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

Pull networking updates from David Miller:
 "Highlights:

   1) Support more Realtek wireless chips, from Jes Sorenson.

   2) New BPF types for per-cpu hash and arrap maps, from Alexei
      Starovoitov.

   3) Make several TCP sysctls per-namespace, from Nikolay Borisov.

   4) Allow the use of SO_REUSEPORT in order to do per-thread processing
   of incoming TCP/UDP connections.  The muxing can be done using a
   BPF program which hashes the incoming packet.  From Craig Gallek.

   5) Add a multiplexer for TCP streams, to provide a messaged based
      interface.  BPF programs can be used to determine the message
      boundaries.  From Tom Herbert.

   6) Add 802.1AE MACSEC support, from Sabrina Dubroca.

   7) Avoid factorial complexity when taking down an inetdev interface
      with lots of configured addresses.  We were doing things like
      traversing the entire address less for each address removed, and
      flushing the entire netfilter conntrack table for every address as
      well.

   8) Add and use SKB bulk free infrastructure, from Jesper Brouer.

   9) Allow offloading u32 classifiers to hardware, and implement for
      ixgbe, from John Fastabend.

  10) Allow configuring IRQ coalescing parameters on a per-queue basis,
      from Kan Liang.

  11) Extend ethtool so that larger link mode masks can be supported.
      From David Decotigny.

  12) Introduce devlink, which can be used to configure port link types
      (ethernet vs Infiniband, etc.), port splitting, and switch device
      level attributes as a whole.  From Jiri Pirko.

  13) Hardware offload support for flower classifiers, from Amir Vadai.

  14) Add "Local Checksum Offload".  Basically, for a tunneled packet
      the checksum of the outer header is 'constant' (because with the
      checksum field filled into the inner protocol header, the payload
      of the outer frame checksums to 'zero'), and we can take advantage
      of that in various ways.  From Edward Cree"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1548 commits)
  bonding: fix bond_get_stats()
  net: bcmgenet: fix dma api length mismatch
  net/mlx4_core: Fix backward compatibility on VFs
  phy: mdio-thunder: Fix some Kconfig typos
  lan78xx: add ndo_get_stats64
  lan78xx: handle statistics counter rollover
  RDS: TCP: Remove unused constant
  RDS: TCP: Add sysctl tunables for sndbuf/rcvbuf on rds-tcp socket
  net: smc911x: convert pxa dma to dmaengine
  team: remove duplicate set of flag IFF_MULTICAST
  bonding: remove duplicate set of flag IFF_MULTICAST
  net: fix a comment typo
  ethernet: micrel: fix some error codes
  ip_tunnels, bpf: define IP_TUNNEL_OPTS_MAX and use it
  bpf, dst: add and use dst_tclassid helper
  bpf: make skb->tc_classid also readable
  net: mvneta: bm: clarify dependencies
  cls_bpf: reset class and reuse major in da
  ldmvsw: Checkpatch sunvnet.c and sunvnet_common.c
  ldmvsw: Add ldmvsw.c driver code
  ...

1 files changed, 124 insertions, 130 deletions

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 64148914803a..bc5196ea1bdf 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -24,6 +24,7 @@
 #include <net/tcp_states.h>
 #include <net/xfrm.h>
 #include <net/tcp.h>
+#include <net/sock_reuseport.h>
 
 #ifdef INET_CSK_DEBUG
 const char inet_csk_timer_bug_msg[] = "inet_csk BUG: unknown timer value\n";
@@ -67,7 +68,8 @@ int inet_csk_bind_conflict(const struct sock *sk,
 			if ((!reuse || !sk2->sk_reuse ||
 			    sk2->sk_state == TCP_LISTEN) &&
 			    (!reuseport || !sk2->sk_reuseport ||
-			    (sk2->sk_state != TCP_TIME_WAIT &&
+			     rcu_access_pointer(sk->sk_reuseport_cb) ||
+			     (sk2->sk_state != TCP_TIME_WAIT &&
 			     !uid_eq(uid, sock_i_uid(sk2))))) {
 
 				if (!sk2->sk_rcv_saddr || !sk->sk_rcv_saddr ||
@@ -89,161 +91,154 @@ EXPORT_SYMBOL_GPL(inet_csk_bind_conflict);
 
