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

Pull networking updates from David Miller:

 1) Add TX fast path in mac80211, from Johannes Berg.

 2) Add TSO/GRO support to ibmveth, from Thomas Falcon

 3) Move away from cached routes in ipv6, just like ipv4, from Martin
    KaFai Lau.

 4) Lots of new rhashtable tests, from Thomas Graf.

 5) Run ingress qdisc lockless, from Alexei Starovoitov.

 6) Allow servers to fetch TCP packet headers for SYN packets of new
    connections, for fingerprinting.  From Eric Dumazet.

 7) Add mode parameter to pktgen, for testing receive.  From Alexei
    Starovoitov.

 8) Cache access optimizations via simplifications of build_skb(), from
    Alexander Duyck.

 9) Move page frag allocator under mm/, also from Alexander.

10) Add xmit_more support to hv_netvsc, from KY Srinivasan.

11) Add a counter guard in case we try to perform endless reclassify
    loops in the packet scheduler.

12) Extern flow dissector to be programmable and use it in new "Flower"
    classifier.  From Jiri Pirko.

13) AF_PACKET fanout rollover fixes, performance improvements, and new
    statistics.  From Willem de Bruijn.

14) Add netdev driver for GENEVE tunnels, from John W Linville.

15) Add ingress netfilter hooks and filtering, from Pablo Neira Ayuso.

16) Fix handling of epoll edge triggers in TCP, from Eric Dumazet.

17) Add an ECN retry fallback for the initial TCP handshake, from Daniel
    Borkmann.

18) Add tail call support to BPF, from Alexei Starovoitov.

19) Add several pktgen helper scripts, from Jesper Dangaard Brouer.

20) Add zerocopy support to AF_UNIX, from Hannes Frederic Sowa.

21) Favor even port numbers for allocation to connect() requests, and
    odd port numbers for bind(0), in an effort to help avoid
    ip_local_port_range exhaustion.  From Eric Dumazet.

22) Add Cavium ThunderX driver, from Sunil Goutham.

23) Allow bpf programs to access skb_iif and dev->ifindex SKB metadata,
    from Alexei Starovoitov.

24) Add support for T6 chips in cxgb4vf driver, from Hariprasad Shenai.

25) Double TCP Small Queues default to 256K to accomodate situations
    like the XEN driver and wireless aggregation.  From Wei Liu.

26) Add more entropy inputs to flow dissector, from Tom Herbert.

27) Add CDG congestion control algorithm to TCP, from Kenneth Klette
    Jonassen.

28) Convert ipset over to RCU locking, from Jozsef Kadlecsik.

29) Track and act upon link status of ipv4 route nexthops, from Andy
    Gospodarek.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1670 commits)
  bridge: vlan: flush the dynamically learned entries on port vlan delete
  bridge: multicast: add a comment to br_port_state_selection about blocking state
  net: inet_diag: export IPV6_V6ONLY sockopt
  stmmac: troubleshoot unexpected bits in des0 & des1
  net: ipv4 sysctl option to ignore routes when nexthop link is down
  net: track link-status of ipv4 nexthops
  net: switchdev: ignore unsupported bridge flags
  net: Cavium: Fix MAC address setting in shutdown state
  drivers: net: xgene: fix for ACPI support without ACPI
  ip: report the original address of ICMP messages
  net/mlx5e: Prefetch skb data on RX
  net/mlx5e: Pop cq outside mlx5e_get_cqe
  net/mlx5e: Remove mlx5e_cq.sqrq back-pointer
  net/mlx5e: Remove extra spaces
  net/mlx5e: Avoid TX CQE generation if more xmit packets expected
  net/mlx5e: Avoid redundant dev_kfree_skb() upon NOP completion
  net/mlx5e: Remove re-assignment of wq type in mlx5e_enable_rq()
  net/mlx5e: Use skb_shinfo(skb)->gso_segs rather than counting them
  net/mlx5e: Static mapping of netdev priv resources to/from netdev TX queues
  net/mlx4_en: Use HW counters for rx/tx bytes/packets in PF device
  ...

