct sock *sk)
 {
-	struct netlink_compare_arg arg = {
-		.net = sock_net(sk),
-		.portid = nlk_sk(sk)->portid,
-	};
+	struct netlink_compare_arg arg;
 
-	return rhashtable_lookup_compare_insert(&table->hash,
-						&nlk_sk(sk)->node,
-						&netlink_compare, &arg);
+	netlink_compare_arg_init(&arg, sock_net(sk), nlk_sk(sk)->portid);
+	return rhashtable_lookup_insert_key(&table->hash, &arg,
+					    &nlk_sk(sk)->node,
+					    netlink_rhashtable_params);
 }
 
 static struct sock *netlink_lookup(struct net *net, int protocol, u32 portid)
@@ -1066,9 +1077,10 @@ static int netlink_insert(struct sock *sk, u32 portid)
 	nlk_sk(sk)->portid = portid;
 	sock_hold(sk);
 
-	err = 0;
-	if (!__netlink_insert(table, sk)) {
-		err = -EADDRINUSE;
+	err = __netlink_insert(table, sk);
+	if (err) {
+		if (err == -EEXIST)
+			err = -EADDRINUSE;
 		sock_put(sk);
 	}
 
@@ -1082,7 +1094,8 @@ static void netlink_remove(struct sock *sk)
 	struct netlink_table *table;
 
 	table = &nl_table[sk->sk_protocol];
-	if (rhashtable_remove(&table->hash, &nlk_sk(sk)->node)) {
+	if (!rhashtable_remove_fast(&table->hash, &nlk_sk(sk)->node,
+				    netlink_rhashtable_params)) {
 		WARN_ON(atomic_read(&sk->sk_refcnt) == 1);
 		__sock_put(sk);
 	}
@@ -2256,8 +2269,7 @@ static void netlink_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb)
 	put_cmsg(msg, SOL_NETLINK, NETLINK_PKTINFO, sizeof(info), &info);
 }
 
-static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
-			   struct msghdr *msg, size_t len)
+static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 {
 	struct sock *sk = sock->sk;
 	struct netlink_sock *nlk = nlk_sk(sk);
@@ -2346,8 +2358,7 @@ out:
 	return err;
 }
 
-static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
-			   struct msghdr *msg, size_t len,
+static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 			   int flags)
 {
 	struct scm_cookie scm;
@@ -3116,17 +3127,28 @@ static struct pernet_operations __net_initdata netlink_net_ops = {
 	.exit = netlink_net_exit,
 };
 
+static inline u32 netlink_hash(const void *data, u32 len, u32 seed)
+{
+	const struct netlink_sock *nlk = data;
+	struct netlink_compare_arg arg;
+
+	netlink_compare_arg_init(&arg, sock_net(&nlk->sk), nlk->portid);
+	return jhash2((u32 *)&arg, netlink_compare_arg_len / sizeof(u32), seed);
+}
+
+static const struct rhashtable_params netlink_rhashtable_params = {
+	.head_offset = offsetof(struct netlink_sock, node),
+	.key_len = netlink_compare_arg_len,
+	.obj_hashfn = netlink_hash,
+	.obj_cmpfn = netlink_compare,
+	.max_size = 65536,
+	.automatic_shrinking = true,
+};
+
 static int __init netlink_proto_init(void)
 {
 	int i;
 	int err = proto_register(&netlink_proto, 0);
-	struct rhashtable_params ht_params = {
-		.head_offset = offsetof(struct netlink_sock, node),
-		.key_offset = offsetof(struct netlink_sock, portid),
-		.key_len = sizeof(u32), /* portid */
-		.hashfn = jhash,
-		.max_shift = 16, /* 64K */
-	};
 
 	if (err != 0)
 		goto out;
@@ -3138,7 +3160,8 @@ static int __init netlink_proto_init(void)
 		goto panic;
 
 	for (i = 0; i < MAX_LINKS; i++) {
-		if (rhashtable_init(&nl_table[i].hash, &ht_params) < 0) {
+		if (rhashtable_init(&nl_table[i].hash,
+				    &netlink_rhashtable_params) < 0) {
 			while (--i > 0)
 				rhashtable_destroy(&nl_table[i].hash);
 			kfree(nl_table);