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, 41 insertions, 31 deletions

diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 9111a4e22155..c6fb80bd5826 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -24,9 +24,9 @@
 #include <net/secure_seq.h>
 #include <net/ip.h>
 
-static unsigned int inet_ehashfn(struct net *net, const __be32 laddr,
-				 const __u16 lport, const __be32 faddr,
-				 const __be16 fport)
+static u32 inet_ehashfn(const struct net *net, const __be32 laddr,
+			const __u16 lport, const __be32 faddr,
+			const __be16 fport)
 {
 	static u32 inet_ehash_secret __read_mostly;
 
@@ -36,17 +36,21 @@ static unsigned int inet_ehashfn(struct net *net, const __be32 laddr,
 			      inet_ehash_secret + net_hash_mix(net));
 }
 
-
-static unsigned int inet_sk_ehashfn(const struct sock *sk)
+/* This function handles inet_sock, but also timewait and request sockets
+ * for IPv4/IPv6.
+ */
+u32 sk_ehashfn(const struct sock *sk)
 {
-	const struct inet_sock *inet = inet_sk(sk);
-	const __be32 laddr = inet->inet_rcv_saddr;
-	const __u16 lport = inet->inet_num;
-	const __be32 faddr = inet->inet_daddr;
-	const __be16 fport = inet->inet_dport;
-	struct net *net = sock_net(sk);
-
-	return inet_ehashfn(net, laddr, lport, faddr, fport);
+#if IS_ENABLED(CONFIG_IPV6)
+	if (sk->sk_family == AF_INET6 &&
+	    !ipv6_addr_v4mapped(&sk->sk_v6_daddr))
+		return inet6_ehashfn(sock_net(sk),
+				     &sk->sk_v6_rcv_saddr, sk->sk_num,
+				     &sk->sk_v6_daddr, sk->sk_dport);
+#endif
+	return inet_ehashfn(sock_net(sk),
+			    sk->sk_rcv_saddr, sk->sk_num,
+			    sk->sk_daddr, sk->sk_dport);
 }
 
 /*
@@ -60,8 +64,8 @@ struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep,
 {
 	struct inet_bind_bucket *tb = kmem_cache_alloc(cachep, GFP_ATOMIC);
 
-	if (tb != NULL) {
-		write_pnet(&tb->ib_net, hold_net(net));
+	if (tb) {
+		write_pnet(&tb->ib_net, net);
 		tb->port      = snum;
 		tb->fastreuse = 0;
 		tb->fastreuseport = 0;
@@ -79,7 +83,6 @@ void inet_bind_bucket_destroy(struct kmem_cache *cachep, struct inet_bind_bucket
 {
 	if (hlist_empty(&tb->owners)) {
 		__hlist_del(&tb->node);
-		release_net(ib_net(tb));
 		kmem_cache_free(cachep, tb);
 	}
 }
@@ -263,11 +266,19 @@ void sock_gen_put(struct sock *sk)
 
 	if (sk->sk_state == TCP_TIME_WAIT)
 		inet_twsk_free(inet_twsk(sk));
+	else if (sk->sk_state == TCP_NEW_SYN_RECV)
+		reqsk_free(inet_reqsk(sk));
 	else
 		sk_free(sk);
 }
 EXPORT_SYMBOL_GPL(sock_gen_put);
 
+void sock_edemux(struct sk_buff *skb)
+{
+	sock_gen_put(skb->sk);
+}
+EXPORT_SYMBOL(sock_edemux);
+
 struct sock *__inet_lookup_established(struct net *net,
 				  struct inet_hashinfo *hashinfo,
 				  const __be32 saddr, const __be16 sport,
@@ -377,7 +388,7 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row,
 		*twp = tw;
 	} else if (tw) {
 		/* Silly. Should hash-dance instead... */
-		inet_twsk_deschedule(tw, death_row);
+		inet_twsk_deschedule(tw);
 
 		inet_twsk_put(tw);
 	}
@@ -400,13 +411,13 @@ int __inet_hash_nolisten(struct sock *sk, struct inet_timewait_sock *tw)
 {
 	struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
 	struct hlist_nulls_head *list;
-	spinlock_t *lock;
 	struct inet_ehash_bucket *head;
+	spinlock_t *lock;
 	int twrefcnt = 0;
 
