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

Pull networking changes from David Miller:
 "Noteworthy changes this time around:

   1) Multicast rejoin support for team driver, from Jiri Pirko.

   2) Centralize and simplify TCP RTT measurement handling in order to
      reduce the impact of bad RTO seeding from SYN/ACKs.  Also, when
      both timestamps and local RTT measurements are available prefer
      the later because there are broken middleware devices which
      scramble the timestamp.

      From Yuchung Cheng.

   3) Add TCP_NOTSENT_LOWAT socket option to limit the amount of kernel
      memory consumed to queue up unsend user data.  From Eric Dumazet.

   4) Add a "physical port ID" abstraction for network devices, from
      Jiri Pirko.

   5) Add a "suppress" operation to influence fib_rules lookups, from
      Stefan Tomanek.

   6) Add a networking development FAQ, from Paul Gortmaker.

   7) Extend the information provided by tcp_probe and add ipv6 support,
      from Daniel Borkmann.

   8) Use RCU locking more extensively in openvswitch data paths, from
      Pravin B Shelar.

   9) Add SCTP support to openvswitch, from Joe Stringer.

  10) Add EF10 chip support to SFC driver, from Ben Hutchings.

  11) Add new SYNPROXY netfilter target, from Patrick McHardy.

  12) Compute a rate approximation for sending in TCP sockets, and use
      this to more intelligently coalesce TSO frames.  Furthermore, add
      a new packet scheduler which takes advantage of this estimate when
      available.  From Eric Dumazet.

  13) Allow AF_PACKET fanouts with random selection, from Daniel
      Borkmann.

  14) Add ipv6 support to vxlan driver, from Cong Wang"

Resolved conflicts as per discussion.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1218 commits)
  openvswitch: Fix alignment of struct sw_flow_key.
  netfilter: Fix build errors with xt_socket.c
  tcp: Add missing braces to do_tcp_setsockopt
  caif: Add missing braces to multiline if in cfctrl_linkup_request
  bnx2x: Add missing braces in bnx2x:bnx2x_link_initialize
  vxlan: Fix kernel panic on device delete.
  net: mvneta: implement ->ndo_do_ioctl() to support PHY ioctls
  net: mvneta: properly disable HW PHY polling and ensure adjust_link() works
  icplus: Use netif_running to determine device state
  ethernet/arc/arc_emac: Fix huge delays in large file copies
  tuntap: orphan frags before trying to set tx timestamp
  tuntap: purge socket error queue on detach
  qlcnic: use standard NAPI weights
  ipv6:introduce function to find route for redirect
  bnx2x: VF RSS support - VF side
  bnx2x: VF RSS support - PF side
  vxlan: Notify drivers for listening UDP port changes
  net: usbnet: update addr_assign_type if appropriate
  driver/net: enic: update enic maintainers and driver
  driver/net: enic: Exposing symbols for Cisco's low latency driver
  ...

1 files changed, 16 insertions, 49 deletions

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 75c8bbf598c8..2e8286b47c28 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -88,7 +88,7 @@
 #include <linux/virtio_net.h>
 #include <linux/errqueue.h>
 #include <linux/net_tstamp.h>
-
+#include <linux/reciprocal_div.h>
 #ifdef CONFIG_INET
 #include <net/inet_common.h>
 #endif
@@ -1135,7 +1135,7 @@ static unsigned int fanout_demux_hash(struct packet_fanout *f,
 				      struct sk_buff *skb,
 				      unsigned int num)
 {
-	return (((u64)skb->rxhash) * num) >> 32;
+	return reciprocal_divide(skb->rxhash, num);
 }
 
 static unsigned int fanout_demux_lb(struct packet_fanout *f,
@@ -1158,6 +1158,13 @@ static unsigned int fanout_demux_cpu(struct packet_fanout *f,
 	return smp_processor_id() % num;
 }
 
+static unsigned int fanout_demux_rnd(struct packet_fanout *f,
+				     struct sk_buff *skb,
+				     unsigned int num)
+{
+	return reciprocal_divide(prandom_u32(), num);
+}
+
 static unsigned int fanout_demux_rollover(struct packet_fanout *f,
 					  struct sk_buff *skb,
 					  unsigned int idx, unsigned int skip,
@@ -1215,6 +1222,9 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev,
 	case PACKET_FANOUT_CPU:
 		idx = fanout_demux_cpu(f, skb, num);
 		break;
+	case PACKET_FANOUT_RND:
+		idx = fanout_demux_rnd(f, skb, num);
+		break;
 	case PACKET_FANOUT_ROLLOVER:
 		idx = fanout_demux_rollover(f, skb, 0, (unsigned int) -1, num);
 		break;
@@ -1284,6 +1294,7 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 	case PACKET_FANOUT_HASH:
 	case PACKET_FANOUT_LB:
 	case PACKET_FANOUT_CPU:
+	case PACKET_FANOUT_RND:
 		break;
 	default:
 		return -EINVAL;
@@ -2181,7 +2192,7 @@ static struct sk_buff *packet_alloc_skb(struct sock *sk, size_t prepad,
 		linear = len;
 
 	skb = sock_alloc_send_pskb(sk, prepad + linear, len - linear, noblock,
-				   err);
+				   err, 0);
 	if (!skb)
 		return NULL;
 
@@ -2638,51 +2649,6 @@ out:
 	return err;
 }
 
-static int packet_recv_error(struct sock *sk, struct msghdr *msg, int len)
-{
-	struct sock_exterr_skb *serr;
-	struct sk_buff *skb, *skb2;
-	int copied, err;
-
-	err = -EAGAIN;
-	skb = skb_dequeue(&sk->sk_error_queue);
-	if (skb == NULL)
-		goto out;
-
-	copied = skb->len;
-	if (copied > len) {
-		msg->msg_flags |= MSG_TRUNC;
-		copied = len;
-	}
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
-	if (err)
-		goto out_free_skb;
-
-	sock_recv_timestamp(msg, sk, skb);
-
-	serr = SKB_EXT_ERR(skb);
-	put_cmsg(msg, SOL_PACKET, PACKET_TX_TIMESTAMP,
-		 sizeof(serr->ee), &serr->ee);
-
-	msg->msg_flags |= MSG_ERRQUEUE;
-	err = copied;
-
-	/* Reset and regenerate socket error */
-	spin_lock_bh(&sk->sk_error_queue.lock);
-	sk->sk_err = 0;
-	if ((skb2 = skb_peek(&sk->sk_error_queue)) != NULL) {
-		sk->sk_err = SKB_EXT_ERR(skb2)->ee.ee_errno;
-		spin_unlock_bh(&sk->sk_error_queue.lock);
-		sk->sk_error_report(sk);
-	} else
-		spin_unlock_bh(&sk->sk_error_queue.lock);
-
-out_free_skb:
-	kfree_skb(skb);
-out:
-	return err;
-}
-
 /*
  *	Pull a packet from our receive queue and hand it to the user.
  *	If necessary we block.
@@ -2708,7 +2674,8 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
 #endif
 
 	if (flags & MSG_ERRQUEUE) {
-		err = packet_recv_error(sk, msg, len);
+		err = sock_recv_errqueue(sk, msg, len,
+					 SOL_PACKET, PACKET_TX_TIMESTAMP);
 		goto out;
 	}