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

Pull networking updates from David Miller:
 "Most notable changes in here:

   1) By far the biggest accomplishment, thanks to a large range of
      contributors, is the addition of multi-send for transmit.  This is
      the result of discussions back in Chicago, and the hard work of
      several individuals.

      Now, when the ->ndo_start_xmit() method of a driver sees
      skb->xmit_more as true, it can choose to defer the doorbell
      telling the driver to start processing the new TX queue entires.

      skb->xmit_more means that the generic networking is guaranteed to
      call the driver immediately with another SKB to send.

      There is logic added to the qdisc layer to dequeue multiple
      packets at a time, and the handling mis-predicted offloads in
      software is now done with no locks held.

      Finally, pktgen is extended to have a "burst" parameter that can
      be used to test a multi-send implementation.

      Several drivers have xmit_more support: i40e, igb, ixgbe, mlx4,
      virtio_net

      Adding support is almost trivial, so export more drivers to
      support this optimization soon.

      I want to thank, in no particular or implied order, Jesper
      Dangaard Brouer, Eric Dumazet, Alexander Duyck, Tom Herbert, Jamal
      Hadi Salim, John Fastabend, Florian Westphal, Daniel Borkmann,
      David Tat, Hannes Frederic Sowa, and Rusty Russell.

   2) PTP and timestamping support in bnx2x, from Michal Kalderon.

   3) Allow adjusting the rx_copybreak threshold for a driver via
      ethtool, and add rx_copybreak support to enic driver.  From
      Govindarajulu Varadarajan.

   4) Significant enhancements to the generic PHY layer and the bcm7xxx
      driver in particular (EEE support, auto power down, etc.) from
      Florian Fainelli.

   5) Allow raw buffers to be used for flow dissection, allowing drivers
      to determine the optimal "linear pull" size for devices that DMA
      into pools of pages.  The objective is to get exactly the
      necessary amount of headers into the linear SKB area pre-pulled,
      but no more.  The new interface drivers use is eth_get_headlen().
      From WANG Cong, with driver conversions (several had their own
      by-hand duplicated implementations) by Alexander Duyck and Eric
      Dumazet.

   6) Support checksumming more smoothly and efficiently for
      encapsulations, and add "foo over UDP" facility.  From Tom
      Herbert.

   7) Add Broadcom SF2 switch driver to DSA layer, from Florian
      Fainelli.

   8) eBPF now can load programs via a system call and has an extensive
      testsuite.  Alexei Starovoitov and Daniel Borkmann.

   9) Major overhaul of the packet scheduler to use RCU in several major
      areas such as the classifiers and rate estimators.  From John
      Fastabend.

  10) Add driver for Intel FM10000 Ethernet Switch, from Alexander
      Duyck.

  11) Rearrange TCP_SKB_CB() to reduce cache line misses, from Eric
      Dumazet.

  12) Add Datacenter TCP congestion control algorithm support, From
      Florian Westphal.

  13) Reorganize sk_buff so that __copy_skb_header() is significantly
      faster.  From Eric Dumazet"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1558 commits)
  netlabel: directly return netlbl_unlabel_genl_init()
  net: add netdev_txq_bql_{enqueue, complete}_prefetchw() helpers
  net: description of dma_cookie cause make xmldocs warning
  cxgb4: clean up a type issue
  cxgb4: potential shift wrapping bug
  i40e: skb->xmit_more support
  net: fs_enet: Add NAPI TX
  net: fs_enet: Remove non NAPI RX
  r8169:add support for RTL8168EP
  net_sched: copy exts->type in tcf_exts_change()
  wimax: convert printk to pr_foo()
  af_unix: remove 0 assignment on static
  ipv6: Do not warn for informational ICMP messages, regardless of type.
  Update Intel Ethernet Driver maintainers list
  bridge: Save frag_max_size between PRE_ROUTING and POST_ROUTING
  tipc: fix bug in multicast congestion handling
  net: better IFF_XMIT_DST_RELEASE support
  net/mlx4_en: remove NETDEV_TX_BUSY
  3c59x: fix bad split of cpu_to_le32(pci_map_single())
  net: bcmgenet: fix Tx ring priority programming
  ...

1 files changed, 44 insertions, 24 deletions

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index fbea536cf5c0..552e87e3c269 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -89,7 +89,6 @@ int sysctl_tcp_tw_reuse __read_mostly;
 int sysctl_tcp_low_latency __read_mostly;
 EXPORT_SYMBOL(sysctl_tcp_low_latency);
 
-
 #ifdef CONFIG_TCP_MD5SIG
 static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
 			       __be32 daddr, __be32 saddr, const struct tcphdr *th);
@@ -430,15 +429,16 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 			break;
 
 		icsk->icsk_backoff--;
-		inet_csk(sk)->icsk_rto = (tp->srtt_us ? __tcp_set_rto(tp) :
-			TCP_TIMEOUT_INIT) << icsk->icsk_backoff;
-		tcp_bound_rto(sk);
+		icsk->icsk_rto = tp->srtt_us ? __tcp_set_rto(tp) :
+					       TCP_TIMEOUT_INIT;
+		icsk->icsk_rto = inet_csk_rto_backoff(icsk, TCP_RTO_MAX);
 
 		skb = tcp_write_queue_head(sk);
 		BUG_ON(!skb);
 