 /* Obtain a reference to a local port for the given sock,
  * if snum is zero it means select any available local port.
+ * We try to allocate an odd port (and leave even ports for connect())
  */
 int inet_csk_get_port(struct sock *sk, unsigned short snum)
 {
-	struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
+	bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN;
+	struct inet_hashinfo *hinfo = sk->sk_prot->h.hashinfo;
+	int ret = 1, attempts = 5, port = snum;
+	int smallest_size = -1, smallest_port;
 	struct inet_bind_hashbucket *head;
-	struct inet_bind_bucket *tb;
-	int ret, attempts = 5;
 	struct net *net = sock_net(sk);
-	int smallest_size = -1, smallest_rover;
+	int i, low, high, attempt_half;
+	struct inet_bind_bucket *tb;
 	kuid_t uid = sock_i_uid(sk);
-	int attempt_half = (sk->sk_reuse == SK_CAN_REUSE) ? 1 : 0;
+	u32 remaining, offset;
 
-	local_bh_disable();
-	if (!snum) {
-		int remaining, rover, low, high;
+	if (port) {
+have_port:
+		head = &hinfo->bhash[inet_bhashfn(net, port,
+						  hinfo->bhash_size)];
+		spin_lock_bh(&head->lock);
+		inet_bind_bucket_for_each(tb, &head->chain)
+			if (net_eq(ib_net(tb), net) && tb->port == port)
+				goto tb_found;
 
