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

Pull networking updates from David Miller:

Changes of note:

 1) Allow to schedule ICMP packets in IPVS, from Alex Gartrell.

 2) Provide FIB table ID in ipv4 route dumps just as ipv6 does, from
    David Ahern.

 3) Allow the user to ask for the statistics to be filtered out of
    ipv4/ipv6 address netlink dumps.  From Sowmini Varadhan.

 4) More work to pass the network namespace context around deep into
    various packet path APIs, starting with the netfilter hooks.  From
    Eric W Biederman.

 5) Add layer 2 TX/RX checksum offloading to qeth driver, from Thomas
    Richter.

 6) Use usec resolution for SYN/ACK RTTs in TCP, from Yuchung Cheng.

 7) Support Very High Throughput in wireless MESH code, from Bob
    Copeland.

 8) Allow setting the ageing_time in switchdev/rocker.  From Scott
    Feldman.

 9) Properly autoload L2TP type modules, from Stephen Hemminger.

10) Fix and enable offload features by default in 8139cp driver, from
    David Woodhouse.

11) Support both ipv4 and ipv6 sockets in a single vxlan device, from
    Jiri Benc.

12) Fix CWND limiting of thin streams in TCP, from Bendik Rønning
    Opstad.

13) Fix IPSEC flowcache overflows on large systems, from Steffen
    Klassert.

14) Convert bridging to track VLANs using rhashtable entries rather than
    a bitmap.  From Nikolay Aleksandrov.

15) Make TCP listener handling completely lockless, this is a major
    accomplishment.  Incoming request sockets now live in the
    established hash table just like any other socket too.

    From Eric Dumazet.

15) Provide more bridging attributes to netlink, from Nikolay
    Aleksandrov.

16) Use hash based algorithm for ipv4 multipath routing, this was very
    long overdue.  From Peter Nørlund.

17) Several y2038 cures, mostly avoiding timespec.  From Arnd Bergmann.

18) Allow non-root execution of EBPF programs, from Alexei Starovoitov.

19) Support SO_INCOMING_CPU as setsockopt, from Eric Dumazet.  This
    influences the port binding selection logic used by SO_REUSEPORT.

20) Add ipv6 support to VRF, from David Ahern.

21) Add support for Mellanox Spectrum switch ASIC, from Jiri Pirko.

22) Add rtl8xxxu Realtek wireless driver, from Jes Sorensen.

23) Implement RACK loss recovery in TCP, from Yuchung Cheng.

24) Support multipath routes in MPLS, from Roopa Prabhu.

25) Fix POLLOUT notification for listening sockets in AF_UNIX, from Eric
    Dumazet.

26) Add new QED Qlogic river, from Yuval Mintz, Manish Chopra, and
    Sudarsana Kalluru.

27) Don't fetch timestamps on AF_UNIX sockets, from Hannes Frederic
    Sowa.

28) Support ipv6 geneve tunnels, from John W Linville.

29) Add flood control support to switchdev layer, from Ido Schimmel.

30) Fix CHECKSUM_PARTIAL handling of potentially fragmented frames, from
    Hannes Frederic Sowa.

31) Support persistent maps and progs in bpf, from Daniel Borkmann.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1790 commits)
  sh_eth: use DMA barriers
  switchdev: respect SKIP_EOPNOTSUPP flag in case there is no recursion
  net: sched: kill dead code in sch_choke.c
  irda: Delete an unnecessary check before the function call "irlmp_unregister_service"
  net: dsa: mv88e6xxx: include DSA ports in VLANs
  net: dsa: mv88e6xxx: disable SA learning for DSA and CPU ports
  net/core: fix for_each_netdev_feature
  vlan: Invoke driver vlan hooks only if device is present
  arcnet/com20020: add LEDS_CLASS dependency
  bpf, verifier: annotate verbose printer with __printf
  dp83640: Only wait for timestamps for packets with timestamping enabled.
  ptp: Change ptp_class to a proper bitmask
  dp83640: Prune rx timestamp list before reading from it
  dp83640: Delay scheduled work.
  dp83640: Include hash in timestamp/packet matching
  ipv6: fix tunnel error handling
  net/mlx5e: Fix LSO vlan insertion
  net/mlx5e: Re-eanble client vlan TX acceleration
  net/mlx5e: Return error in case mlx5e_set_features() fails
  net/mlx5e: Don't allow more than max supported channels
  ...

