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

Pull networking updates from David Miller:

 1) Seccomp BPF filters can now be JIT'd, from Alexei Starovoitov.

 2) Multiqueue support in xen-netback and xen-netfront, from Andrew J
    Benniston.

 3) Allow tweaking of aggregation settings in cdc_ncm driver, from Bjørn
    Mork.

 4) BPF now has a "random" opcode, from Chema Gonzalez.

 5) Add more BPF documentation and improve test framework, from Daniel
    Borkmann.

 6) Support TCP fastopen over ipv6, from Daniel Lee.

 7) Add software TSO helper functions and use them to support software
    TSO in mvneta and mv643xx_eth drivers.  From Ezequiel Garcia.

 8) Support software TSO in fec driver too, from Nimrod Andy.

 9) Add Broadcom SYSTEMPORT driver, from Florian Fainelli.

10) Handle broadcasts more gracefully over macvlan when there are large
    numbers of interfaces configured, from Herbert Xu.

11) Allow more control over fwmark used for non-socket based responses,
    from Lorenzo Colitti.

12) Do TCP congestion window limiting based upon measurements, from Neal
    Cardwell.

13) Support busy polling in SCTP, from Neal Horman.

14) Allow RSS key to be configured via ethtool, from Venkata Duvvuru.

15) Bridge promisc mode handling improvements from Vlad Yasevich.

16) Don't use inetpeer entries to implement ID generation any more, it
    performs poorly, from Eric Dumazet.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1522 commits)
  rtnetlink: fix userspace API breakage for iproute2 < v3.9.0
  tcp: fixing TLP's FIN recovery
  net: fec: Add software TSO support
  net: fec: Add Scatter/gather support
  net: fec: Increase buffer descriptor entry number
  net: fec: Factorize feature setting
  net: fec: Enable IP header hardware checksum
  net: fec: Factorize the .xmit transmit function
  bridge: fix compile error when compiling without IPv6 support
  bridge: fix smatch warning / potential null pointer dereference
  via-rhine: fix full-duplex with autoneg disable
  bnx2x: Enlarge the dorq threshold for VFs
  bnx2x: Check for UNDI in uncommon branch
  bnx2x: Fix 1G-baseT link
  bnx2x: Fix link for KR with swapped polarity lane
  sctp: Fix sk_ack_backlog wrap-around problem
  net/core: Add VF link state control policy
  net/fsl: xgmac_mdio is dependent on OF_MDIO
  net/fsl: Make xgmac_mdio read error message useful
  net_sched: drr: warn when qdisc is not work conserving
  ...

1 files changed, 48 insertions, 38 deletions

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index e289830ed6e3..229239ad96b1 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -340,7 +340,8 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	struct sock *sk;
 	int err;
 	struct tcp_sock *tp;
-	__u32 seq;
+	struct request_sock *fastopen;
+	__u32 seq, snd_una;
 	struct net *net = dev_net(skb->dev);
 
 	sk = inet6_lookup(net, &tcp_hashinfo, &hdr->daddr,
@@ -371,8 +372,11 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 
 	tp = tcp_sk(sk);
 	seq = ntohl(th->seq);
+	/* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */
+	fastopen = tp->fastopen_rsk;
+	snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una;
 	if (sk->sk_state != TCP_LISTEN &&
-	    !between(seq, tp->snd_una, tp->snd_nxt)) {
+	    !between(seq, snd_una, tp->snd_nxt)) {
 		NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
 		goto out;
 	}
@@ -436,8 +440,13 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		goto out;
 
 	case TCP_SYN_SENT:
-	case TCP_SYN_RECV:  /* Cannot happen.
-			       It can, it SYNs are crossed. --ANK */
+	case TCP_SYN_RECV:
+		/* Only in fast or simultaneous open. If a fast open socket is
+		 * is already accepted it is treated as a connected one below.
+		 */
+		if (fastopen && fastopen->sk == NULL)
+			break;
+
 		if (!sock_owned_by_user(sk)) {
 			sk->sk_err = err;
 			sk->sk_error_report(sk);		/* Wake people up to see the error (see connect in sock.c) */
@@ -463,7 +472,8 @@ out:
 static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst,
 			      struct flowi6 *fl6,
 			      struct request_sock *req,
-			      u16 queue_mapping)
+			      u16 queue_mapping,
+			      struct tcp_fastopen_cookie *foc)
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
 	struct ipv6_pinfo *np = inet6_sk(sk);
@@ -474,7 +484,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst,
 	if (!dst && (dst = inet6_csk_route_req(sk, fl6, req)) == NULL)
 		goto done;
 
-	skb = tcp_make_synack(sk, dst, req, NULL);
+	skb = tcp_make_synack(sk, dst, req, foc);
 
 	if (skb) {
 		__tcp_v6_send_check(skb, &ireq->ir_v6_loc_addr,
@@ -498,7 +508,7 @@ static int tcp_v6_rtx_synack(struct sock *sk, struct request_sock *req)
 	struct flowi6 fl6;
 	int res;
 