1 files changed, 56 insertions, 50 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index a369e8a..b1c218d 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -50,8 +50,8 @@ int sysctl_tcp_retrans_collapse __read_mostly = 1;
  */
 int sysctl_tcp_workaround_signed_windows __read_mostly = 0;
 
-/* Default TSQ limit of two TSO segments */
-int sysctl_tcp_limit_output_bytes __read_mostly = 131072;
+/* Default TSQ limit of four TSO segments */
+int sysctl_tcp_limit_output_bytes __read_mostly = 262144;
 
 /* This limits the percentage of the congestion window which we
  * will allow a single TSO frame to consume.  Building TSO frames
@@ -350,6 +350,15 @@ static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb)
 	}
 }
 
+static void tcp_ecn_clear_syn(struct sock *sk, struct sk_buff *skb)
+{
+	if (sock_net(sk)->ipv4.sysctl_tcp_ecn_fallback)
+		/* tp->ecn_flags are cleared at a later point in time when
+		 * SYN ACK is ultimatively being received.
+		 */
+		TCP_SKB_CB(skb)->tcp_flags &= ~(TCPHDR_ECE | TCPHDR_CWR);
+}
+
 static void
 tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th,
 		    struct sock *sk)
@@ -393,8 +402,6 @@ static void tcp_ecn_send(struct sock *sk, struct sk_buff *skb,
  */
 static void tcp_init_nondata_skb(struct sk_buff *skb, u32 seq, u8 flags)
 {
-	struct skb_shared_info *shinfo = skb_shinfo(skb);
-
 	skb->ip_summed = CHECKSUM_PARTIAL;
 	skb->csum = 0;
 
@@ -402,8 +409,6 @@ static void tcp_init_nondata_skb(struct sk_buff *skb, u32 seq, u8 flags)
 	TCP_SKB_CB(skb)->sacked = 0;
 
 	tcp_skb_pcount_set(skb, 1);
-	shinfo->gso_size = 0;
-	shinfo->gso_type = 0;
 
 	TCP_SKB_CB(skb)->seq = seq;
 	if (flags & (TCPHDR_SYN | TCPHDR_FIN))
@@ -994,6 +999,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	}
 
 	tcp_options_write((__be32 *)(th + 1), tp, &opts);
+	skb_shinfo(skb)->gso_type = sk->sk_gso_type;
 	if (likely((tcb->tcp_flags & TCPHDR_SYN) == 0))
 		tcp_ecn_send(sk, skb, tcp_header_size);
 
@@ -1018,8 +1024,10 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 		TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS,
 			      tcp_skb_pcount(skb));
 
-	/* OK, its time to fill skb_shinfo(skb)->gso_segs */
+	tp->segs_out += tcp_skb_pcount(skb);
+	/* OK, its time to fill skb_shinfo(skb)->gso_{segs|size} */
 	skb_shinfo(skb)->gso_segs = tcp_skb_pcount(skb);
+	skb_shinfo(skb)->gso_size = tcp_skb_mss(skb);
 
 	/* Our usage of tstamp should remain private */
 	skb->tstamp.tv64 = 0;
@@ -1056,25 +1064,17 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb)
 }
 
 /* Initialize TSO segments for a packet. */
-static void tcp_set_skb_tso_segs(const struct sock *sk, struct sk_buff *skb,
-				 unsigned int mss_now)
+static void tcp_set_skb_tso_segs(struct sk_buff *skb, unsigned int mss_now)
 {
-	struct skb_shared_info *shinfo = skb_shinfo(skb);
-
-	/* Make sure we own this skb before messing gso_size/gso_segs */
-	WARN_ON_ONCE(skb_cloned(skb));
-
 	if (skb->len <= mss_now || skb->ip_summed == CHECKSUM_NONE) {
 		/* Avoid the costly divide in the normal
 		 * non-TSO case.
 		 */
 		tcp_skb_pcount_set(skb, 1);
-		shinfo->gso_size = 0;
-		shinfo->gso_type = 0;
+		TCP_SKB_CB(skb)->tcp_gso_size = 0;
 	} else {
 		tcp_skb_pcount_set(skb, DIV_ROUND_UP(skb->len, mss_now));
-		shinfo->gso_size = mss_now;
-		shinfo->gso_type = sk->sk_gso_type;
+		TCP_SKB_CB(skb)->tcp_gso_size = mss_now;
 	}
 }
 
