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

Pull networking updates from David Miller:

 1) Seccomp BPF filters can now be JIT'd, from Alexei Starovoitov.

 2) Multiqueue support in xen-netback and xen-netfront, from Andrew J
    Benniston.

 3) Allow tweaking of aggregation settings in cdc_ncm driver, from Bjørn
    Mork.

 4) BPF now has a "random" opcode, from Chema Gonzalez.

 5) Add more BPF documentation and improve test framework, from Daniel
    Borkmann.

 6) Support TCP fastopen over ipv6, from Daniel Lee.

 7) Add software TSO helper functions and use them to support software
    TSO in mvneta and mv643xx_eth drivers.  From Ezequiel Garcia.

 8) Support software TSO in fec driver too, from Nimrod Andy.

 9) Add Broadcom SYSTEMPORT driver, from Florian Fainelli.

10) Handle broadcasts more gracefully over macvlan when there are large
    numbers of interfaces configured, from Herbert Xu.

11) Allow more control over fwmark used for non-socket based responses,
    from Lorenzo Colitti.

12) Do TCP congestion window limiting based upon measurements, from Neal
    Cardwell.

13) Support busy polling in SCTP, from Neal Horman.

14) Allow RSS key to be configured via ethtool, from Venkata Duvvuru.

15) Bridge promisc mode handling improvements from Vlad Yasevich.

16) Don't use inetpeer entries to implement ID generation any more, it
    performs poorly, from Eric Dumazet.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1522 commits)
  rtnetlink: fix userspace API breakage for iproute2 < v3.9.0
  tcp: fixing TLP's FIN recovery
  net: fec: Add software TSO support
  net: fec: Add Scatter/gather support
  net: fec: Increase buffer descriptor entry number
  net: fec: Factorize feature setting
  net: fec: Enable IP header hardware checksum
  net: fec: Factorize the .xmit transmit function
  bridge: fix compile error when compiling without IPv6 support
  bridge: fix smatch warning / potential null pointer dereference
  via-rhine: fix full-duplex with autoneg disable
  bnx2x: Enlarge the dorq threshold for VFs
  bnx2x: Check for UNDI in uncommon branch
  bnx2x: Fix 1G-baseT link
  bnx2x: Fix link for KR with swapped polarity lane
  sctp: Fix sk_ack_backlog wrap-around problem
  net/core: Add VF link state control policy
  net/fsl: xgmac_mdio is dependent on OF_MDIO
  net/fsl: Make xgmac_mdio read error message useful
  net_sched: drr: warn when qdisc is not work conserving
  ...

1 files changed, 87 insertions, 34 deletions

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 3c0256962f7d..ef0475568f9e 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -36,6 +36,7 @@
 
 #include "core.h"
 #include "port.h"
+#include "node.h"
 
 #include <linux/export.h>
 
@@ -44,7 +45,7 @@
 
 #define CONN_TIMEOUT_DEFAULT	8000	/* default connect timeout = 8s */
 
-static int backlog_rcv(struct sock *sk, struct sk_buff *skb);
+static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb);
 static void tipc_data_ready(struct sock *sk);
 static void tipc_write_space(struct sock *sk);
 static int tipc_release(struct socket *sock);
@@ -195,11 +196,12 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
 	sock->state = state;
 
 	sock_init_data(sock, sk);
-	sk->sk_backlog_rcv = backlog_rcv;
+	sk->sk_backlog_rcv = tipc_backlog_rcv;
 	sk->sk_rcvbuf = sysctl_tipc_rmem[1];
 	sk->sk_data_ready = tipc_data_ready;
 	sk->sk_write_space = tipc_write_space;
-	tipc_sk(sk)->conn_timeout = CONN_TIMEOUT_DEFAULT;
+	tsk->conn_timeout = CONN_TIMEOUT_DEFAULT;
+	atomic_set(&tsk->dupl_rcvcnt, 0);
 	tipc_port_unlock(port);
 
 	if (sock->state == SS_READY) {
@@ -983,10 +985,11 @@ static int anc_data_recv(struct msghdr *m, struct tipc_msg *msg,
 	return 0;
 }
 
