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

Pull networking fixes from David Miller:
 "A decent batch of fixes here. I'd say about half are for problems that
  have existed for a while, and half are for new regressions added in
  the 4.20 merge window.

   1) Fix 10G SFP phy module detection in mvpp2, from Baruch Siach.

   2) Revert bogus emac driver change, from Benjamin Herrenschmidt.

   3) Handle BPF exported data structure with pointers when building
      32-bit userland, from Daniel Borkmann.

   4) Memory leak fix in act_police, from Davide Caratti.

   5) Check RX checksum offload in RX descriptors properly in aquantia
      driver, from Dmitry Bogdanov.

   6) SKB unlink fix in various spots, from Edward Cree.

   7) ndo_dflt_fdb_dump() only works with ethernet, enforce this, from
      Eric Dumazet.

   8) Fix FID leak in mlxsw driver, from Ido Schimmel.

   9) IOTLB locking fix in vhost, from Jean-Philippe Brucker.

  10) Fix SKB truesize accounting in ipv4/ipv6/netfilter frag memory
      limits otherwise namespace exit can hang. From Jiri Wiesner.

  11) Address block parsing length fixes in x25 from Martin Schiller.

  12) IRQ and ring accounting fixes in bnxt_en, from Michael Chan.

  13) For tun interfaces, only iface delete works with rtnl ops, enforce
      this by disallowing add. From Nicolas Dichtel.

  14) Use after free in liquidio, from Pan Bian.

  15) Fix SKB use after passing to netif_receive_skb(), from Prashant
      Bhole.

  16) Static key accounting and other fixes in XPS from Sabrina Dubroca.

  17) Partially initialized flow key passed to ip6_route_output(), from
      Shmulik Ladkani.

  18) Fix RTNL deadlock during reset in ibmvnic driver, from Thomas
      Falcon.

  19) Several small TCP fixes (off-by-one on window probe abort, NULL
      deref in tail loss probe, SNMP mis-estimations) from Yuchung
      Cheng"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (93 commits)
  net/sched: cls_flower: Reject duplicated rules also under skip_sw
  bnxt_en: Fix _bnxt_get_max_rings() for 57500 chips.
  bnxt_en: Fix NQ/CP rings accounting on the new 57500 chips.
  bnxt_en: Keep track of reserved IRQs.
  bnxt_en: Fix CNP CoS queue regression.
  net/mlx4_core: Correctly set PFC param if global pause is turned off.
  Revert "net/ibm/emac: wrong bit is used for STA control"
  neighbour: Avoid writing before skb->head in neigh_hh_output()
  ipv6: Check available headroom in ip6_xmit() even without options
  tcp: lack of available data can also cause TSO defer
  ipv6: sr: properly initialize flowi6 prior passing to ip6_route_output
  mlxsw: spectrum_switchdev: Fix VLAN device deletion via ioctl
  mlxsw: spectrum_router: Relax GRE decap matching check
  mlxsw: spectrum_switchdev: Avoid leaking FID's reference count
  mlxsw: spectrum_nve: Remove easily triggerable warnings
  ipv4: ipv6: netfilter: Adjust the frag mem limit when truesize changes
  sctp: frag_point sanity check
  tcp: fix NULL ref in tail loss probe
  tcp: Do not underestimate rwnd_limited
  net: use skb_list_del_init() to remove from RX sublists
  ...

4 files changed, 46 insertions, 20 deletions

diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index d6ee343fdb86..aa0b22697998 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -515,6 +515,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
 	struct rb_node *rbn;
 	int len;
 	int ihlen;
+	int delta;
 	int err;
 	u8 ecn;
 
@@ -556,10 +557,16 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
 	if (len > 65535)
 		goto out_oversize;
 
+	delta = - head->truesize;
+
 	/* Head of list must not be cloned. */
 	if (skb_unclone(head, GFP_ATOMIC))
 		goto out_nomem;
 
+	delta += head->truesize;
+	if (delta)
+		add_frag_mem_limit(qp->q.net, delta);
+
 	/* If the first fragment is fragmented itself, we split
 	 * it to two chunks: the first with data and paged part
 	 * and the second, holding only fragments. */
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 35a786c0aaa0..e609b08c9df4 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -547,7 +547,7 @@ static void ip_list_rcv_finish(struct net *net, struct sock *sk,
 	list_for_each_entry_safe(skb, next, head, list) {
 		struct dst_entry *dst;
 
-		list_del(&skb->list);
+		skb_list_del_init(skb);
 		/* if ingress device is enslaved to an L3 master device pass the
 		 * skb to its handler for processing
 		 */
@@ -594,7 +594,7 @@ void ip_list_rcv(struct list_head *head, struct packet_type *pt,
 		struct net_device *dev = skb->dev;
 		struct net *net = dev_net(dev);
 
