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

Pull networking fixes from David Miller:

 1) MLX5 bug fixes from Saeed Mahameed et al:
     - released wrong resources when firmware timeout happens
     - fix wrong check for encapsulation size limits
     - UAR memory leak
     - ETHTOOL_GRXCLSRLALL failed to fill in info->data

 2) Don't cache l3mdev on mis-matches local route, causes net devices to
    leak refs. From Robert Shearman.

 3) Handle fragmented SKBs properly in macsec driver, the problem is
    that we were mis-sizing the sgvec table. From Jason A. Donenfeld.

 4) We cannot have checksum offload enabled for inner UDP tunneled
    packet during IPSEC, from Ansis Atteka.

 5) Fix double SKB free in ravb driver, from Dan Carpenter.

 6) Fix CPU port handling in b53 DSA driver, from Florian Dainelli.

 7) Don't use on-stack buffers for usb_control_msg() in CAN usb driver,
    from Maksim Salau.

 8) Fix device leak in macvlan driver, from Herbert Xu. We have to purge
    the broadcast queue properly on port destroy.

 9) Fix tx ring entry limit on EF10 devices in sfc driver. From Bert
    Kenward.

10) Fix memory leaks in team driver, from Pan Bian.

11) Don't setup ipv6_stub before it can be actually used, from Paolo
    Abeni.

12) Fix tipc socket flow control accounting, from Parthasarathy
    Bhuvaragan.

13) Fix crash on module unload in hso driver, from Andreas Kemnade.

14) Fix purging of bridge multicast entries, the problem is that if we
    don't defer it to ndo_uninit it's possible for new entries to get
    added after we purge. Fix from Xin Long.

15) Don't return garbage for PACKET_HDRLEN getsockopt, from Alexander
    Potapenko.

16) Fix autoneg stall properly in PHY layer, and revert micrel driver
    change that was papering over it. From Alexander Kochetkov.

17) Don't dereference an ipv4 route as an ipv6 one in the ip6_tunnnel
    code, from Cong Wang.

18) Clear out the congestion control private of the TCP socket in all of
    the right places, from Wei Wang.

19) rawv6_ioctl measures SKB length incorrectly, fix from Jamie
    Bainbridge.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (41 commits)
  ipv6: check raw payload size correctly in ioctl
  tcp: memset ca_priv data to 0 properly
  ipv6: check skb->protocol before lookup for nexthop
  net: core: Prevent from dereferencing null pointer when releasing SKB
  macsec: dynamically allocate space for sglist
  Revert "phy: micrel: Disable auto negotiation on startup"
  net: phy: fix auto-negotiation stall due to unavailable interrupt
  net/packet: check length in getsockopt() called with PACKET_HDRLEN
  net: ipv6: regenerate host route if moved to gc list
  bridge: move bridge multicast cleanup to ndo_uninit
  ipv6: fix source routing
  qed: Fix error in the dcbx app meta data initialization.
  netvsc: fix calculation of available send sections
  net: hso: fix module unloading
  tipc: fix socket flow control accounting error at tipc_recv_stream
  tipc: fix socket flow control accounting error at tipc_send_stream
  ipv6: move stub initialization after ipv6 setup completion
  team: fix memory leaks
  sfc: tx ring can only have 2048 entries for all EF10 NICs
  macvlan: Fix device ref leak when purging bc_queue
  ...

14 files changed, 57 insertions, 35 deletions

diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 90f49a194249..430b53e7d941 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -123,6 +123,7 @@ static void br_dev_uninit(struct net_device *dev)
 {
 	struct net_bridge *br = netdev_priv(dev);
 
+	br_multicast_dev_del(br);
 	br_multicast_uninit_stats(br);
 	br_vlan_flush(br);
 	free_percpu(br->stats);
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index 56a2a72e7738..a8d0ed282a10 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -311,7 +311,6 @@ void br_dev_delete(struct net_device *dev, struct list_head *head)
 
 	br_fdb_delete_by_port(br, NULL, 0, 1);
 
-	br_multicast_dev_del(br);
 	cancel_delayed_work_sync(&br->gc_work);
 
 	br_sysfs_delbr(br->dev);
diff --git a/net/core/dev.c b/net/core/dev.c
index 533a6d6f6092..9b5875388c23 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2450,6 +2450,9 @@ void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason)
 {
 	unsigned long flags;
 
+	if (unlikely(!skb))
+		return;
+
 	if (likely(atomic_read(&skb->users) == 1)) {
 		smp_rmb();
 		atomic_set(&skb->users, 0);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index acd69cfe2951..d9724889ff09 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2359,7 +2359,8 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
 		}
 