+		goto tb_not_found;
+	}
 again:
-		inet_get_local_port_range(net, &low, &high);
-		if (attempt_half) {
-			int half = low + ((high - low) >> 1);
-
-			if (attempt_half == 1)
-				high = half;
-			else
-				low = half;
-		}
-		remaining = (high - low) + 1;
-		smallest_rover = rover = prandom_u32() % remaining + low;
-
-		smallest_size = -1;
-		do {
-			if (inet_is_local_reserved_port(net, rover))
-				goto next_nolock;
-			head = &hashinfo->bhash[inet_bhashfn(net, rover,
-					hashinfo->bhash_size)];
-			spin_lock(&head->lock);
-			inet_bind_bucket_for_each(tb, &head->chain)
-				if (net_eq(ib_net(tb), net) && tb->port == rover) {
-					if (((tb->fastreuse > 0 &&
-					      sk->sk_reuse &&
-					      sk->sk_state != TCP_LISTEN) ||
-					     (tb->fastreuseport > 0 &&
-					      sk->sk_reuseport &&
-					      uid_eq(tb->fastuid, uid))) &&
-					    (tb->num_owners < smallest_size || smallest_size == -1)) {
-						smallest_size = tb->num_owners;
-						smallest_rover = rover;
-					}
-					if (!inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, false)) {
-						snum = rover;
-						goto tb_found;
-					}
-					goto next;
+	attempt_half = (sk->sk_reuse == SK_CAN_REUSE) ? 1 : 0;
+other_half_scan:
+	inet_get_local_port_range(net, &low, &high);
+	high++; /* [32768, 60999] -> [32768, 61000[ */
+	if (high - low < 4)
+		attempt_half = 0;
+	if (attempt_half) {
+		int half = low + (((high - low) >> 2) << 1);
+
+		if (attempt_half == 1)
+			high = half;
+		else
+			low = half;
+	}
+	remaining = high - low;
+	if (likely(remaining > 1))
+		remaining &= ~1U;
+
+	offset = prandom_u32() % remaining;
+	/* __inet_hash_connect() favors ports having @low parity
+	 * We do the opposite to not pollute connect() users.
+	 */
+	offset |= 1U;
+	smallest_size = -1;
+	smallest_port = low; /* avoid compiler warning */
+
+other_parity_scan:
+	port = low + offset;
+	for (i = 0; i < remaining; i += 2, port += 2) {
+		if (unlikely(port >= high))
+			port -= remaining;
+		if (inet_is_local_reserved_port(net, port))
+			continue;
+		head = &hinfo->bhash[inet_bhashfn(net, port,
+						  hinfo->bhash_size)];
+		spin_lock_bh(&head->lock);
+		inet_bind_bucket_for_each(tb, &head->chain)
+			if (net_eq(ib_net(tb), net) && tb->port == port) {
+				if (((tb->fastreuse > 0 && reuse) ||
+				     (tb->fastreuseport > 0 &&
+				      sk->sk_reuseport &&
+				      !rcu_access_pointer(sk->sk_reuseport_cb) &&
+				      uid_eq(tb->fastuid, uid))) &&
+				    (tb->num_owners < smallest_size || smallest_size == -1)) {
+					smallest_size = tb->num_owners;
+					smallest_port = port;
 				}
-			break;
-		next:
-			spin_unlock(&head->lock);
-		next_nolock:
-			if (++rover > high)
-				rover = low;
-		} while (--remaining > 0);
-
-		/* Exhausted local port range during search?  It is not
-		 * possible for us to be holding one of the bind hash
-		 * locks if this test triggers, because if 'remaining'
-		 * drops to zero, we broke out of the do/while loop at
-		 * the top level, not from the 'break;' statement.
-		 */
-		ret = 1;
-		if (remaining <= 0) {
-			if (smallest_size != -1) {
-				snum = smallest_rover;
-				goto have_snum;
-			}
-			if (attempt_half == 1) {
-				/* OK we now try the upper half of the range */
-				attempt_half = 2;
-				goto again;
+				if (!inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, false))
+					goto tb_found;
+				goto next_port;
 			}
-			goto fail;
-		}
-		/* OK, here is the one we will use.  HEAD is
-		 * non-NULL and we hold it's mutex.
-		 */
-		snum = rover;
-	} else {
-have_snum:
-		head = &hashinfo->bhash[inet_bhashfn(net, snum,
-				hashinfo->bhash_size)];
-		spin_lock(&head->lock);
-		inet_bind_bucket_for_each(tb, &head->chain)
-			if (net_eq(ib_net(tb), net) && tb->port == snum)
-				goto tb_found;
+		goto tb_not_found;
+next_port:
+		spin_unlock_bh(&head->lock);
+		cond_resched();
+	}
+
+	if (smallest_size != -1) {
+		port = smallest_port;
+		goto have_port;
 	}
-	tb = NULL;
-	goto tb_not_found;
+	offset--;
+	if (!(offset & 1))
+		goto other_parity_scan;
+
+	if (attempt_half == 1) {
+		/* OK we now try the upper half of the range */
+		attempt_half = 2;
+		goto other_half_scan;
+	}
+	return ret;
+
+tb_not_found:
+	tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep,
+				     net, head, port);
+	if (!tb)
+		goto fail_unlock;
 tb_found:
 	if (!hlist_empty(&tb->owners)) {
 		if (sk->sk_reuse == SK_FORCE_REUSE)
 			goto success;
 