@@ -1163,7 +1163,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
 		return -ENOMEM;
 
 	/* Get a new skb... force flag on. */
-	buff = sk_stream_alloc_skb(sk, nsize, gfp);
+	buff = sk_stream_alloc_skb(sk, nsize, gfp, true);
 	if (!buff)
 		return -ENOMEM; /* We'll just try again later. */
 
@@ -1206,8 +1206,8 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
 	old_factor = tcp_skb_pcount(skb);
 
 	/* Fix up tso_factor for both original and new SKB.  */
-	tcp_set_skb_tso_segs(sk, skb, mss_now);
-	tcp_set_skb_tso_segs(sk, buff, mss_now);
+	tcp_set_skb_tso_segs(skb, mss_now);
+	tcp_set_skb_tso_segs(buff, mss_now);
 
 	/* If this packet has been sent out already, we must
 	 * adjust the various packet counters.
@@ -1287,7 +1287,7 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
 
 	/* Any change of skb->len requires recalculation of tso factor. */
 	if (tcp_skb_pcount(skb) > 1)
-		tcp_set_skb_tso_segs(sk, skb, tcp_skb_mss(skb));
+		tcp_set_skb_tso_segs(skb, tcp_skb_mss(skb));
 
 	return 0;
 }
@@ -1619,13 +1619,12 @@ static inline unsigned int tcp_cwnd_test(const struct tcp_sock *tp,
  * This must be invoked the first time we consider transmitting
  * SKB onto the wire.
  */
-static int tcp_init_tso_segs(const struct sock *sk, struct sk_buff *skb,
-			     unsigned int mss_now)
+static int tcp_init_tso_segs(struct sk_buff *skb, unsigned int mss_now)
 {
 	int tso_segs = tcp_skb_pcount(skb);
 
 	if (!tso_segs || (tso_segs > 1 && tcp_skb_mss(skb) != mss_now)) {
-		tcp_set_skb_tso_segs(sk, skb, mss_now);
+		tcp_set_skb_tso_segs(skb, mss_now);
 		tso_segs = tcp_skb_pcount(skb);
 	}
 	return tso_segs;
@@ -1680,7 +1679,7 @@ static unsigned int tcp_snd_test(const struct sock *sk, struct sk_buff *skb,
 	const struct tcp_sock *tp = tcp_sk(sk);
 	unsigned int cwnd_quota;
 
-	tcp_init_tso_segs(sk, skb, cur_mss);
+	tcp_init_tso_segs(skb, cur_mss);
 
 	if (!tcp_nagle_test(tp, skb, cur_mss, nonagle))
 		return 0;
@@ -1722,7 +1721,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
 	if (skb->len != skb->data_len)
 		return tcp_fragment(sk, skb, len, mss_now, gfp);
 
-	buff = sk_stream_alloc_skb(sk, 0, gfp);
+	buff = sk_stream_alloc_skb(sk, 0, gfp, true);
 	if (unlikely(!buff))
 		return -ENOMEM;
 
@@ -1749,8 +1748,8 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
 	tcp_fragment_tstamp(skb, buff);
 
 	/* Fix up tso_factor for both original and new SKB.  */
-	tcp_set_skb_tso_segs(sk, skb, mss_now);
-	tcp_set_skb_tso_segs(sk, buff, mss_now);
+	tcp_set_skb_tso_segs(skb, mss_now);
+	tcp_set_skb_tso_segs(buff, mss_now);
 
 	/* Link BUFF into the send queue. */
 	__skb_header_release(buff);
@@ -1941,7 +1940,7 @@ static int tcp_mtu_probe(struct sock *sk)
 	}
 
 	/* We're allowed to probe.  Build it now. */
-	nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC);
+	nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC, false);
 	if (!nskb)
 		return -1;
 	sk->sk_wmem_queued += nskb->truesize;
@@ -1984,7 +1983,7 @@ static int tcp_mtu_probe(struct sock *sk)
 								 skb->len, 0);
 			} else {
 				__pskb_trim_head(skb, copy);
-				tcp_set_skb_tso_segs(sk, skb, mss_now);
+				tcp_set_skb_tso_segs(skb, mss_now);
 			}
 			TCP_SKB_CB(skb)->seq += copy;
 		}
@@ -1994,7 +1993,7 @@ static int tcp_mtu_probe(struct sock *sk)
 		if (len >= probe_size)
 			break;
 	}
-	tcp_init_tso_segs(sk, nskb, nskb->len);
+	tcp_init_tso_segs(nskb, nskb->len);
 