 		/* L3 master device is the loopback for that domain */
-		dev_out = l3mdev_master_dev_rcu(dev_out) ? : net->loopback_dev;
+		dev_out = l3mdev_master_dev_rcu(FIB_RES_DEV(res)) ? :
+			net->loopback_dev;
 		fl4->flowi4_oif = dev_out->ifindex;
 		flags |= RTCF_LOCAL;
 		goto make_route;
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 79c4817abc94..6e3c512054a6 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -168,12 +168,8 @@ void tcp_assign_congestion_control(struct sock *sk)
 	}
 out:
 	rcu_read_unlock();
+	memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
 
-	/* Clear out private data before diag gets it and
-	 * the ca has not been initialized.
-	 */
-	if (ca->get_info)
-		memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
 	if (ca->flags & TCP_CONG_NEEDS_ECN)
 		INET_ECN_xmit(sk);
 	else
@@ -200,11 +196,10 @@ static void tcp_reinit_congestion_control(struct sock *sk,
 	tcp_cleanup_congestion_control(sk);
 	icsk->icsk_ca_ops = ca;
 	icsk->icsk_ca_setsockopt = 1;
+	memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
 
-	if (sk->sk_state != TCP_CLOSE) {
-		memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
+	if (sk->sk_state != TCP_CLOSE)
 		tcp_init_congestion_control(sk);
-	}
 }
 
 /* Manage refcounts on socket close. */
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index b2be1d9757ef..781250151d40 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -29,6 +29,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 	u16 mac_len = skb->mac_len;
 	int udp_offset, outer_hlen;
 	__wsum partial;
+	bool need_ipsec;
 
 	if (unlikely(!pskb_may_pull(skb, tnl_hlen)))
 		goto out;
@@ -62,8 +63,10 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 
 	ufo = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP);
 
+	need_ipsec = skb_dst(skb) && dst_xfrm(skb_dst(skb));
 	/* Try to offload checksum if possible */
 	offload_csum = !!(need_csum &&
+			  !need_ipsec &&
 			  (skb->dev->features &
 			   (is_ipv6 ? (NETIF_F_HW_CSUM | NETIF_F_IPV6_CSUM) :
 				      (NETIF_F_HW_CSUM | NETIF_F_IP_CSUM))));
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 80ce478c4851..0ea96c4d334d 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3271,14 +3271,24 @@ static void addrconf_gre_config(struct net_device *dev)
 static int fixup_permanent_addr(struct inet6_dev *idev,
 				struct inet6_ifaddr *ifp)
 {
-	if (!ifp->rt) {
-		struct rt6_info *rt;
+	/* rt6i_ref == 0 means the host route was removed from the
+	 * FIB, for example, if 'lo' device is taken down. In that
+	 * case regenerate the host route.
+	 */
+	if (!ifp->rt || !atomic_read(&ifp->rt->rt6i_ref)) {
+		struct rt6_info *rt, *prev;
 
 		rt = addrconf_dst_alloc(idev, &ifp->addr, false);
 		if (unlikely(IS_ERR(rt)))
 			return PTR_ERR(rt);
 
+		/* ifp->rt can be accessed outside of rtnl */
+		spin_lock(&ifp->lock);
+		prev = ifp->rt;
 		ifp->rt = rt;
+		spin_unlock(&ifp->lock);
+
+		ip6_rt_put(prev);
 	}
 
 	if (!(ifp->flags & IFA_F_NOPREFIXROUTE)) {
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index a9a9553ee63d..e82e59f22dfc 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -933,8 +933,6 @@ static int __init inet6_init(void)
 	if (err)
 		goto igmp_fail;
 
-	ipv6_stub = &ipv6_stub_impl;
-
 	err = ipv6_netfilter_init();
 	if (err)
 		goto netfilter_fail;
@@ -1010,6 +1008,10 @@ static int __init inet6_init(void)
 	if (err)
 		goto sysctl_fail;
 #endif
+
+	/* ensure that ipv6 stubs are visible only after ipv6 is ready */
+	wmb();
+	ipv6_stub = &ipv6_stub_impl;
 out:
 	return err;
 