1 files changed, 44 insertions, 40 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 3dbee0d83b15..cb7ca569052c 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -357,14 +357,10 @@ static void tcp_ecn_clear_syn(struct sock *sk, struct sk_buff *skb)
 }
 
 static void
-tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th,
-		    struct sock *sk)
+tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th)
 {
-	if (inet_rsk(req)->ecn_ok) {
+	if (inet_rsk(req)->ecn_ok)
 		th->ece = 1;
-		if (tcp_ca_needs_ecn(sk))
-			INET_ECN_xmit(sk);
-	}
 }
 
 /* Set up ECN state for a packet on a ESTABLISHED socket that is about to
@@ -612,12 +608,11 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 }
 
 /* Set up TCP options for SYN-ACKs. */
-static unsigned int tcp_synack_options(struct sock *sk,
-				   struct request_sock *req,
-				   unsigned int mss, struct sk_buff *skb,
-				   struct tcp_out_options *opts,
-				   const struct tcp_md5sig_key *md5,
-				   struct tcp_fastopen_cookie *foc)
+static unsigned int tcp_synack_options(struct request_sock *req,
+				       unsigned int mss, struct sk_buff *skb,
+				       struct tcp_out_options *opts,
+				       const struct tcp_md5sig_key *md5,
+				       struct tcp_fastopen_cookie *foc)
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
 	unsigned int remaining = MAX_TCP_OPTION_SPACE;
@@ -1827,7 +1822,7 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
 
 	/* Ok, it looks like it is advisable to defer. */
 
-	if (cong_win < send_win && cong_win < skb->len)
+	if (cong_win < send_win && cong_win <= skb->len)
 		*is_cwnd_limited = true;
 
 	return true;
@@ -2060,7 +2055,6 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 
 		cwnd_quota = tcp_cwnd_test(tp, skb);
 		if (!cwnd_quota) {
-			is_cwnd_limited = true;
 			if (push_one == 2)
 				/* Force out a loss probe pkt. */
 				cwnd_quota = 1;
@@ -2142,6 +2136,7 @@ repair:
 		/* Send one loss probe per tail loss episode. */
 		if (push_one != 2)
 			tcp_schedule_loss_probe(sk);
+		is_cwnd_limited |= (tcp_packets_in_flight(tp) >= tp->snd_cwnd);
 		tcp_cwnd_validate(sk, is_cwnd_limited);
 		return false;
 	}
@@ -2165,7 +2160,7 @@ bool tcp_schedule_loss_probe(struct sock *sk)
 	/* Don't do any loss probe on a Fast Open connection before 3WHS
 	 * finishes.
 	 */
-	if (sk->sk_state == TCP_SYN_RECV)
+	if (tp->fastopen_rsk)
 		return false;
 
 	/* TLP is only scheduled when next timer event is RTO. */
@@ -2175,7 +2170,7 @@ bool tcp_schedule_loss_probe(struct sock *sk)
 	/* Schedule a loss probe in 2*RTT for SACK capable connections
 	 * in Open state, that are either limited by cwnd or application.
 	 */
-	if (sysctl_tcp_early_retrans < 3 || !tp->srtt_us || !tp->packets_out ||
+	if (sysctl_tcp_early_retrans < 3 || !tp->packets_out ||
 	    !tcp_is_sack(tp) || inet_csk(sk)->icsk_ca_state != TCP_CA_Open)
 		return false;
 
@@ -2184,9 +2179,10 @@ bool tcp_schedule_loss_probe(struct sock *sk)
 		return false;
 
 	/* Probe timeout is at least 1.5*rtt + TCP_DELACK_MAX to account
-	 * for delayed ack when there's one outstanding packet.
+	 * for delayed ack when there's one outstanding packet. If no RTT
+	 * sample is available then probe after TCP_TIMEOUT_INIT.
 	 */
-	timeout = rtt << 1;
+	timeout = rtt << 1 ? : TCP_TIMEOUT_INIT;
 	if (tp->packets_out == 1)
 		timeout = max_t(u32, timeout,
 				(rtt + (rtt >> 1) + TCP_DELACK_MAX));
@@ -2659,8 +2655,6 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 			net_dbg_ratelimited("retrans_out leaked\n");
 		}
 #endif
-		if (!tp->retrans_out)
-			tp->lost_retrans_low = tp->snd_nxt;
 		TCP_SKB_CB(skb)->sacked |= TCPCB_RETRANS;
 		tp->retrans_out += tcp_skb_pcount(skb);
 
@@ -2668,10 +2662,6 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 		if (!tp->retrans_stamp)
 			tp->retrans_stamp = tcp_skb_timestamp(skb);
 
