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

Pull networking fixes from David Miller:

 1) Use an appropriate TSQ pacing shift in mac80211, from Toke
    Høiland-Jørgensen.

 2) Just like ipv4's ip_route_me_harder(), we have to use skb_to_full_sk
    in ip6_route_me_harder, from Eric Dumazet.

 3) Fix several shutdown races and similar other problems in l2tp, from
    James Chapman.

 4) Handle missing XDP flush properly in tuntap, for real this time.
    From Jason Wang.

 5) Out-of-bounds access in powerpc ebpf tailcalls, from Daniel
    Borkmann.

 6) Fix phy_resume() locking, from Andrew Lunn.

 7) IFLA_MTU values are ignored on newlink for some tunnel types, fix
    from Xin Long.

 8) Revert F-RTO middle box workarounds, they only handle one dimension
    of the problem. From Yuchung Cheng.

 9) Fix socket refcounting in RDS, from Ka-Cheong Poon.

10) Don't allow ppp unit registration to an unregistered channel, from
    Guillaume Nault.

11) Various hv_netvsc fixes from Stephen Hemminger.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (98 commits)
  hv_netvsc: propagate rx filters to VF
  hv_netvsc: filter multicast/broadcast
  hv_netvsc: defer queue selection to VF
  hv_netvsc: use napi_schedule_irqoff
  hv_netvsc: fix race in napi poll when rescheduling
  hv_netvsc: cancel subchannel setup before halting device
  hv_netvsc: fix error unwind handling if vmbus_open fails
  hv_netvsc: only wake transmit queue if link is up
  hv_netvsc: avoid retry on send during shutdown
  virtio-net: re enable XDP_REDIRECT for mergeable buffer
  ppp: prevent unregistered channels from connecting to PPP units
  tc-testing: skbmod: fix match value of ethertype
  mlxsw: spectrum_switchdev: Check success of FDB add operation
  net: make skb_gso_*_seglen functions private
  net: xfrm: use skb_gso_validate_network_len() to check gso sizes
  net: sched: tbf: handle GSO_BY_FRAGS case in enqueue
  net: rename skb_gso_validate_mtu -> skb_gso_validate_network_len
  rds: Incorrect reference counting in TCP socket creation
  net: ethtool: don't ignore return from driver get_fecparam method
  vrf: check forwarding on the original netdevice when generating ICMP dest unreachable
  ...

10 files changed, 43 insertions, 44 deletions

diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 2dd21c3281a1..b54b948b0596 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -55,7 +55,7 @@ static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
 	if (skb->ignore_df)
 		return false;
 
-	if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu))
+	if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu))
 		return false;
 
 	return true;
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 45d97e9b2759..0901de42ed85 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -970,9 +970,6 @@ static void __gre_tunnel_init(struct net_device *dev)
 
 	t_hlen = tunnel->hlen + sizeof(struct iphdr);
 
-	dev->needed_headroom	= LL_MAX_HEADER + t_hlen + 4;
-	dev->mtu		= ETH_DATA_LEN - t_hlen - 4;
-
 	dev->features		|= GRE_FEATURES;
 	dev->hw_features	|= GRE_FEATURES;
 
@@ -1290,8 +1287,6 @@ static int erspan_tunnel_init(struct net_device *dev)
 		       erspan_hdr_len(tunnel->erspan_ver);
 	t_hlen = tunnel->hlen + sizeof(struct iphdr);
 
-	dev->needed_headroom = LL_MAX_HEADER + t_hlen + 4;
-	dev->mtu = ETH_DATA_LEN - t_hlen - 4;
 	dev->features		|= GRE_FEATURES;
 	dev->hw_features	|= GRE_FEATURES;
 	dev->priv_flags		|= IFF_LIVE_ADDR_CHANGE;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index e8e675be60ec..66340ab750e6 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -248,7 +248,7 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk,
 
 	/* common case: seglen is <= mtu
 	 */
-	if (skb_gso_validate_mtu(skb, mtu))
+	if (skb_gso_validate_network_len(skb, mtu))
 		return ip_finish_output2(net, sk, skb);
 
 	/* Slowpath -  GSO segment length exceeds the egress MTU.
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index d786a8441bce..6d21068f9b55 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -710,16 +710,9 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		}
 	}
 