-		list_del(&skb->list);
+		skb_list_del_init(skb);
 		skb = ip_rcv_core(skb, net);
 		if (skb == NULL)
 			continue;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 3f510cad0b3e..d1676d8a6ed7 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1904,7 +1904,9 @@ static int tso_fragment(struct sock *sk, enum tcp_queue tcp_queue,
  * This algorithm is from John Heffner.
  */
 static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
-				 bool *is_cwnd_limited, u32 max_segs)
+				 bool *is_cwnd_limited,
+				 bool *is_rwnd_limited,
+				 u32 max_segs)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	u32 age, send_win, cong_win, limit, in_flight;
@@ -1912,9 +1914,6 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
 	struct sk_buff *head;
 	int win_divisor;
 
-	if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
-		goto send_now;
-
 	if (icsk->icsk_ca_state >= TCP_CA_Recovery)
 		goto send_now;
 
@@ -1973,10 +1972,27 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
 	if (age < (tp->srtt_us >> 4))
 		goto send_now;
 
-	/* Ok, it looks like it is advisable to defer. */
+	/* Ok, it looks like it is advisable to defer.
+	 * Three cases are tracked :
+	 * 1) We are cwnd-limited
+	 * 2) We are rwnd-limited
+	 * 3) We are application limited.
+	 */
+	if (cong_win < send_win) {
+		if (cong_win <= skb->len) {
+			*is_cwnd_limited = true;
+			return true;
+		}
+	} else {
+		if (send_win <= skb->len) {
+			*is_rwnd_limited = true;
+			return true;
+		}
+	}
 
-	if (cong_win < send_win && cong_win <= skb->len)
-		*is_cwnd_limited = true;
+	/* If this packet won't get more data, do not wait. */
+	if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
+		goto send_now;
 
 	return true;
 
@@ -2356,7 +2372,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 		} else {
 			if (!push_one &&
 			    tcp_tso_should_defer(sk, skb, &is_cwnd_limited,
-						 max_segs))
+						 &is_rwnd_limited, max_segs))
 				break;
 		}
 
@@ -2494,15 +2510,18 @@ void tcp_send_loss_probe(struct sock *sk)
 		goto rearm_timer;
 	}
 	skb = skb_rb_last(&sk->tcp_rtx_queue);
+	if (unlikely(!skb)) {
+		WARN_ONCE(tp->packets_out,
+			  "invalid inflight: %u state %u cwnd %u mss %d\n",
+			  tp->packets_out, sk->sk_state, tp->snd_cwnd, mss);
+		inet_csk(sk)->icsk_pending = 0;
+		return;
+	}
 
 	/* At most one outstanding TLP retransmission. */
 	if (tp->tlp_high_seq)
 		goto rearm_timer;
 
-	/* Retransmit last segment. */
-	if (WARN_ON(!skb))
-		goto rearm_timer;
-
 	if (skb_still_in_host_queue(sk, skb))
 		goto rearm_timer;
 
@@ -2920,7 +2939,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 		TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS;
 		trace_tcp_retransmit_skb(sk, skb);
 	} else if (err != -EBUSY) {
-		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL);
+		NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL, segs);
 	}
 	return err;
 }
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 091c53925e4d..f87dbc78b6bc 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -378,7 +378,7 @@ static void tcp_probe_timer(struct sock *sk)
 			return;
 	}
 
-	if (icsk->icsk_probes_out > max_probes) {
+	if (icsk->icsk_probes_out >= max_probes) {
 abort:		tcp_write_err(sk);
 	} else {
 		/* Only send another probe if we didn't close things up. */
@@ -484,11 +484,12 @@ void tcp_retransmit_timer(struct sock *sk)
 		goto out_reset_timer;
 	}
 
+	__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPTIMEOUTS);
 	if (tcp_write_timeout(sk))
 		goto out;
 
 	if (icsk->icsk_retransmits == 0) {
-		int mib_idx;
+		int mib_idx = 0;
 
 		if (icsk->icsk_ca_state == TCP_CA_Recovery) {
 			if (tcp_is_sack(tp))
@@ -503,10 +504,9 @@ void tcp_retransmit_timer(struct sock *sk)
 				mib_idx = LINUX_MIB_TCPSACKFAILURES;
 			else
 				mib_idx = LINUX_MIB_TCPRENOFAILURES;
-		} else {
-			mib_idx = LINUX_MIB_TCPTIMEOUTS;
 		}
-		__NET_INC_STATS(sock_net(sk), mib_idx);
+		if (mib_idx)
+			__NET_INC_STATS(sock_net(sk), mib_idx);
 	}
 
 	tcp_enter_loss(sk);