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

Pull networking updates from David Miller:
 "Highlights:

   - Gustavo A. R. Silva keeps working on the implicit switch fallthru
     changes.

   - Support 802.11ax High-Efficiency wireless in cfg80211 et al, From
     Luca Coelho.

   - Re-enable ASPM in r8169, from Kai-Heng Feng.

   - Add virtual XFRM interfaces, which avoids all of the limitations of
     existing IPSEC tunnels. From Steffen Klassert.

   - Convert GRO over to use a hash table, so that when we have many
     flows active we don't traverse a long list during accumluation.

   - Many new self tests for routing, TC, tunnels, etc. Too many
     contributors to mention them all, but I'm really happy to keep
     seeing this stuff.

   - Hardware timestamping support for dpaa_eth/fsl-fman from Yangbo Lu.

   - Lots of cleanups and fixes in L2TP code from Guillaume Nault.

   - Add IPSEC offload support to netdevsim, from Shannon Nelson.

   - Add support for slotting with non-uniform distribution to netem
     packet scheduler, from Yousuk Seung.

   - Add UDP GSO support to mlx5e, from Boris Pismenny.

   - Support offloading of Team LAG in NFP, from John Hurley.

   - Allow to configure TX queue selection based upon RX queue, from
     Amritha Nambiar.

   - Support ethtool ring size configuration in aquantia, from Anton
     Mikaev.

   - Support DSCP and flowlabel per-transport in SCTP, from Xin Long.

   - Support list based batching and stack traversal of SKBs, this is
     very exciting work. From Edward Cree.

   - Busyloop optimizations in vhost_net, from Toshiaki Makita.

   - Introduce the ETF qdisc, which allows time based transmissions. IGB
     can offload this in hardware. From Vinicius Costa Gomes.

   - Add parameter support to devlink, from Moshe Shemesh.

   - Several multiplication and division optimizations for BPF JIT in
     nfp driver, from Jiong Wang.

   - Lots of prepatory work to make more of the packet scheduler layer
     lockless, when possible, from Vlad Buslov.

   - Add ACK filter and NAT awareness to sch_cake packet scheduler, from
     Toke Høiland-Jørgensen.

   - Support regions and region snapshots in devlink, from Alex Vesker.

   - Allow to attach XDP programs to both HW and SW at the same time on
     a given device, with initial support in nfp. From Jakub Kicinski.

   - Add TLS RX offload and support in mlx5, from Ilya Lesokhin.

   - Use PHYLIB in r8169 driver, from Heiner Kallweit.

   - All sorts of changes to support Spectrum 2 in mlxsw driver, from
     Ido Schimmel.

   - PTP support in mv88e6xxx DSA driver, from Andrew Lunn.

   - Make TCP_USER_TIMEOUT socket option more accurate, from Jon
     Maxwell.

   - Support for templates in packet scheduler classifier, from Jiri
     Pirko.

   - IPV6 support in RDS, from Ka-Cheong Poon.

   - Native tproxy support in nf_tables, from Máté Eckl.

   - Maintain IP fragment queue in an rbtree, but optimize properly for
     in-order frags. From Peter Oskolkov.

   - Improvde handling of ACKs on hole repairs, from Yuchung Cheng"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1996 commits)
  bpf: test: fix spelling mistake "REUSEEPORT" -> "REUSEPORT"
  hv/netvsc: Fix NULL dereference at single queue mode fallback
  net: filter: mark expected switch fall-through
  xen-netfront: fix warn message as irq device name has '/'
  cxgb4: Add new T5 PCI device ids 0x50af and 0x50b0
  net: dsa: mv88e6xxx: missing unlock on error path
  rds: fix building with IPV6=m
  inet/connection_sock: prefer _THIS_IP_ to current_text_addr
  net: dsa: mv88e6xxx: bitwise vs logical bug
  net: sock_diag: Fix spectre v1 gadget in __sock_diag_cmd()
  ieee802154: hwsim: using right kind of iteration
  net: hns3: Add vlan filter setting by ethtool command -K
  net: hns3: Set tx ring' tc info when netdev is up
  net: hns3: Remove tx ring BD len register in hns3_enet
  net: hns3: Fix desc num set to default when setting channel
  net: hns3: Fix for phy link issue when using marvell phy driver
  net: hns3: Fix for information of phydev lost problem when down/up
  net: hns3: Fix for command format parsing error in hclge_is_all_function_id_zero
  net: hns3: Add support for serdes loopback selftest
  bnxt_en: take coredump_record structure off stack
  ...