-	if (tunnel->fwmark) {
-		init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr,
-				 tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link,
-				 tunnel->fwmark);
-	}
-	else {
-		init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr,
-				 tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link,
-				 skb->mark);
-	}
+	init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr,
+			 tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link,
+			 tunnel->fwmark);
 
 	if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0)
 		goto tx_error;
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index 4b02ab39ebc5..8a8ae61cea71 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -232,7 +232,6 @@ clusterip_config_init(struct net *net, const struct ipt_clusterip_tgt_info *i,
 	c->hash_mode = i->hash_mode;
 	c->hash_initval = i->hash_initval;
 	refcount_set(&c->refcount, 1);
-	refcount_set(&c->entries, 1);
 
 	spin_lock_bh(&cn->lock);
 	if (__clusterip_config_find(net, ip)) {
@@ -263,8 +262,10 @@ clusterip_config_init(struct net *net, const struct ipt_clusterip_tgt_info *i,
 
 	c->notifier.notifier_call = clusterip_netdev_event;
 	err = register_netdevice_notifier(&c->notifier);
-	if (!err)
+	if (!err) {
+		refcount_set(&c->entries, 1);
 		return c;
+	}
 
 #ifdef CONFIG_PROC_FS
 	proc_remove(c->pde);
@@ -273,7 +274,7 @@ err:
 	spin_lock_bh(&cn->lock);
 	list_del_rcu(&c->list);
 	spin_unlock_bh(&cn->lock);
-	kfree(c);
+	clusterip_config_put(c);
 
 	return ERR_PTR(err);
 }
@@ -496,12 +497,15 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par)
 				return PTR_ERR(config);
 		}
 	}
-	cipinfo->config = config;
 
 	ret = nf_ct_netns_get(par->net, par->family);
-	if (ret < 0)
+	if (ret < 0) {
 		pr_info("cannot load conntrack support for proto=%u\n",
 			par->family);
+		clusterip_config_entry_put(par->net, config);
+		clusterip_config_put(config);
+		return ret;
+	}
 
 	if (!par->net->xt.clusterip_deprecated_warning) {
 		pr_info("ipt_CLUSTERIP is deprecated and it will removed soon, "
@@ -509,6 +513,7 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par)
 		par->net->xt.clusterip_deprecated_warning = true;
 	}
 
+	cipinfo->config = config;
 	return ret;
 }
 
diff --git a/net/ipv4/netfilter/nf_flow_table_ipv4.c b/net/ipv4/netfilter/nf_flow_table_ipv4.c
index 25d2975da156..0cd46bffa469 100644
--- a/net/ipv4/netfilter/nf_flow_table_ipv4.c
+++ b/net/ipv4/netfilter/nf_flow_table_ipv4.c
@@ -111,6 +111,7 @@ static int nf_flow_dnat_ip(const struct flow_offload *flow, struct sk_buff *skb,
 	default:
 		return -1;
 	}
+	csum_replace4(&iph->check, addr, new_addr);
 
 	return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr);
 }
@@ -185,7 +186,7 @@ static bool __nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
 	if ((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0)
 		return false;
 
-	if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu))
+	if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu))
 		return false;
 
 	return true;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index a4f44d815a61..860b3fd2f54b 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -128,10 +128,11 @@ static int ip_rt_redirect_silence __read_mostly	= ((HZ / 50) << (9 + 1));
 static int ip_rt_error_cost __read_mostly	= HZ;
 static int ip_rt_error_burst __read_mostly	= 5 * HZ;
 static int ip_rt_mtu_expires __read_mostly	= 10 * 60 * HZ;
-static int ip_rt_min_pmtu __read_mostly		= 512 + 20 + 20;
+static u32 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.
  */
@@ -930,14 +931,23 @@ out_put_peer:
 
 static int ip_error(struct sk_buff *skb)
 {
-	struct in_device *in_dev = __in_dev_get_rcu(skb->dev);
 	struct rtable *rt = skb_rtable(skb);
+	struct net_device *dev = skb->dev;
+	struct in_device *in_dev;
 	struct inet_peer *peer;
 	unsigned long now;
 	struct net *net;
 	bool send;
 	int code;
 