 	WARN_ON(!sk_unhashed(sk));
 
-	sk->sk_hash = inet_sk_ehashfn(sk);
+	sk->sk_hash = sk_ehashfn(sk);
 	head = inet_ehash_bucket(hashinfo, sk->sk_hash);
 	list = &head->chain;
 	lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
@@ -423,15 +434,13 @@ int __inet_hash_nolisten(struct sock *sk, struct inet_timewait_sock *tw)
 }
 EXPORT_SYMBOL_GPL(__inet_hash_nolisten);
 
-static void __inet_hash(struct sock *sk)
+int __inet_hash(struct sock *sk, struct inet_timewait_sock *tw)
 {
 	struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
 	struct inet_listen_hashbucket *ilb;
 
-	if (sk->sk_state != TCP_LISTEN) {
-		__inet_hash_nolisten(sk, NULL);
-		return;
-	}
+	if (sk->sk_state != TCP_LISTEN)
+		return __inet_hash_nolisten(sk, tw);
 
 	WARN_ON(!sk_unhashed(sk));
 	ilb = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)];
@@ -440,13 +449,15 @@ static void __inet_hash(struct sock *sk)
 	__sk_nulls_add_node_rcu(sk, &ilb->head);
 	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
 	spin_unlock(&ilb->lock);
+	return 0;
 }
+EXPORT_SYMBOL(__inet_hash);
 
 void inet_hash(struct sock *sk)
 {
 	if (sk->sk_state != TCP_CLOSE) {
 		local_bh_disable();
-		__inet_hash(sk);
+		__inet_hash(sk, NULL);
 		local_bh_enable();
 	}
 }
@@ -477,8 +488,7 @@ EXPORT_SYMBOL_GPL(inet_unhash);
 int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 		struct sock *sk, u32 port_offset,
 		int (*check_established)(struct inet_timewait_death_row *,
-			struct sock *, __u16, struct inet_timewait_sock **),
-		int (*hash)(struct sock *sk, struct inet_timewait_sock *twp))
+			struct sock *, __u16, struct inet_timewait_sock **))
 {
 	struct inet_hashinfo *hinfo = death_row->hashinfo;
 	const unsigned short snum = inet_sk(sk)->inet_num;
@@ -548,14 +558,14 @@ ok:
 		inet_bind_hash(sk, tb, port);
 		if (sk_unhashed(sk)) {
 			inet_sk(sk)->inet_sport = htons(port);
-			twrefcnt += hash(sk, tw);
+			twrefcnt += __inet_hash_nolisten(sk, tw);
 		}
 		if (tw)
 			twrefcnt += inet_twsk_bind_unhash(tw, hinfo);
 		spin_unlock(&head->lock);
 
 		if (tw) {
-			inet_twsk_deschedule(tw, death_row);
+			inet_twsk_deschedule(tw);
 			while (twrefcnt) {
 				twrefcnt--;
 				inet_twsk_put(tw);
@@ -570,7 +580,7 @@ ok:
 	tb  = inet_csk(sk)->icsk_bind_hash;
 	spin_lock_bh(&head->lock);
 	if (sk_head(&tb->owners) == sk && !sk->sk_bind_node.next) {
-		hash(sk, NULL);
+		__inet_hash_nolisten(sk, NULL);
 		spin_unlock_bh(&head->lock);
 		return 0;
 	} else {
@@ -590,7 +600,7 @@ int inet_hash_connect(struct inet_timewait_death_row *death_row,
 		      struct sock *sk)
 {
 	return __inet_hash_connect(death_row, sk, inet_sk_port_offset(sk),
-			__inet_check_established, __inet_hash_nolisten);
+				   __inet_check_established);
 }
 EXPORT_SYMBOL_GPL(inet_hash_connect);