 	/* We're ready to send.  If this fails, the probe will
 	 * be resegmented into mss-sized pieces by tcp_write_xmit().
@@ -2056,7 +2055,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 	while ((skb = tcp_send_head(sk))) {
 		unsigned int limit;
 
-		tso_segs = tcp_init_tso_segs(sk, skb, mss_now);
+		tso_segs = tcp_init_tso_segs(skb, mss_now);
 		BUG_ON(!tso_segs);
 
 		if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) {
@@ -2078,7 +2077,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 		if (unlikely(!tcp_snd_wnd_test(tp, skb, mss_now)))
 			break;
 
-		if (tso_segs == 1 || !max_segs) {
+		if (tso_segs == 1) {
 			if (unlikely(!tcp_nagle_test(tp, skb, mss_now,
 						     (tcp_skb_is_last(sk, skb) ?
 						      nonagle : TCP_NAGLE_PUSH))))
@@ -2091,7 +2090,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 		}
 
 		limit = mss_now;
-		if (tso_segs > 1 && max_segs && !tcp_urg_mode(tp))
+		if (tso_segs > 1 && !tcp_urg_mode(tp))
 			limit = tcp_mss_split_point(sk, skb, mss_now,
 						    min_t(unsigned int,
 							  cwnd_quota,
@@ -2392,7 +2391,7 @@ u32 __tcp_select_window(struct sock *sk)
 	if (free_space < (full_space >> 1)) {
 		icsk->icsk_ack.quick = 0;
 
-		if (sk_under_memory_pressure(sk))
+		if (tcp_under_memory_pressure(sk))
 			tp->rcv_ssthresh = min(tp->rcv_ssthresh,
 					       4U * tp->advmss);
 
@@ -2610,11 +2609,15 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 		if (unlikely(oldpcount > 1)) {
 			if (skb_unclone(skb, GFP_ATOMIC))
 				return -ENOMEM;
-			tcp_init_tso_segs(sk, skb, cur_mss);
+			tcp_init_tso_segs(skb, cur_mss);
 			tcp_adjust_pcount(sk, skb, oldpcount - tcp_skb_pcount(skb));
 		}
 	}
 
+	/* RFC3168, section 6.1.1.1. ECN fallback */
+	if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN_ECN) == TCPHDR_SYN_ECN)
+		tcp_ecn_clear_syn(sk, skb);
+
 	tcp_retrans_try_collapse(sk, skb, cur_mss);
 
 	/* Make a copy, if the first transmission SKB clone we made
@@ -2816,8 +2819,10 @@ begin_fwd:
  * connection tear down and (memory) recovery.
  * Otherwise tcp_send_fin() could be tempted to either delay FIN
  * or even be forced to close flow without any FIN.
+ * In general, we want to allow one skb per socket to avoid hangs
+ * with edge trigger epoll()
  */
-static void sk_forced_wmem_schedule(struct sock *sk, int size)
+void sk_forced_mem_schedule(struct sock *sk, int size)
 {
 	int amt, status;
 
@@ -2841,7 +2846,7 @@ void tcp_send_fin(struct sock *sk)
 	 * Note: in the latter case, FIN packet will be sent after a timeout,
 	 * as TCP stack thinks it has already been transmitted.
 	 */
-	if (tskb && (tcp_send_head(sk) || sk_under_memory_pressure(sk))) {
+	if (tskb && (tcp_send_head(sk) || tcp_under_memory_pressure(sk))) {
 coalesce:
 		TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN;
 		TCP_SKB_CB(tskb)->end_seq++;
@@ -2864,7 +2869,7 @@ coalesce:
 			return;
 		}
 		skb_reserve(skb, MAX_TCP_HEADER);
-		sk_forced_wmem_schedule(sk, skb->truesize);
+		sk_forced_mem_schedule(sk, skb->truesize);
 		/* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */
 		tcp_init_nondata_skb(skb, tp->write_seq,
 				     TCPHDR_ACK | TCPHDR_FIN);
@@ -3175,7 +3180,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 	/* limit to order-0 allocations */
 	space = min_t(size_t, space, SKB_MAX_HEAD(MAX_TCP_HEADER));
 
