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

Pull networking updates from David Miller:

 1) New ipset extensions for matching on destination MAC addresses, from
    Stefano Brivio.

 2) Add ipv4 ttl and tos, plus ipv6 flow label and hop limit offloads to
    nfp driver. From Stefano Brivio.

 3) Implement GRO for plain UDP sockets, from Paolo Abeni.

 4) Lots of work from Michał Mirosław to eliminate the VLAN_TAG_PRESENT
    bit so that we could support the entire vlan_tci value.

 5) Rework the IPSEC policy lookups to better optimize more usecases,
    from Florian Westphal.

 6) Infrastructure changes eliminating direct manipulation of SKB lists
    wherever possible, and to always use the appropriate SKB list
    helpers. This work is still ongoing...

 7) Lots of PHY driver and state machine improvements and
    simplifications, from Heiner Kallweit.

 8) Various TSO deferral refinements, from Eric Dumazet.

 9) Add ntuple filter support to aquantia driver, from Dmitry Bogdanov.

10) Batch dropping of XDP packets in tuntap, from Jason Wang.

11) Lots of cleanups and improvements to the r8169 driver from Heiner
    Kallweit, including support for ->xmit_more. This driver has been
    getting some much needed love since he started working on it.

12) Lots of new forwarding selftests from Petr Machata.

13) Enable VXLAN learning in mlxsw driver, from Ido Schimmel.

14) Packed ring support for virtio, from Tiwei Bie.

15) Add new Aquantia AQtion USB driver, from Dmitry Bezrukov.

16) Add XDP support to dpaa2-eth driver, from Ioana Ciocoi Radulescu.

17) Implement coalescing on TCP backlog queue, from Eric Dumazet.

18) Implement carrier change in tun driver, from Nicolas Dichtel.

19) Support msg_zerocopy in UDP, from Willem de Bruijn.

20) Significantly improve garbage collection of neighbor objects when
    the table has many PERMANENT entries, from David Ahern.

21) Remove egdev usage from nfp and mlx5, and remove the facility
    completely from the tree as it no longer has any users. From Oz
    Shlomo and others.

22) Add a NETDEV_PRE_CHANGEADDR so that drivers can veto the change and
    therefore abort the operation before the commit phase (which is the
    NETDEV_CHANGEADDR event). From Petr Machata.

23) Add indirect call wrappers to avoid retpoline overhead, and use them
    in the GRO code paths. From Paolo Abeni.

24) Add support for netlink FDB get operations, from Roopa Prabhu.

25) Support bloom filter in mlxsw driver, from Nir Dotan.

26) Add SKB extension infrastructure. This consolidates the handling of
    the auxiliary SKB data used by IPSEC and bridge netfilter, and is
    designed to support the needs to MPTCP which could be integrated in
    the future.

27) Lots of XDP TX optimizations in mlx5 from Tariq Toukan.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1845 commits)
  net: dccp: fix kernel crash on module load
  drivers/net: appletalk/cops: remove redundant if statement and mask
  bnx2x: Fix NULL pointer dereference in bnx2x_del_all_vlans() on some hw
  net/net_namespace: Check the return value of register_pernet_subsys()
  net/netlink_compat: Fix a missing check of nla_parse_nested
  ieee802154: lowpan_header_create check must check daddr
  net/mlx4_core: drop useless LIST_HEAD
  mlxsw: spectrum: drop useless LIST_HEAD
  net/mlx5e: drop useless LIST_HEAD
  iptunnel: Set tun_flags in the iptunnel_metadata_reply from src
  net/mlx5e: fix semicolon.cocci warnings
  staging: octeon: fix build failure with XFRM enabled
  net: Revert recent Spectre-v1 patches.
  can: af_can: Fix Spectre v1 vulnerability
  packet: validate address length if non-zero
  nfc: af_nfc: Fix Spectre v1 vulnerability
  phonet: af_phonet: Fix Spectre v1 vulnerability
  net: core: Fix Spectre v1 vulnerability
  net: minor cleanup in skb_ext_add()
  net: drop the unused helper skb_ext_get()
  ...