1 files changed, 51 insertions, 17 deletions

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index f9dcb29be12d..4c2dd9f863f7 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -78,6 +78,7 @@
 #include <linux/errqueue.h>
 #include <trace/events/tcp.h>
 #include <linux/static_key.h>
+#include <net/busy_poll.h>
 
 int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
 
@@ -244,16 +245,16 @@ static void tcp_ecn_queue_cwr(struct tcp_sock *tp)
 		tp->ecn_flags |= TCP_ECN_QUEUE_CWR;
 }
 
-static void tcp_ecn_accept_cwr(struct tcp_sock *tp, const struct sk_buff *skb)
+static void tcp_ecn_accept_cwr(struct sock *sk, const struct sk_buff *skb)
 {
 	if (tcp_hdr(skb)->cwr) {
-		tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
+		tcp_sk(sk)->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
 
 		/* If the sender is telling us it has entered CWR, then its
 		 * cwnd may be very low (even just 1 packet), so we should ACK
 		 * immediately.
 		 */
-		tcp_enter_quickack_mode((struct sock *)tp, 2);
+		inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
 	}
 }
 
@@ -590,9 +591,12 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk,
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	if (tp->rx_opt.rcv_tsecr &&
-	    (TCP_SKB_CB(skb)->end_seq -
-	     TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss)) {
+	if (tp->rx_opt.rcv_tsecr == tp->rcv_rtt_last_tsecr)
+		return;
+	tp->rcv_rtt_last_tsecr = tp->rx_opt.rcv_tsecr;
+
+	if (TCP_SKB_CB(skb)->end_seq -
+	    TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss) {
 		u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr;
 		u32 delta_us;
 
@@ -877,6 +881,7 @@ static void tcp_dsack_seen(struct tcp_sock *tp)
 {
 	tp->rx_opt.sack_ok |= TCP_DSACK_SEEN;
 	tp->rack.dsack_seen = 1;
+	tp->dsack_dups++;
 }
 
 /* It's reordering when higher sequence was delivered (i.e. sacked) before
@@ -908,8 +913,8 @@ static void tcp_check_sack_reordering(struct sock *sk, const u32 low_seq,
 				       sock_net(sk)->ipv4.sysctl_tcp_max_reordering);
 	}
 
-	tp->rack.reord = 1;
 	/* This exciting event is worth to be remembered. 8) */
+	tp->reord_seen++;
 	NET_INC_STATS(sock_net(sk),
 		      ts ? LINUX_MIB_TCPTSREORDER : LINUX_MIB_TCPSACKREORDER);
 }
@@ -1873,6 +1878,7 @@ static void tcp_check_reno_reordering(struct sock *sk, const int addend)
 
 	tp->reordering = min_t(u32, tp->packets_out + addend,
 			       sock_net(sk)->ipv4.sysctl_tcp_max_reordering);
+	tp->reord_seen++;
 	NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRENOREORDER);
 }
 
@@ -3466,7 +3472,7 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb)
 static void tcp_store_ts_recent(struct tcp_sock *tp)
 {
 	tp->rx_opt.ts_recent = tp->rx_opt.rcv_tsval;
-	tp->rx_opt.ts_recent_stamp = get_seconds();
+	tp->rx_opt.ts_recent_stamp = ktime_get_seconds();
 }
 
 static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq)
@@ -4347,6 +4353,11 @@ static bool tcp_try_coalesce(struct sock *sk,
 	if (TCP_SKB_CB(from)->seq != TCP_SKB_CB(to)->end_seq)
 		return false;
 
+#ifdef CONFIG_TLS_DEVICE
+	if (from->decrypted != to->decrypted)
+		return false;
+#endif
+
 	if (!skb_try_coalesce(to, from, fragstolen, &delta))
 		return false;
 
@@ -4642,8 +4653,10 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
 	skb->data_len = data_len;
 	skb->len = size;
 
-	if (tcp_try_rmem_schedule(sk, skb, skb->truesize))
+	if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) {
+		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP);
 		goto err_free;
+	}
 
 	err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size);
 	if (err)
@@ -4690,7 +4703,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 	skb_dst_drop(skb);
 	__skb_pull(skb, tcp_hdr(skb)->doff * 4);
 
-	tcp_ecn_accept_cwr(tp, skb);
+	tcp_ecn_accept_cwr(sk, skb);
 
 	tp->rx_opt.dsack = 0;
 
