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

Pull networking fixes from David Miller:
 "Looks like a lot, but mostly driver fixes scattered all over as usual.

  Of note:

   1) Add conditional sched in nf conntrack in cleanup to avoid NMI
      watchdogs.  From Florian Westphal.

   2) Fix deadlock in nfnetlink cttimeout, also from Floarian.

   3) Fix handling of slaves in bonding ARP monitor validation, from Jay
      Vosburgh.

   4) Callers of ip_cmsg_send() are responsible for freeing IP options,
      some were not doing so.  Fix from Eric Dumazet.

   5) Fix per-cpu bugs in mvneta driver, from Gregory CLEMENT.

   6) Fix vlan handling in mv88e6xxx DSA driver, from Vivien Didelot.

   7) bcm7xxx PHY driver bug fixes from Florian Fainelli.

   8) Avoid unaligned accesses to protocol headers wrt.  GRE, from
      Alexander Duyck.

   9) SKB leaks and other problems in arc_emac driver, from Alexander
      Kochetkov.

  10) tcp_v4_inbound_md5_hash() releases listener socket instead of
      request socket on error path, oops.  Fix from Eric Dumazet.

  11) Missing socket release in pppoe_rcv_core() that seems to have
      existed basically forever.  From Guillaume Nault.

  12) Missing slave_dev unregister in dsa_slave_create() error path,
      from Florian Fainelli.

  13) crypto_alloc_hash() never returns NULL, fix return value check in
      __tcp_alloc_md5sig_pool.  From Insu Yun.

  14) Properly expire exception route entries in ipv4, from Xin Long.

  15) Fix races in tcp/dccp listener socket dismantle, from Eric
      Dumazet.

  16) Don't set IFF_TX_SKB_SHARING in vxlan, geneve, or GRE, it's not
      legal.  These drivers modify the SKB on transmit.  From Jiri Benc.

  17) Fix regression in the initialziation of netdev->tx_queue_len.
      From Phil Sutter.

  18) Missing unlock in tipc_nl_add_bc_link() error path, from Insu Yun.

  19) SCTP port hash sizing does not properly ensure that table is a
      power of two in size.  From Neil Horman.

  20) Fix initializing of software copy of MAC address in fmvj18x_cs
      driver, from Ken Kawasaki"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (129 commits)
  bnx2x: Fix 84833 phy command handler
  bnx2x: Fix led setting for 84858 phy.
  bnx2x: Correct 84858 PHY fw version
  bnx2x: Fix 84833 RX CRC
  bnx2x: Fix link-forcing for KR2
  net: ethernet: davicom: fix devicetree irq resource
  fmvj18x_cs: fix incorrect indexing of dev->dev_addr[] when copying the MAC address
  Driver: Vmxnet3: Update Rx ring 2 max size
  net: netcp: rework the code for get/set sw_data in dma desc
  soc: ti: knav_dma: rename pad in struct knav_dma_desc to sw_data
  net: ti: netcp: restore get/set_pad_info() functionality
  MAINTAINERS: Drop myself as xen netback maintainer
  sctp: Fix port hash table size computation
  can: ems_usb: Fix possible tx overflow
  Bluetooth: hci_core: Avoid mixing up req_complete and req_complete_skb
  net: bcmgenet: Fix internal PHY link state
  af_unix: Don't use continue to re-execute unix_stream_read_generic loop
  unix_diag: fix incorrect sign extension in unix_lookup_by_ino
  bnxt_en: Failure to update PHY is not fatal condition.
  bnxt_en: Remove unnecessary call to update PHY settings.
  ...

11 files changed, 101 insertions, 38 deletions

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index cebd9d31e65a..f6303b17546b 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1847,7 +1847,7 @@ static int inet_netconf_get_devconf(struct sk_buff *in_skb,
 	if (err < 0)
 		goto errout;
 
-	err = EINVAL;
+	err = -EINVAL;
 	if (!tb[NETCONFA_IFINDEX])
 		goto errout;
 
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 46b9c887bede..64148914803a 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -789,14 +789,16 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req,
 	reqsk_put(req);
 }
 
-void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req,
-			      struct sock *child)
+struct sock *inet_csk_reqsk_queue_add(struct sock *sk,
+				      struct request_sock *req,
+				      struct sock *child)
 {
 	struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
 
 	spin_lock(&queue->rskq_lock);
 	if (unlikely(sk->sk_state != TCP_LISTEN)) {
 		inet_child_forget(sk, req, child);
+		child = NULL;
 	} else {
 		req->sk = child;
 		req->dl_next = NULL;
@@ -808,6 +810,7 @@ void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req,
 		sk_acceptq_added(sk);
 	}
 	spin_unlock(&queue->rskq_lock);
+	return child;
 }
 EXPORT_SYMBOL(inet_csk_reqsk_queue_add);
 