1 files changed, 43 insertions, 35 deletions

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a9d9555a973f..76858b14ebe9 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1865,16 +1865,20 @@ static void tcp_check_reno_reordering(struct sock *sk, const int addend)
 
 /* Emulate SACKs for SACKless connection: account for a new dupack. */
 
-static void tcp_add_reno_sack(struct sock *sk)
+static void tcp_add_reno_sack(struct sock *sk, int num_dupack)
 {
-	struct tcp_sock *tp = tcp_sk(sk);
-	u32 prior_sacked = tp->sacked_out;
+	if (num_dupack) {
+		struct tcp_sock *tp = tcp_sk(sk);
+		u32 prior_sacked = tp->sacked_out;
+		s32 delivered;
 
-	tp->sacked_out++;
-	tcp_check_reno_reordering(sk, 0);
-	if (tp->sacked_out > prior_sacked)
-		tp->delivered++; /* Some out-of-order packet is delivered */
-	tcp_verify_left_out(tp);
+		tp->sacked_out += num_dupack;
+		tcp_check_reno_reordering(sk, 0);
+		delivered = tp->sacked_out - prior_sacked;
+		if (delivered > 0)
+			tp->delivered += delivered;
+		tcp_verify_left_out(tp);
+	}
 }
 
 /* Account for ACK, ACKing some data in Reno Recovery phase. */
@@ -2459,8 +2463,8 @@ void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int flag)
 		u64 dividend = (u64)tp->snd_ssthresh * tp->prr_delivered +
 			       tp->prior_cwnd - 1;
 		sndcnt = div_u64(dividend, tp->prior_cwnd) - tp->prr_out;
-	} else if ((flag & FLAG_RETRANS_DATA_ACKED) &&
-		   !(flag & FLAG_LOST_RETRANS)) {
+	} else if ((flag & (FLAG_RETRANS_DATA_ACKED | FLAG_LOST_RETRANS)) ==
+		   FLAG_RETRANS_DATA_ACKED) {
 		sndcnt = min_t(int, delta,
 			       max_t(int, tp->prr_delivered - tp->prr_out,
 				     newly_acked_sacked) + 1);
@@ -2636,7 +2640,7 @@ void tcp_enter_recovery(struct sock *sk, bool ece_ack)
 /* Process an ACK in CA_Loss state. Move to CA_Open if lost data are
  * recovered or spurious. Otherwise retransmits more on partial ACKs.
  */
-static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack,
+static void tcp_process_loss(struct sock *sk, int flag, int num_dupack,
 			     int *rexmit)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -2655,7 +2659,7 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack,
 			return;
 
 		if (after(tp->snd_nxt, tp->high_seq)) {
-			if (flag & FLAG_DATA_SACKED || is_dupack)
+			if (flag & FLAG_DATA_SACKED || num_dupack)
 				tp->frto = 0; /* Step 3.a. loss was real */
 		} else if (flag & FLAG_SND_UNA_ADVANCED && !recovered) {
 			tp->high_seq = tp->snd_nxt;
@@ -2681,8 +2685,8 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack,
 		/* A Reno DUPACK means new data in F-RTO step 2.b above are
 		 * delivered. Lower inflight to clock out (re)tranmissions.
 		 */
-		if (after(tp->snd_nxt, tp->high_seq) && is_dupack)
-			tcp_add_reno_sack(sk);
+		if (after(tp->snd_nxt, tp->high_seq) && num_dupack)
+			tcp_add_reno_sack(sk, num_dupack);
 		else if (flag & FLAG_SND_UNA_ADVANCED)
 			tcp_reset_reno_sack(tp);
 	}
@@ -2759,13 +2763,13 @@ static bool tcp_force_fast_retransmit(struct sock *sk)
  * tcp_xmit_retransmit_queue().
  */
 static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
-				  bool is_dupack, int *ack_flag, int *rexmit)
+				  int num_dupack, int *ack_flag, int *rexmit)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	int fast_rexmit = 0, flag = *ack_flag;
-	bool do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) &&
-				     tcp_force_fast_retransmit(sk));
+	bool do_lost = num_dupack || ((flag & FLAG_DATA_SACKED) &&
+				      tcp_force_fast_retransmit(sk));
 
 	if (!tp->packets_out && tp->sacked_out)
 		tp->sacked_out = 0;
@@ -2812,8 +2816,8 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
 	switch (icsk->icsk_ca_state) {
 	case TCP_CA_Recovery:
 		if (!(flag & FLAG_SND_UNA_ADVANCED)) {
-			if (tcp_is_reno(tp) && is_dupack)
-				tcp_add_reno_sack(sk);
+			if (tcp_is_reno(tp))
+				tcp_add_reno_sack(sk, num_dupack);
 		} else {
 			if (tcp_try_undo_partial(sk, prior_snd_una))
 				return;
@@ -2828,7 +2832,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
 		tcp_identify_packet_loss(sk, ack_flag);
 		break;
 	case TCP_CA_Loss:
-		tcp_process_loss(sk, flag, is_dupack, rexmit);
+		tcp_process_loss(sk, flag, num_dupack, rexmit);
 		tcp_identify_packet_loss(sk, ack_flag);
 		if (!(icsk->icsk_ca_state == TCP_CA_Open ||
 		      (*ack_flag & FLAG_LOST_RETRANS)))
@@ -2839,8 +2843,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
 		if (tcp_is_reno(tp)) {
 			if (flag & FLAG_SND_UNA_ADVANCED)
 				tcp_reset_reno_sack(tp);
-			if (is_dupack)
-				tcp_add_reno_sack(sk);
+			tcp_add_reno_sack(sk, num_dupack);
 		}
 