-		if (((tb->fastreuse > 0 &&
-		      sk->sk_reuse && sk->sk_state != TCP_LISTEN) ||
+		if (((tb->fastreuse > 0 && reuse) ||
 		     (tb->fastreuseport > 0 &&
+		      !rcu_access_pointer(sk->sk_reuseport_cb) &&
 		      sk->sk_reuseport && uid_eq(tb->fastuid, uid))) &&
-		    smallest_size == -1) {
+		    smallest_size == -1)
 			goto success;
-		} else {
-			ret = 1;
-			if (inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, true)) {
-				if (((sk->sk_reuse && sk->sk_state != TCP_LISTEN) ||
-				     (tb->fastreuseport > 0 &&
-				      sk->sk_reuseport && uid_eq(tb->fastuid, uid))) &&
-				    smallest_size != -1 && --attempts >= 0) {
-					spin_unlock(&head->lock);
-					goto again;
-				}
-
-				goto fail_unlock;
+		if (inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, true)) {
+			if ((reuse ||
+			     (tb->fastreuseport > 0 &&
+			      sk->sk_reuseport &&
+			      !rcu_access_pointer(sk->sk_reuseport_cb) &&
+			      uid_eq(tb->fastuid, uid))) &&
+			    smallest_size != -1 && --attempts >= 0) {
+				spin_unlock_bh(&head->lock);
+				goto again;
 			}
+			goto fail_unlock;
 		}
-	}
-tb_not_found:
-	ret = 1;
-	if (!tb && (tb = inet_bind_bucket_create(hashinfo->bind_bucket_cachep,
-					net, head, snum)) == NULL)
-		goto fail_unlock;
-	if (hlist_empty(&tb->owners)) {
-		if (sk->sk_reuse && sk->sk_state != TCP_LISTEN)
-			tb->fastreuse = 1;
-		else
+		if (!reuse)
 			tb->fastreuse = 0;
+		if (!sk->sk_reuseport || !uid_eq(tb->fastuid, uid))
+			tb->fastreuseport = 0;
+	} else {
+		tb->fastreuse = reuse;
 		if (sk->sk_reuseport) {
 			tb->fastreuseport = 1;
 			tb->fastuid = uid;
-		} else
-			tb->fastreuseport = 0;
-	} else {
-		if (tb->fastreuse &&
-		    (!sk->sk_reuse || sk->sk_state == TCP_LISTEN))
-			tb->fastreuse = 0;
-		if (tb->fastreuseport &&
-		    (!sk->sk_reuseport || !uid_eq(tb->fastuid, uid)))
+		} else {
 			tb->fastreuseport = 0;
+		}
 	}
 success:
 	if (!inet_csk(sk)->icsk_bind_hash)
-		inet_bind_hash(sk, tb, snum);
+		inet_bind_hash(sk, tb, port);
 	WARN_ON(inet_csk(sk)->icsk_bind_hash != tb);
 	ret = 0;
 
 fail_unlock:
-	spin_unlock(&head->lock);
-fail:
-	local_bh_enable();
+	spin_unlock_bh(&head->lock);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(inet_csk_get_port);
@@ -482,10 +477,6 @@ EXPORT_SYMBOL_GPL(inet_csk_route_child_sock);
 #define AF_INET_FAMILY(fam) true
 #endif
 
-/* Only thing we need from tcp.h */
-extern int sysctl_tcp_synack_retries;
-
-
 /* Decide when to expire the request and when to resend SYN-ACK */
 static inline void syn_ack_recalc(struct request_sock *req, const int thresh,
 				  const int max_retries,
@@ -557,6 +548,7 @@ static void reqsk_timer_handler(unsigned long data)
 {
 	struct request_sock *req = (struct request_sock *)data;
 	struct sock *sk_listener = req->rsk_listener;
+	struct net *net = sock_net(sk_listener);
 	struct inet_connection_sock *icsk = inet_csk(sk_listener);
 	struct request_sock_queue *queue = &icsk->icsk_accept_queue;
 	int qlen, expire = 0, resend = 0;
@@ -566,7 +558,7 @@ static void reqsk_timer_handler(unsigned long data)
 	if (sk_state_load(sk_listener) != TCP_LISTEN)
 		goto drop;
 
-	max_retries = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries;
+	max_retries = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_synack_retries;
 	thresh = max_retries;
 	/* Normally all the openreqs are young and become mature
 	 * (i.e. converted to established socket) for first timeout.
@@ -737,6 +729,7 @@ int inet_csk_listen_start(struct sock *sk, int backlog)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct inet_sock *inet = inet_sk(sk);
+	int err = -EADDRINUSE;
 
 	reqsk_queue_alloc(&icsk->icsk_accept_queue);
 
@@ -754,13 +747,14 @@ int inet_csk_listen_start(struct sock *sk, int backlog)
 		inet->inet_sport = htons(inet->inet_num);
 
 		sk_dst_reset(sk);
-		sk->sk_prot->hash(sk);
+		err = sk->sk_prot->hash(sk);
 
-		return 0;
+		if (likely(!err))
+			return 0;
 	}
 
 	sk->sk_state = TCP_CLOSE;
-	return -EADDRINUSE;
+	return err;
 }
 EXPORT_SYMBOL_GPL(inet_csk_listen_start);