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 25192a3b0cd7..d32e2110aff2 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -909,6 +909,8 @@ static void ipv6_push_rthdr(struct sk_buff *skb, u8 *proto,
 {
 	switch (opt->type) {
 	case IPV6_SRCRT_TYPE_0:
+	case IPV6_SRCRT_STRICT:
+	case IPV6_SRCRT_TYPE_2:
 		ipv6_push_rthdr0(skb, proto, opt, addr_p, saddr);
 		break;
 	case IPV6_SRCRT_TYPE_4:
@@ -1163,6 +1165,8 @@ struct in6_addr *fl6_update_dst(struct flowi6 *fl6,
 
 	switch (opt->srcrt->type) {
 	case IPV6_SRCRT_TYPE_0:
+	case IPV6_SRCRT_STRICT:
+	case IPV6_SRCRT_TYPE_2:
 		fl6->daddr = *((struct rt0_hdr *)opt->srcrt)->addr;
 		break;
 	case IPV6_SRCRT_TYPE_4:
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 75fac933c209..a9692ec0cd6d 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1037,7 +1037,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 	struct ip6_tnl *t = netdev_priv(dev);
 	struct net *net = t->net;
 	struct net_device_stats *stats = &t->dev->stats;
-	struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+	struct ipv6hdr *ipv6h;
 	struct ipv6_tel_txoption opt;
 	struct dst_entry *dst = NULL, *ndst = NULL;
 	struct net_device *tdev;
@@ -1057,26 +1057,28 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 
 	/* NBMA tunnel */
 	if (ipv6_addr_any(&t->parms.raddr)) {
-		struct in6_addr *addr6;
-		struct neighbour *neigh;
-		int addr_type;
+		if (skb->protocol == htons(ETH_P_IPV6)) {
+			struct in6_addr *addr6;
+			struct neighbour *neigh;
+			int addr_type;
 
-		if (!skb_dst(skb))
-			goto tx_err_link_failure;
+			if (!skb_dst(skb))
+				goto tx_err_link_failure;
 
-		neigh = dst_neigh_lookup(skb_dst(skb),
-					 &ipv6_hdr(skb)->daddr);
-		if (!neigh)
-			goto tx_err_link_failure;
+			neigh = dst_neigh_lookup(skb_dst(skb),
+						 &ipv6_hdr(skb)->daddr);
+			if (!neigh)
+				goto tx_err_link_failure;
 
-		addr6 = (struct in6_addr *)&neigh->primary_key;
-		addr_type = ipv6_addr_type(addr6);
+			addr6 = (struct in6_addr *)&neigh->primary_key;
+			addr_type = ipv6_addr_type(addr6);
 
-		if (addr_type == IPV6_ADDR_ANY)
-			addr6 = &ipv6_hdr(skb)->daddr;
+			if (addr_type == IPV6_ADDR_ANY)
+				addr6 = &ipv6_hdr(skb)->daddr;
 
-		memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr));
-		neigh_release(neigh);
+			memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr));
+			neigh_release(neigh);
+		}
 	} else if (!(t->parms.flags &
 		     (IP6_TNL_F_USE_ORIG_TCLASS | IP6_TNL_F_USE_ORIG_FWMARK))) {
 		/* enable the cache only only if the routing decision does
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 7ebac630d3c6..cb1766724a4c 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1749,7 +1749,8 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event,
 		idev = in6_dev_get(dev);
 		if (!idev)
 			break;
-		if (idev->cnf.ndisc_notify)
+		if (idev->cnf.ndisc_notify ||
+		    net->ipv6.devconf_all->ndisc_notify)
 			ndisc_send_unsol_na(dev);
 		in6_dev_put(idev);
 		break;
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index f174e76e6505..0da6a12b5472 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -1178,8 +1178,7 @@ static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg)
 		spin_lock_bh(&sk->sk_receive_queue.lock);
 		skb = skb_peek(&sk->sk_receive_queue);
 		if (skb)
-			amount = skb_tail_pointer(skb) -
-				skb_transport_header(skb);
+			amount = skb->len;
 		spin_unlock_bh(&sk->sk_receive_queue.lock);
 		return put_user(amount, (int __user *)arg);
 	}
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 8489beff5c25..ea81ccf3c7d6 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3836,6 +3836,8 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
 	case PACKET_HDRLEN:
 		if (len > sizeof(int))
 			len = sizeof(int);
+		if (len < sizeof(int))
+			return -EINVAL;
 		if (copy_from_user(&val, optval, len))
 			return -EFAULT;
 		switch (val) {
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 7130e73bd42c..566906795c8c 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1083,7 +1083,7 @@ static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dlen)
 		}
 	} while (sent < dlen && !rc);
 
-	return rc ? rc : sent;
+	return sent ? sent : rc;
 }
 
 /**
@@ -1484,7 +1484,7 @@ restart:
 	if (unlikely(flags & MSG_PEEK))
 		goto exit;
 
-	tsk->rcv_unacked += tsk_inc(tsk, hlen + sz);
+	tsk->rcv_unacked += tsk_inc(tsk, hlen + msg_data_sz(msg));
 	if (unlikely(tsk->rcv_unacked >= (tsk->rcv_win / 4)))
 		tipc_sk_send_ack(tsk);
 	tsk_advance_rx_queue(sk);