+	if (netif_is_l3_master(skb->dev)) {
+		dev = __dev_get_by_index(dev_net(skb->dev), IPCB(skb)->iif);
+		if (!dev)
+			goto out;
+	}
+
+	in_dev = __in_dev_get_rcu(dev);
+
 	/* IP on this device is disabled. */
 	if (!in_dev)
 		goto out;
@@ -2818,6 +2828,7 @@ void ip_rt_multicast_event(struct in_device *in_dev)
 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;
+static int ip_min_valid_pmtu __read_mostly	= IPV4_MIN_MTU;
 
 static int ipv4_sysctl_rtcache_flush(struct ctl_table *__ctl, int write,
 					void __user *buffer,
@@ -2933,7 +2944,8 @@ static struct ctl_table ipv4_route_table[] = {
 		.data		= &ip_rt_min_pmtu,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &ip_min_valid_pmtu,
 	},
 	{
 		.procname	= "min_adv_mss",
diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c
index 7c843578f233..faddf4f9a707 100644
--- a/net/ipv4/tcp_illinois.c
+++ b/net/ipv4/tcp_illinois.c
@@ -6,7 +6,7 @@
  * The algorithm is described in:
  * "TCP-Illinois: A Loss and Delay-Based Congestion Control Algorithm
  *  for High-Speed Networks"
- * http://www.ifp.illinois.edu/~srikant/Papers/liubassri06perf.pdf
+ * http://tamerbasar.csl.illinois.edu/LiuBasarSrikantPerfEvalArtJun2008.pdf
  *
  * Implemented from description in paper and ns-2 simulation.
  * Copyright (C) 2007 Stephen Hemminger <shemminger@linux-foundation.org>
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 575d3c1fb6e8..9a1b3c1c1c14 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1971,11 +1971,6 @@ void tcp_enter_loss(struct sock *sk)
 	/* F-RTO RFC5682 sec 3.1 step 1: retransmit SND.UNA if no previous
 	 * loss recovery is underway except recurring timeout(s) on
 	 * the same SND.UNA (sec 3.2). Disable F-RTO on path MTU probing
-	 *
-	 * In theory F-RTO can be used repeatedly during loss recovery.
-	 * In practice this interacts badly with broken middle-boxes that
-	 * falsely raise the receive window, which results in repeated
-	 * timeouts and stop-and-go behavior.
 	 */
 	tp->frto = net->ipv4.sysctl_tcp_frto &&
 		   (new_recovery || icsk->icsk_retransmits) &&
@@ -2631,18 +2626,14 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack,
 	    tcp_try_undo_loss(sk, false))
 		return;
 
-	/* The ACK (s)acks some never-retransmitted data meaning not all
-	 * the data packets before the timeout were lost. Therefore we
-	 * undo the congestion window and state. This is essentially
-	 * the operation in F-RTO (RFC5682 section 3.1 step 3.b). Since
-	 * a retransmitted skb is permantly marked, we can apply such an
-	 * operation even if F-RTO was not used.
-	 */
-	if ((flag & FLAG_ORIG_SACK_ACKED) &&
-	    tcp_try_undo_loss(sk, tp->undo_marker))
-		return;
-
 	if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */
+		/* Step 3.b. A timeout is spurious if not all data are
+		 * lost, i.e., never-retransmitted data are (s)acked.
+		 */
+		if ((flag & FLAG_ORIG_SACK_ACKED) &&
+		    tcp_try_undo_loss(sk, true))
+			return;
+
 		if (after(tp->snd_nxt, tp->high_seq)) {
 			if (flag & FLAG_DATA_SACKED || is_dupack)
 				tp->frto = 0; /* Step 3.a. loss was real */
@@ -4001,6 +3992,7 @@ void tcp_reset(struct sock *sk)
 	/* This barrier is coupled with smp_rmb() in tcp_poll() */
 	smp_wmb();
 
+	tcp_write_queue_purge(sk);
 	tcp_done(sk);
 
 	if (!sock_flag(sk, SOCK_DEAD))
diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
index 94b8702603bc..be980c195fc5 100644
--- a/net/ipv4/xfrm4_output.c
+++ b/net/ipv4/xfrm4_output.c
@@ -30,7 +30,8 @@ static int xfrm4_tunnel_check_size(struct sk_buff *skb)
 
 	mtu = dst_mtu(skb_dst(skb));
 	if ((!skb_is_gso(skb) && skb->len > mtu) ||
-	    (skb_is_gso(skb) && skb_gso_network_seglen(skb) > ip_skb_dst_mtu(skb->sk, skb))) {
+	    (skb_is_gso(skb) &&
+	     !skb_gso_validate_network_len(skb, ip_skb_dst_mtu(skb->sk, skb)))) {
 		skb->protocol = htons(ETH_P_IP);
 
 		if (skb->sk)