-	res = tcp_v6_send_synack(sk, NULL, &fl6, req, 0);
+	res = tcp_v6_send_synack(sk, NULL, &fl6, req, 0, NULL);
 	if (!res) {
 		TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);
@@ -802,6 +812,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
 		fl6.flowi6_oif = inet6_iif(skb);
 	else
 		fl6.flowi6_oif = oif;
+	fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark);
 	fl6.fl6_dport = t1->dest;
 	fl6.fl6_sport = t1->source;
 	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
@@ -917,7 +928,12 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb)
 static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
 				  struct request_sock *req)
 {
-	tcp_v6_send_ack(skb, tcp_rsk(req)->snt_isn + 1, tcp_rsk(req)->rcv_isn + 1,
+	/* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV
+	 * sk->sk_state == TCP_SYN_RECV -> for Fast Open.
+	 */
+	tcp_v6_send_ack(skb, (sk->sk_state == TCP_LISTEN) ?
+			tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt,
+			tcp_rsk(req)->rcv_nxt,
 			req->rcv_wnd, tcp_time_stamp, req->ts_recent, sk->sk_bound_dev_if,
 			tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr),
 			0, 0);
@@ -969,8 +985,10 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 	struct tcp_sock *tp = tcp_sk(sk);
 	__u32 isn = TCP_SKB_CB(skb)->when;
 	struct dst_entry *dst = NULL;
+	struct tcp_fastopen_cookie foc = { .len = -1 };
+	bool want_cookie = false, fastopen;
 	struct flowi6 fl6;
-	bool want_cookie = false;
+	int err;
 
 	if (skb->protocol == htons(ETH_P_IP))
 		return tcp_v4_conn_request(sk, skb);
@@ -1001,7 +1019,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 	tcp_clear_options(&tmp_opt);
 	tmp_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
 	tmp_opt.user_mss = tp->rx_opt.user_mss;
-	tcp_parse_options(skb, &tmp_opt, 0, NULL);
+	tcp_parse_options(skb, &tmp_opt, 0, want_cookie ? NULL : &foc);
 
 	if (want_cookie && !tmp_opt.saw_tstamp)
 		tcp_clear_options(&tmp_opt);
@@ -1016,6 +1034,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 		TCP_ECN_create_request(req, skb, sock_net(sk));
 
 	ireq->ir_iif = sk->sk_bound_dev_if;
+	ireq->ir_mark = inet_request_mark(sk, skb);
 
 	/* So that link locals have meaning */
 	if (!sk->sk_bound_dev_if &&
@@ -1074,19 +1093,27 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 		isn = tcp_v6_init_sequence(skb);
 	}
 have_isn:
-	tcp_rsk(req)->snt_isn = isn;
 
 	if (security_inet_conn_request(sk, skb, req))
 		goto drop_and_release;
 
-	if (tcp_v6_send_synack(sk, dst, &fl6, req,
-			       skb_get_queue_mapping(skb)) ||
-	    want_cookie)
+	if (!dst && (dst = inet6_csk_route_req(sk, &fl6, req)) == NULL)
 		goto drop_and_free;
 
+	tcp_rsk(req)->snt_isn = isn;
 	tcp_rsk(req)->snt_synack = tcp_time_stamp;
-	tcp_rsk(req)->listener = NULL;
-	inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
+	tcp_openreq_init_rwin(req, sk, dst);
+	fastopen = !want_cookie &&
+		   tcp_try_fastopen(sk, skb, req, &foc, dst);
+	err = tcp_v6_send_synack(sk, dst, &fl6, req,
+				 skb_get_queue_mapping(skb), &foc);
+	if (!fastopen) {
+		if (err || want_cookie)
+			goto drop_and_free;
+
+		tcp_rsk(req)->listener = NULL;
+		inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
+	}
 	return 0;
 
 drop_and_release:
@@ -1294,25 +1321,6 @@ out:
 	return NULL;
 }
 
-static __sum16 tcp_v6_checksum_init(struct sk_buff *skb)
-{
-	if (skb->ip_summed == CHECKSUM_COMPLETE) {
-		if (!tcp_v6_check(skb->len, &ipv6_hdr(skb)->saddr,
-				  &ipv6_hdr(skb)->daddr, skb->csum)) {
-			skb->ip_summed = CHECKSUM_UNNECESSARY;
-			return 0;
-		}
-	}
-
-	skb->csum = ~csum_unfold(tcp_v6_check(skb->len,
-					      &ipv6_hdr(skb)->saddr,
-					      &ipv6_hdr(skb)->daddr, 0));
-
-	if (skb->len <= 76)
-		return __skb_checksum_complete(skb);
-	return 0;
-}
-
 /* The socket must have it's spinlock held when we get
  * here.
  *
@@ -1486,7 +1494,7 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 	if (!pskb_may_pull(skb, th->doff*4))
 		goto discard_it;
 
-	if (!skb_csum_unnecessary(skb) && tcp_v6_checksum_init(skb))
+	if (skb_checksum_init(skb, IPPROTO_TCP, ip6_compute_pseudo))
 		goto csum_error;
 
 	th = tcp_hdr(skb);
@@ -1779,6 +1787,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
 	const struct inet_sock *inet = inet_sk(sp);
 	const struct tcp_sock *tp = tcp_sk(sp);
 	const struct inet_connection_sock *icsk = inet_csk(sp);
+	struct fastopen_queue *fastopenq = icsk->icsk_accept_queue.fastopenq;
 
 	dest  = &sp->sk_v6_daddr;
 	src   = &sp->sk_v6_rcv_saddr;
@@ -1821,7 +1830,9 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
 		   jiffies_to_clock_t(icsk->icsk_ack.ato),
 		   (icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong,
 		   tp->snd_cwnd,
-		   tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh
+		   sp->sk_state == TCP_LISTEN ?
+			(fastopenq ? fastopenq->max_qlen : 0) :
+			(tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh)
 		   );
 }
 
@@ -1981,7 +1992,6 @@ static struct inet_protosw tcpv6_protosw = {
 	.protocol	=	IPPROTO_TCP,
 	.prot		=	&tcpv6_prot,
 	.ops		=	&inet6_stream_ops,
-	.no_check	=	0,
 	.flags		=	INET_PROTOSW_PERMANENT |
 				INET_PROTOSW_ICSK,
 };