-		remaining = icsk->icsk_rto - min(icsk->icsk_rto,
-				tcp_time_stamp - TCP_SKB_CB(skb)->when);
+		remaining = icsk->icsk_rto -
+			    min(icsk->icsk_rto,
+				tcp_time_stamp - tcp_skb_timestamp(skb));
 
 		if (remaining) {
 			inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
@@ -680,8 +680,9 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
 
 	net = dev_net(skb_dst(skb)->dev);
 	arg.tos = ip_hdr(skb)->tos;
-	ip_send_unicast_reply(net, skb, ip_hdr(skb)->saddr,
-			      ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len);
+	ip_send_unicast_reply(net, skb, &TCP_SKB_CB(skb)->header.h4.opt,
+			      ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
+			      &arg, arg.iov[0].iov_len);
 
 	TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS);
 	TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS);
@@ -763,8 +764,9 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
 	if (oif)
 		arg.bound_dev_if = oif;
 	arg.tos = tos;
-	ip_send_unicast_reply(net, skb, ip_hdr(skb)->saddr,
-			      ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len);
+	ip_send_unicast_reply(net, skb, &TCP_SKB_CB(skb)->header.h4.opt,
+			      ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
+			      &arg, arg.iov[0].iov_len);
 
 	TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS);
 }
@@ -883,18 +885,16 @@ EXPORT_SYMBOL(tcp_syn_flood_action);
  */
 static struct ip_options_rcu *tcp_v4_save_options(struct sk_buff *skb)
 {
-	const struct ip_options *opt = &(IPCB(skb)->opt);
+	const struct ip_options *opt = &TCP_SKB_CB(skb)->header.h4.opt;
 	struct ip_options_rcu *dopt = NULL;
 
 	if (opt && opt->optlen) {
 		int opt_size = sizeof(*dopt) + opt->optlen;
 
 		dopt = kmalloc(opt_size, GFP_ATOMIC);
-		if (dopt) {
-			if (ip_options_echo(&dopt->opt, skb)) {
-				kfree(dopt);
-				dopt = NULL;
-			}
+		if (dopt && __ip_options_echo(&dopt->opt, skb, opt)) {
+			kfree(dopt);
+			dopt = NULL;
 		}
 	}
 	return dopt;
@@ -1268,7 +1268,7 @@ struct request_sock_ops tcp_request_sock_ops __read_mostly = {
 	.send_ack	=	tcp_v4_reqsk_send_ack,
 	.destructor	=	tcp_v4_reqsk_destructor,
 	.send_reset	=	tcp_v4_send_reset,
-	.syn_ack_timeout = 	tcp_syn_ack_timeout,
+	.syn_ack_timeout =	tcp_syn_ack_timeout,
 };
 
 static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = {
@@ -1428,7 +1428,7 @@ static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb)
 
 #ifdef CONFIG_SYN_COOKIES
 	if (!th->syn)
-		sk = cookie_v4_check(sk, skb, &(IPCB(skb)->opt));
+		sk = cookie_v4_check(sk, skb, &TCP_SKB_CB(skb)->header.h4.opt);
 #endif
 	return sk;
 }
@@ -1558,7 +1558,17 @@ bool tcp_prequeue(struct sock *sk, struct sk_buff *skb)
 	    skb_queue_len(&tp->ucopy.prequeue) == 0)
 		return false;
 
-	skb_dst_force(skb);
+	/* Before escaping RCU protected region, we need to take care of skb
+	 * dst. Prequeue is only enabled for established sockets.
+	 * For such sockets, we might need the skb dst only to set sk->sk_rx_dst
+	 * Instead of doing full sk_rx_dst validity here, let's perform
+	 * an optimistic check.
+	 */
+	if (likely(sk->sk_rx_dst))
+		skb_dst_drop(skb);
+	else
+		skb_dst_force(skb);
+
 	__skb_queue_tail(&tp->ucopy.prequeue, skb);
 	tp->ucopy.memory += skb->truesize;
 	if (tp->ucopy.memory > sk->sk_rcvbuf) {
@@ -1623,11 +1633,19 @@ int tcp_v4_rcv(struct sk_buff *skb)
 
 	th = tcp_hdr(skb);
 	iph = ip_hdr(skb);
+	/* This is tricky : We move IPCB at its correct location into TCP_SKB_CB()
+	 * barrier() makes sure compiler wont play fool^Waliasing games.
+	 */
+	memmove(&TCP_SKB_CB(skb)->header.h4, IPCB(skb),
+		sizeof(struct inet_skb_parm));
+	barrier();
+
 	TCP_SKB_CB(skb)->seq = ntohl(th->seq);
 	TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
 				    skb->len - th->doff * 4);
 	TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
-	TCP_SKB_CB(skb)->when	 = 0;
+	TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
+	TCP_SKB_CB(skb)->tcp_tw_isn = 0;
 	TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph);
 	TCP_SKB_CB(skb)->sacked	 = 0;
 
@@ -1754,9 +1772,11 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
 
-	dst_hold(dst);
-	sk->sk_rx_dst = dst;
-	inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
+	if (dst) {
+		dst_hold(dst);
+		sk->sk_rx_dst = dst;
+		inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
+	}
 }
 EXPORT_SYMBOL(inet_sk_rx_dst_set);
 
@@ -2167,7 +2187,7 @@ int tcp_seq_open(struct inode *inode, struct file *file)
 
 	s = ((struct seq_file *)file->private_data)->private;
 	s->family		= afinfo->family;
-	s->last_pos 		= 0;
+	s->last_pos		= 0;
 	return 0;
 }
 EXPORT_SYMBOL(tcp_seq_open);