-static int tipc_wait_for_rcvmsg(struct socket *sock, long timeo)
+static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop)
 {
 	struct sock *sk = sock->sk;
 	DEFINE_WAIT(wait);
+	long timeo = *timeop;
 	int err;
 
 	for (;;) {
@@ -1011,6 +1014,7 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long timeo)
 			break;
 	}
 	finish_wait(sk_sleep(sk), &wait);
+	*timeop = timeo;
 	return err;
 }
 
@@ -1054,7 +1058,7 @@ static int tipc_recvmsg(struct kiocb *iocb, struct socket *sock,
 restart:
 
 	/* Look for a message in receive queue; wait if necessary */
-	res = tipc_wait_for_rcvmsg(sock, timeo);
+	res = tipc_wait_for_rcvmsg(sock, &timeo);
 	if (res)
 		goto exit;
 
@@ -1100,7 +1104,7 @@ restart:
 	/* Consume received message (optional) */
 	if (likely(!(flags & MSG_PEEK))) {
 		if ((sock->state != SS_READY) &&
-		    (++port->conn_unacked >= TIPC_FLOW_CONTROL_WIN))
+		    (++port->conn_unacked >= TIPC_CONNACK_INTV))
 			tipc_acknowledge(port->ref, port->conn_unacked);
 		advance_rx_queue(sk);
 	}
@@ -1152,7 +1156,7 @@ static int tipc_recv_stream(struct kiocb *iocb, struct socket *sock,
 
 restart:
 	/* Look for a message in receive queue; wait if necessary */
-	res = tipc_wait_for_rcvmsg(sock, timeo);
+	res = tipc_wait_for_rcvmsg(sock, &timeo);
 	if (res)
 		goto exit;
 
@@ -1209,7 +1213,7 @@ restart:
 
 	/* Consume received message (optional) */
 	if (likely(!(flags & MSG_PEEK))) {
-		if (unlikely(++port->conn_unacked >= TIPC_FLOW_CONTROL_WIN))
+		if (unlikely(++port->conn_unacked >= TIPC_CONNACK_INTV))
 			tipc_acknowledge(port->ref, port->conn_unacked);
 		advance_rx_queue(sk);
 	}
@@ -1415,7 +1419,7 @@ static u32 filter_rcv(struct sock *sk, struct sk_buff *buf)
 }
 
 /**
- * backlog_rcv - handle incoming message from backlog queue
+ * tipc_backlog_rcv - handle incoming message from backlog queue
  * @sk: socket
  * @buf: message
  *
@@ -1423,47 +1427,74 @@ static u32 filter_rcv(struct sock *sk, struct sk_buff *buf)
  *
  * Returns 0
  */
-static int backlog_rcv(struct sock *sk, struct sk_buff *buf)
+static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *buf)
 {
 	u32 res;
+	struct tipc_sock *tsk = tipc_sk(sk);
+	uint truesize = buf->truesize;
 
 	res = filter_rcv(sk, buf);
-	if (res)
+	if (unlikely(res))
 		tipc_reject_msg(buf, res);
+
+	if (atomic_read(&tsk->dupl_rcvcnt) < TIPC_CONN_OVERLOAD_LIMIT)
+		atomic_add(truesize, &tsk->dupl_rcvcnt);
+
 	return 0;
 }
 
 /**
  * tipc_sk_rcv - handle incoming message
- * @sk:  socket receiving message
- * @buf: message
- *
- * Called with port lock already taken.
- *
- * Returns TIPC error status code (TIPC_OK if message is not to be rejected)
+ * @buf: buffer containing arriving message
+ * Consumes buffer
+ * Returns 0 if success, or errno: -EHOSTUNREACH
  */
-u32 tipc_sk_rcv(struct sock *sk, struct sk_buff *buf)
+int tipc_sk_rcv(struct sk_buff *buf)
 {
-	u32 res;
+	struct tipc_sock *tsk;
+	struct tipc_port *port;
+	struct sock *sk;
+	u32 dport = msg_destport(buf_msg(buf));
+	int err = TIPC_OK;
+	uint limit;
 