 		if (icsk->icsk_ca_state <= TCP_CA_Disorder)
@@ -3562,7 +3565,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	bool is_sack_reneg = tp->is_sack_reneg;
 	u32 ack_seq = TCP_SKB_CB(skb)->seq;
 	u32 ack = TCP_SKB_CB(skb)->ack_seq;
-	bool is_dupack = false;
+	int num_dupack = 0;
 	int prior_packets = tp->packets_out;
 	u32 delivered = tp->delivered;
 	u32 lost = tp->lost;
@@ -3614,7 +3617,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	if (flag & FLAG_UPDATE_TS_RECENT)
 		tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq);
 
-	if (!(flag & FLAG_SLOWPATH) && after(ack, prior_snd_una)) {
+	if ((flag & (FLAG_SLOWPATH | FLAG_SND_UNA_ADVANCED)) ==
+	    FLAG_SND_UNA_ADVANCED) {
 		/* Window is constant, pure forward advance.
 		 * No more checks are required.
 		 * Note, we use the fact that SND.UNA>=SND.WL2.
@@ -3672,8 +3676,13 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 		tcp_set_xmit_timer(sk);
 
 	if (tcp_ack_is_dubious(sk, flag)) {
-		is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP));
-		tcp_fastretrans_alert(sk, prior_snd_una, is_dupack, &flag,
+		if (!(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP))) {
+			num_dupack = 1;
+			/* Consider if pure acks were aggregated in tcp_add_backlog() */
+			if (!(flag & FLAG_DATA))
+				num_dupack = max_t(u16, 1, skb_shinfo(skb)->gso_segs);
+		}
+		tcp_fastretrans_alert(sk, prior_snd_una, num_dupack, &flag,
 				      &rexmit);
 	}
 
@@ -3691,7 +3700,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 no_queue:
 	/* If data was DSACKed, see if we can undo a cwnd reduction. */
 	if (flag & FLAG_DSACKING_ACK) {
-		tcp_fastretrans_alert(sk, prior_snd_una, is_dupack, &flag,
+		tcp_fastretrans_alert(sk, prior_snd_una, num_dupack, &flag,
 				      &rexmit);
 		tcp_newly_delivered(sk, delivered, flag);
 	}
@@ -3716,7 +3725,7 @@ old_ack:
 	if (TCP_SKB_CB(skb)->sacked) {
 		flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una,
 						&sack_state);
-		tcp_fastretrans_alert(sk, prior_snd_una, is_dupack, &flag,
+		tcp_fastretrans_alert(sk, prior_snd_una, num_dupack, &flag,
 				      &rexmit);
 		tcp_newly_delivered(sk, delivered, flag);
 		tcp_xmit_recovery(sk, rexmit);
@@ -4606,13 +4615,12 @@ end:
 	}
 }
 
-static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int hdrlen,
-		  bool *fragstolen)
+static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb,
+				      bool *fragstolen)
 {
 	int eaten;
 	struct sk_buff *tail = skb_peek_tail(&sk->sk_receive_queue);
 
-	__skb_pull(skb, hdrlen);
 	eaten = (tail &&
 		 tcp_try_coalesce(sk, tail,
 				  skb, fragstolen)) ? 1 : 0;
@@ -4663,7 +4671,7 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
 	TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(skb)->seq + size;
 	TCP_SKB_CB(skb)->ack_seq = tcp_sk(sk)->snd_una - 1;
 
-	if (tcp_queue_rcv(sk, skb, 0, &fragstolen)) {
+	if (tcp_queue_rcv(sk, skb, &fragstolen)) {
 		WARN_ON_ONCE(fragstolen); /* should not happen */
 		__kfree_skb(skb);
 	}
@@ -4723,7 +4731,7 @@ queue_and_out:
 			goto drop;
 		}
 
-		eaten = tcp_queue_rcv(sk, skb, 0, &fragstolen);
+		eaten = tcp_queue_rcv(sk, skb, &fragstolen);
 		if (skb->len)
 			tcp_event_data_recv(sk, skb);
 		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
@@ -5599,8 +5607,8 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
 			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHPHITS);
 
 			/* Bulk data transfer: receiver */
-			eaten = tcp_queue_rcv(sk, skb, tcp_header_len,
-					      &fragstolen);
+			__skb_pull(skb, tcp_header_len);
+			eaten = tcp_queue_rcv(sk, skb, &fragstolen);
 
 			tcp_event_data_recv(sk, skb);