@@ -817,11 +820,8 @@ struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child,
 	if (own_req) {
 		inet_csk_reqsk_queue_drop(sk, req);
 		reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req);
-		inet_csk_reqsk_queue_add(sk, req, child);
-		/* Warning: caller must not call reqsk_put(req);
-		 * child stole last reference on it.
-		 */
-		return child;
+		if (inet_csk_reqsk_queue_add(sk, req, child))
+			return child;
 	}
 	/* Too bad, another child took ownership of the request, undo. */
 	bh_unlock_sock(child);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 56fdf4e0dce4..41ba68de46d8 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1054,8 +1054,9 @@ static const struct net_device_ops gre_tap_netdev_ops = {
 static void ipgre_tap_setup(struct net_device *dev)
 {
 	ether_setup(dev);
-	dev->netdev_ops		= &gre_tap_netdev_ops;
-	dev->priv_flags 	|= IFF_LIVE_ADDR_CHANGE;
+	dev->netdev_ops	= &gre_tap_netdev_ops;
+	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
+	dev->priv_flags	|= IFF_LIVE_ADDR_CHANGE;
 	ip_tunnel_setup(dev, gre_tap_net_id);
 }
 
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 5f73a7c03e27..a50124260f5a 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -249,6 +249,8 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc,
 		switch (cmsg->cmsg_type) {
 		case IP_RETOPTS:
 			err = cmsg->cmsg_len - CMSG_ALIGN(sizeof(struct cmsghdr));
+
+			/* Our caller is responsible for freeing ipc->opt */
 			err = ip_options_get(net, &ipc->opt, CMSG_DATA(cmsg),
 					     err < 40 ? err : 40);
 			if (err)
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index c117b21b937d..d3a27165f9cc 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -746,8 +746,10 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	if (msg->msg_controllen) {
 		err = ip_cmsg_send(sock_net(sk), msg, &ipc, false);
-		if (err)
+		if (unlikely(err)) {
+			kfree(ipc.opt);
 			return err;
+		}
 		if (ipc.opt)
 			free = 1;
 	}
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index bc35f1842512..7113bae4e6a0 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -547,8 +547,10 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	if (msg->msg_controllen) {
 		err = ip_cmsg_send(net, msg, &ipc, false);
-		if (err)
+		if (unlikely(err)) {
+			kfree(ipc.opt);
 			goto out;
+		}
 		if (ipc.opt)
 			free = 1;
 	}
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 85f184e429c6..02c62299d717 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -129,6 +129,7 @@ static int ip_rt_mtu_expires __read_mostly	= 10 * 60 * HZ;
 static int ip_rt_min_pmtu __read_mostly		= 512 + 20 + 20;
 static int ip_rt_min_advmss __read_mostly	= 256;
 
+static int ip_rt_gc_timeout __read_mostly	= RT_GC_TIMEOUT;
 /*
  *	Interface to generic destination cache.
  */
@@ -755,7 +756,7 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
 				struct fib_nh *nh = &FIB_RES_NH(res);
 
 				update_or_create_fnhe(nh, fl4->daddr, new_gw,
-						      0, 0);
+						0, jiffies + ip_rt_gc_timeout);
 			}
 			if (kill_route)
 				rt->dst.obsolete = DST_OBSOLETE_KILL;
@@ -1556,6 +1557,36 @@ static void ip_handle_martian_source(struct net_device *dev,
 #endif
 }
 
+static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr)
+{
+	struct fnhe_hash_bucket *hash;
+	struct fib_nh_exception *fnhe, __rcu **fnhe_p;
+	u32 hval = fnhe_hashfun(daddr);
+
+	spin_lock_bh(&fnhe_lock);
+
+	hash = rcu_dereference_protected(nh->nh_exceptions,
+					 lockdep_is_held(&fnhe_lock));
+	hash += hval;
+
+	fnhe_p = &hash->chain;
+	fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock));
+	while (fnhe) {
+		if (fnhe->fnhe_daddr == daddr) {
+			rcu_assign_pointer(*fnhe_p, rcu_dereference_protected(
+				fnhe->fnhe_next, lockdep_is_held(&fnhe_lock)));
+			fnhe_flush_routes(fnhe);
+			kfree_rcu(fnhe, rcu);
+			break;
+		}
+		fnhe_p = &fnhe->fnhe_next;
+		fnhe = rcu_dereference_protected(fnhe->fnhe_next,
+						 lockdep_is_held(&fnhe_lock));
+	}
+
+	spin_unlock_bh(&fnhe_lock);
+}
+
 /* called in rcu_read_lock() section */
 static int __mkroute_input(struct sk_buff *skb,
 			   const struct fib_result *res,
@@ -1609,11 +1640,20 @@ static int __mkroute_input(struct sk_buff *skb,
 
 	fnhe = find_exception(&FIB_RES_NH(*res), daddr);
 	if (do_cache) {
-		if (fnhe)
+		if (fnhe) {
 			rth = rcu_dereference(fnhe->fnhe_rth_input);
-		else
-			rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
+			if (rth && rth->dst.expires &&
+			    time_after(jiffies, rth->dst.expires)) {
+				ip_del_fnhe(&FIB_RES_NH(*res), daddr);
+				fnhe = NULL;
+			} else {
+				goto rt_cache;
+			}
+		}
+
+		rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
 