-	/*
-	 * Process message if socket is unlocked; otherwise add to backlog queue
-	 *
-	 * This code is based on sk_receive_skb(), but must be distinct from it
-	 * since a TIPC-specific filter/reject mechanism is utilized
-	 */
+	/* Forward unresolved named message */
+	if (unlikely(!dport)) {
+		tipc_net_route_msg(buf);
+		return 0;
+	}
+
+	/* Validate destination */
+	port = tipc_port_lock(dport);
+	if (unlikely(!port)) {
+		err = TIPC_ERR_NO_PORT;
+		goto exit;
+	}
+
+	tsk = tipc_port_to_sock(port);
+	sk = &tsk->sk;
+
+	/* Queue message */
 	bh_lock_sock(sk);
+
 	if (!sock_owned_by_user(sk)) {
-		res = filter_rcv(sk, buf);
+		err = filter_rcv(sk, buf);
 	} else {
-		if (sk_add_backlog(sk, buf, rcvbuf_limit(sk, buf)))
-			res = TIPC_ERR_OVERLOAD;
-		else
-			res = TIPC_OK;
+		if (sk->sk_backlog.len == 0)
+			atomic_set(&tsk->dupl_rcvcnt, 0);
+		limit = rcvbuf_limit(sk, buf) + atomic_read(&tsk->dupl_rcvcnt);
+		if (sk_add_backlog(sk, buf, limit))
+			err = TIPC_ERR_OVERLOAD;
 	}
+
 	bh_unlock_sock(sk);
+	tipc_port_unlock(port);
 
-	return res;
+	if (likely(!err))
+		return 0;
+exit:
+	tipc_reject_msg(buf, err);
+	return -EHOSTUNREACH;
 }
 
 static int tipc_wait_for_connect(struct socket *sock, long *timeo_p)
@@ -1905,6 +1936,28 @@ static int tipc_getsockopt(struct socket *sock, int lvl, int opt,
 	return put_user(sizeof(value), ol);
 }
 
+int tipc_ioctl(struct socket *sk, unsigned int cmd, unsigned long arg)
+{
+	struct tipc_sioc_ln_req lnr;
+	void __user *argp = (void __user *)arg;
+
+	switch (cmd) {
+	case SIOCGETLINKNAME:
+		if (copy_from_user(&lnr, argp, sizeof(lnr)))
+			return -EFAULT;
+		if (!tipc_node_get_linkname(lnr.bearer_id, lnr.peer,
+					    lnr.linkname, TIPC_MAX_LINK_NAME)) {
+			if (copy_to_user(argp, &lnr, sizeof(lnr)))
+				return -EFAULT;
+			return 0;
+		}
+		return -EADDRNOTAVAIL;
+		break;
+	default:
+		return -ENOIOCTLCMD;
+	}
+}
+
 /* Protocol switches for the various types of TIPC sockets */
 
 static const struct proto_ops msg_ops = {
@@ -1917,7 +1970,7 @@ static const struct proto_ops msg_ops = {
 	.accept		= sock_no_accept,
 	.getname	= tipc_getname,
 	.poll		= tipc_poll,
-	.ioctl		= sock_no_ioctl,
+	.ioctl		= tipc_ioctl,
 	.listen		= sock_no_listen,
 	.shutdown	= tipc_shutdown,
 	.setsockopt	= tipc_setsockopt,
@@ -1938,7 +1991,7 @@ static const struct proto_ops packet_ops = {
 	.accept		= tipc_accept,
 	.getname	= tipc_getname,
 	.poll		= tipc_poll,
-	.ioctl		= sock_no_ioctl,
+	.ioctl		= tipc_ioctl,
 	.listen		= tipc_listen,
 	.shutdown	= tipc_shutdown,
 	.setsockopt	= tipc_setsockopt,
@@ -1959,7 +2012,7 @@ static const struct proto_ops stream_ops = {
 	.accept		= tipc_accept,
 	.getname	= tipc_getname,
 	.poll		= tipc_poll,
-	.ioctl		= sock_no_ioctl,
+	.ioctl		= tipc_ioctl,
 	.listen		= tipc_listen,
 	.shutdown	= tipc_shutdown,
 	.setsockopt	= tipc_setsockopt,