-		/* snd_nxt is stored to detect loss of retransmitted segment,
-		 * see tcp_input.c tcp_sacktag_write_queue().
-		 */
-		TCP_SKB_CB(skb)->ack_seq = tp->snd_nxt;
 	} else if (err != -EBUSY) {
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL);
 	}
@@ -2949,20 +2939,22 @@ int tcp_send_synack(struct sock *sk)
  * Allocate one skb and build a SYNACK packet.
  * @dst is consumed : Caller should not use it again.
  */
-struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
+struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 				struct request_sock *req,
-				struct tcp_fastopen_cookie *foc)
+				struct tcp_fastopen_cookie *foc,
+				bool attach_req)
 {
-	struct tcp_out_options opts;
 	struct inet_request_sock *ireq = inet_rsk(req);
-	struct tcp_sock *tp = tcp_sk(sk);
-	struct tcphdr *th;
-	struct sk_buff *skb;
+	const struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_md5sig_key *md5 = NULL;
+	struct tcp_out_options opts;
+	struct sk_buff *skb;
 	int tcp_header_size;
+	struct tcphdr *th;
+	u16 user_mss;
 	int mss;
 
-	skb = sock_wmalloc(sk, MAX_TCP_HEADER, 1, GFP_ATOMIC);
+	skb = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC);
 	if (unlikely(!skb)) {
 		dst_release(dst);
 		return NULL;
@@ -2970,11 +2962,21 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	/* Reserve space for headers. */
 	skb_reserve(skb, MAX_TCP_HEADER);
 
+	if (attach_req) {
+		skb_set_owner_w(skb, req_to_sk(req));
+	} else {
+		/* sk is a const pointer, because we want to express multiple
+		 * cpu might call us concurrently.
+		 * sk->sk_wmem_alloc in an atomic, we can promote to rw.
+		 */
+		skb_set_owner_w(skb, (struct sock *)sk);
+	}
 	skb_dst_set(skb, dst);
 
 	mss = dst_metric_advmss(dst);
-	if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss)
-		mss = tp->rx_opt.user_mss;
+	user_mss = READ_ONCE(tp->rx_opt.user_mss);
+	if (user_mss && user_mss < mss)
+		mss = user_mss;
 
 	memset(&opts, 0, sizeof(opts));
 #ifdef CONFIG_SYN_COOKIES
@@ -2988,8 +2990,9 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	rcu_read_lock();
 	md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req));
 #endif
-	tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5,
-					     foc) + sizeof(*th);
+	skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4);
+	tcp_header_size = tcp_synack_options(req, mss, skb, &opts, md5, foc) +
+			  sizeof(*th);
 
 	skb_push(skb, tcp_header_size);
 	skb_reset_transport_header(skb);
@@ -2998,7 +3001,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	memset(th, 0, sizeof(struct tcphdr));
 	th->syn = 1;
 	th->ack = 1;
-	tcp_ecn_make_synack(req, th, sk);
+	tcp_ecn_make_synack(req, th);
 	th->source = htons(ireq->ir_num);
 	th->dest = ireq->ir_rmt_port;
 	/* Setting of flags are superfluous here for callers (and ECE is
@@ -3012,8 +3015,8 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	th->ack_seq = htonl(tcp_rsk(req)->rcv_nxt);
 
 	/* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */
-	th->window = htons(min(req->rcv_wnd, 65535U));
-	tcp_options_write((__be32 *)(th + 1), tp, &opts);
+	th->window = htons(min(req->rsk_rcv_wnd, 65535U));
+	tcp_options_write((__be32 *)(th + 1), NULL, &opts);
 	th->doff = (tcp_header_size >> 2);
 	TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_OUTSEGS);
 
@@ -3500,13 +3503,14 @@ void tcp_send_probe0(struct sock *sk)
 				  TCP_RTO_MAX);
 }
 
-int tcp_rtx_synack(struct sock *sk, struct request_sock *req)
+int tcp_rtx_synack(const struct sock *sk, struct request_sock *req)
 {
 	const struct tcp_request_sock_ops *af_ops = tcp_rsk(req)->af_specific;
 	struct flowi fl;
 	int res;
 
-	res = af_ops->send_synack(sk, NULL, &fl, req, 0, NULL);
+	tcp_rsk(req)->txhash = net_tx_rndhash();
+	res = af_ops->send_synack(sk, NULL, &fl, req, NULL, true);
 	if (!res) {
 		TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);