@@ -4699,18 +4712,21 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 	 *  Out of sequence packets to the out_of_order_queue.
 	 */
 	if (TCP_SKB_CB(skb)->seq == tp->rcv_nxt) {
-		if (tcp_receive_window(tp) == 0)
+		if (tcp_receive_window(tp) == 0) {
+			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPZEROWINDOWDROP);
 			goto out_of_window;
+		}
 
 		/* Ok. In sequence. In window. */
 queue_and_out:
 		if (skb_queue_len(&sk->sk_receive_queue) == 0)
 			sk_forced_mem_schedule(sk, skb->truesize);
-		else if (tcp_try_rmem_schedule(sk, skb, skb->truesize))
+		else if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) {
+			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP);
 			goto drop;
+		}
 
 		eaten = tcp_queue_rcv(sk, skb, 0, &fragstolen);
-		tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq);
 		if (skb->len)
 			tcp_event_data_recv(sk, skb);
 		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
@@ -4719,11 +4735,11 @@ queue_and_out:
 		if (!RB_EMPTY_ROOT(&tp->out_of_order_queue)) {
 			tcp_ofo_queue(sk);
 
-			/* RFC2581. 4.2. SHOULD send immediate ACK, when
+			/* RFC5681. 4.2. SHOULD send immediate ACK, when
 			 * gap in queue is filled.
 			 */
 			if (RB_EMPTY_ROOT(&tp->out_of_order_queue))
-				inet_csk(sk)->icsk_ack.pingpong = 0;
+				inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
 		}
 
 		if (tp->rx_opt.num_sacks)
@@ -4766,8 +4782,10 @@ drop:
 		/* If window is closed, drop tail of packet. But after
 		 * remembering D-SACK for its head made in previous line.
 		 */
-		if (!tcp_receive_window(tp))
+		if (!tcp_receive_window(tp)) {
+			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPZEROWINDOWDROP);
 			goto out_of_window;
+		}
 		goto queue_and_out;
 	}
 
@@ -4885,6 +4903,9 @@ restart:
 			break;
 
 		memcpy(nskb->cb, skb->cb, sizeof(skb->cb));
+#ifdef CONFIG_TLS_DEVICE
+		nskb->decrypted = skb->decrypted;
+#endif
 		TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(nskb)->end_seq = start;
 		if (list)
 			__skb_queue_before(list, skb, nskb);
@@ -4912,6 +4933,10 @@ restart:
 				    skb == tail ||
 				    (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)))
 					goto end;
+#ifdef CONFIG_TLS_DEVICE
+				if (skb->decrypted != nskb->decrypted)
+					goto end;
+#endif
 			}
 		}
 	}
@@ -5154,7 +5179,9 @@ static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible)
 	    (tp->rcv_nxt - tp->copied_seq < sk->sk_rcvlowat ||
 	     __tcp_select_window(sk) >= tp->rcv_wnd)) ||
 	    /* We ACK each frame or... */
-	    tcp_in_quickack_mode(sk)) {
+	    tcp_in_quickack_mode(sk) ||
+	    /* Protocol state mandates a one-time immediate ACK */
+	    inet_csk(sk)->icsk_ack.pending & ICSK_ACK_NOW) {
 send_now:
 		tcp_send_ack(sk);
 		return;
@@ -5530,6 +5557,11 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
 				tcp_ack(sk, skb, 0);
 				__kfree_skb(skb);
 				tcp_data_snd_check(sk);
+				/* When receiving pure ack in fast path, update
+				 * last ts ecr directly instead of calling
+				 * tcp_rcv_rtt_measure_ts()
+				 */
+				tp->rcv_rtt_last_tsecr = tp->rx_opt.rcv_tsecr;
 				return;
 			} else { /* Header too small */
 				TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS);
@@ -5631,6 +5663,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
 	if (skb) {
 		icsk->icsk_af_ops->sk_rx_dst_set(sk, skb);
 		security_inet_conn_established(sk, skb);
+		sk_mark_napi_id(sk, skb);
 	}
 
 	tcp_init_transfer(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB);
@@ -6459,6 +6492,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	tcp_rsk(req)->snt_isn = isn;
 	tcp_rsk(req)->txhash = net_tx_rndhash();
 	tcp_openreq_init_rwin(req, sk, dst);
+	sk_rx_queue_set(req_to_sk(req), skb);
 	if (!want_cookie) {
 		tcp_reqsk_record_syn(sk, req, skb);
 		fastopen_sk = tcp_try_fastopen(sk, skb, req, &foc, dst);