-	syn_data = sk_stream_alloc_skb(sk, space, sk->sk_allocation);
+	syn_data = sk_stream_alloc_skb(sk, space, sk->sk_allocation, false);
 	if (!syn_data)
 		goto fallback;
 	syn_data->ip_summed = CHECKSUM_PARTIAL;
@@ -3241,7 +3246,7 @@ int tcp_connect(struct sock *sk)
 		return 0;
 	}
 
-	buff = sk_stream_alloc_skb(sk, 0, sk->sk_allocation);
+	buff = sk_stream_alloc_skb(sk, 0, sk->sk_allocation, true);
 	if (unlikely(!buff))
 		return -ENOBUFS;
 
@@ -3382,7 +3387,7 @@ EXPORT_SYMBOL_GPL(tcp_send_ack);
  * one is with SEG.SEQ=SND.UNA to deliver urgent pointer, another is
  * out-of-date with SND.UNA-1 to probe window.
  */
-static int tcp_xmit_probe_skb(struct sock *sk, int urgent)
+static int tcp_xmit_probe_skb(struct sock *sk, int urgent, int mib)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb;
@@ -3400,6 +3405,7 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent)
 	 */
 	tcp_init_nondata_skb(skb, tp->snd_una - !urgent, TCPHDR_ACK);
 	skb_mstamp_get(&skb->skb_mstamp);
+	NET_INC_STATS_BH(sock_net(sk), mib);
 	return tcp_transmit_skb(sk, skb, 0, GFP_ATOMIC);
 }
 
@@ -3407,12 +3413,12 @@ void tcp_send_window_probe(struct sock *sk)
 {
 	if (sk->sk_state == TCP_ESTABLISHED) {
 		tcp_sk(sk)->snd_wl1 = tcp_sk(sk)->rcv_nxt - 1;
-		tcp_xmit_probe_skb(sk, 0);
+		tcp_xmit_probe_skb(sk, 0, LINUX_MIB_TCPWINPROBE);
 	}
 }
 
 /* Initiate keepalive or window probe from timer. */
-int tcp_write_wakeup(struct sock *sk)
+int tcp_write_wakeup(struct sock *sk, int mib)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb;
@@ -3440,7 +3446,7 @@ int tcp_write_wakeup(struct sock *sk)
 			if (tcp_fragment(sk, skb, seg_size, mss, GFP_ATOMIC))
 				return -1;
 		} else if (!tcp_skb_pcount(skb))
-			tcp_set_skb_tso_segs(sk, skb, mss);
+			tcp_set_skb_tso_segs(skb, mss);
 
 		TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH;
 		err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
@@ -3449,8 +3455,8 @@ int tcp_write_wakeup(struct sock *sk)
 		return err;
 	} else {
 		if (between(tp->snd_up, tp->snd_una + 1, tp->snd_una + 0xFFFF))
-			tcp_xmit_probe_skb(sk, 1);
-		return tcp_xmit_probe_skb(sk, 0);
+			tcp_xmit_probe_skb(sk, 1, mib);
+		return tcp_xmit_probe_skb(sk, 0, mib);
 	}
 }
 
@@ -3464,7 +3470,7 @@ void tcp_send_probe0(struct sock *sk)
 	unsigned long probe_max;
 	int err;
 
-	err = tcp_write_wakeup(sk);
+	err = tcp_write_wakeup(sk, LINUX_MIB_TCPWINPROBE);
 
 	if (tp->packets_out || !tcp_send_head(sk)) {
 		/* Cancel probe timer, if it is not required. */
@@ -3490,7 +3496,7 @@ void tcp_send_probe0(struct sock *sk)
 		probe_max = TCP_RESOURCE_PROBE_INTERVAL;
 	}
 	inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
-				  inet_csk_rto_backoff(icsk, probe_max),
+				  tcp_probe0_when(sk, probe_max),
 				  TCP_RTO_MAX);
 }