+rt_cache:
 		if (rt_cache_valid(rth)) {
 			skb_dst_set_noref(skb, &rth->dst);
 			goto out;
@@ -2014,19 +2054,29 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 		struct fib_nh *nh = &FIB_RES_NH(*res);
 
 		fnhe = find_exception(nh, fl4->daddr);
-		if (fnhe)
+		if (fnhe) {
 			prth = &fnhe->fnhe_rth_output;
-		else {
-			if (unlikely(fl4->flowi4_flags &
-				     FLOWI_FLAG_KNOWN_NH &&
-				     !(nh->nh_gw &&
-				       nh->nh_scope == RT_SCOPE_LINK))) {
-				do_cache = false;
-				goto add;
+			rth = rcu_dereference(*prth);
+			if (rth && rth->dst.expires &&
+			    time_after(jiffies, rth->dst.expires)) {
+				ip_del_fnhe(nh, fl4->daddr);
+				fnhe = NULL;
+			} else {
+				goto rt_cache;
 			}
-			prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
 		}
+
+		if (unlikely(fl4->flowi4_flags &
+			     FLOWI_FLAG_KNOWN_NH &&
+			     !(nh->nh_gw &&
+			       nh->nh_scope == RT_SCOPE_LINK))) {
+			do_cache = false;
+			goto add;
+		}
+		prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
 		rth = rcu_dereference(*prth);
+
+rt_cache:
 		if (rt_cache_valid(rth)) {
 			dst_hold(&rth->dst);
 			return rth;
@@ -2569,7 +2619,6 @@ void ip_rt_multicast_event(struct in_device *in_dev)
 }
 
 #ifdef CONFIG_SYSCTL
-static int ip_rt_gc_timeout __read_mostly	= RT_GC_TIMEOUT;
 static int ip_rt_gc_interval __read_mostly  = 60 * HZ;
 static int ip_rt_gc_min_interval __read_mostly	= HZ / 2;
 static int ip_rt_gc_elasticity __read_mostly	= 8;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 0c36ef4a3f86..483ffdf5aa4d 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2950,7 +2950,7 @@ static void __tcp_alloc_md5sig_pool(void)
 			struct crypto_hash *hash;
 
 			hash = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC);
-			if (IS_ERR_OR_NULL(hash))
+			if (IS_ERR(hash))
 				return;
 			per_cpu(tcp_md5sig_pool, cpu).md5_desc.tfm = hash;
 		}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 1c2a73406261..3b2c8e90a475 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2896,7 +2896,10 @@ static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us)
 {
 	const u32 now = tcp_time_stamp, wlen = sysctl_tcp_min_rtt_wlen * HZ;
 	struct rtt_meas *m = tcp_sk(sk)->rtt_min;
-	struct rtt_meas rttm = { .rtt = (rtt_us ? : 1), .ts = now };
+	struct rtt_meas rttm = {
+		.rtt = likely(rtt_us) ? rtt_us : jiffies_to_usecs(1),
+		.ts = now,
+	};
 	u32 elapsed;
 
 	/* Check if the new measurement updates the 1st, 2nd, or 3rd choices */
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 7f6ff037adaf..487ac67059e2 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1597,28 +1597,30 @@ process:
 
 	if (sk->sk_state == TCP_NEW_SYN_RECV) {
 		struct request_sock *req = inet_reqsk(sk);
-		struct sock *nsk = NULL;
+		struct sock *nsk;
 
 		sk = req->rsk_listener;
-		if (tcp_v4_inbound_md5_hash(sk, skb))
-			goto discard_and_relse;
-		if (likely(sk->sk_state == TCP_LISTEN)) {
-			nsk = tcp_check_req(sk, skb, req, false);
-		} else {
+		if (unlikely(tcp_v4_inbound_md5_hash(sk, skb))) {
+			reqsk_put(req);
+			goto discard_it;
+		}
+		if (unlikely(sk->sk_state != TCP_LISTEN)) {
 			inet_csk_reqsk_queue_drop_and_put(sk, req);
 			goto lookup;
 		}
+		sock_hold(sk);
+		nsk = tcp_check_req(sk, skb, req, false);
 		if (!nsk) {
 			reqsk_put(req);
-			goto discard_it;
+			goto discard_and_relse;
 		}
 		if (nsk == sk) {
-			sock_hold(sk);
 			reqsk_put(req);
 		} else if (tcp_child_process(sk, nsk, skb)) {
 			tcp_v4_send_reset(nsk, skb);
-			goto discard_it;
+			goto discard_and_relse;
 		} else {
+			sock_put(sk);
 			return 0;
 		}
 	}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index be0b21852b13..95d2f198017e 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1048,8 +1048,10 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	if (msg->msg_controllen) {
 		err = ip_cmsg_send(sock_net(sk), msg, &ipc,
 				   sk->sk_family == AF_INET6);
-		if (err)
+		if (unlikely(err)) {
+			kfree(ipc.opt);
 			return err;
+		}
 		if (ipc.opt)
 			free = 1;
 		connected = 0;