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, 34 insertions, 36 deletions

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index c4ce243824bb..86de99ad2976 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1479,7 +1479,8 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
 				 MAX_SKB_FRAGS * PAGE_SIZE);
 
 	skb = sock_alloc_send_pskb(sk, len - data_len, data_len,
-				   msg->msg_flags & MSG_DONTWAIT, &err);
+				   msg->msg_flags & MSG_DONTWAIT, &err,
+				   PAGE_ALLOC_COSTLY_ORDER);
 	if (skb == NULL)
 		goto out;
 
@@ -1596,6 +1597,10 @@ out:
 	return err;
 }
 
+/* We use paged skbs for stream sockets, and limit occupancy to 32768
+ * bytes, and a minimun of a full page.
+ */
+#define UNIX_SKB_FRAGS_SZ (PAGE_SIZE << get_order(32768))
 
 static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
 			       struct msghdr *msg, size_t len)
@@ -1609,6 +1614,7 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	struct scm_cookie tmp_scm;
 	bool fds_sent = false;
 	int max_level;
+	int data_len;
 
 	if (NULL == siocb->scm)
 		siocb->scm = &tmp_scm;
@@ -1635,40 +1641,22 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
 		goto pipe_err;
 
 	while (sent < len) {
-		/*
-		 *	Optimisation for the fact that under 0.01% of X
-		 *	messages typically need breaking up.
-		 */
-
-		size = len-sent;
+		size = len - sent;
 
 		/* Keep two messages in the pipe so it schedules better */
-		if (size > ((sk->sk_sndbuf >> 1) - 64))
-			size = (sk->sk_sndbuf >> 1) - 64;
+		size = min_t(int, size, (sk->sk_sndbuf >> 1) - 64);
 
-		if (size > SKB_MAX_ALLOC)
-			size = SKB_MAX_ALLOC;
-
-		/*
-		 *	Grab a buffer
-		 */
+		/* allow fallback to order-0 allocations */
+		size = min_t(int, size, SKB_MAX_HEAD(0) + UNIX_SKB_FRAGS_SZ);
 
-		skb = sock_alloc_send_skb(sk, size, msg->msg_flags&MSG_DONTWAIT,
-					  &err);
+		data_len = max_t(int, 0, size - SKB_MAX_HEAD(0));
 
-		if (skb == NULL)
+		skb = sock_alloc_send_pskb(sk, size - data_len, data_len,
+					   msg->msg_flags & MSG_DONTWAIT, &err,
+					   get_order(UNIX_SKB_FRAGS_SZ));
+		if (!skb)
 			goto out_err;
 
-		/*
-		 *	If you pass two values to the sock_alloc_send_skb
-		 *	it tries to grab the large buffer with GFP_NOFS
-		 *	(which can fail easily), and if it fails grab the
-		 *	fallback size buffer which is under a page and will
-		 *	succeed. [Alan]
-		 */
-		size = min_t(int, size, skb_tailroom(skb));
-
-
 		/* Only send the fds in the first buffer */
 		err = unix_scm_to_skb(siocb->scm, skb, !fds_sent);
 		if (err < 0) {
@@ -1678,7 +1666,11 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
 		max_level = err + 1;
 		fds_sent = true;
 
-		err = memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size);
+		skb_put(skb, size - data_len);
+		skb->data_len = data_len;
+		skb->len = size;
+		err = skb_copy_datagram_from_iovec(skb, 0, msg->msg_iov,
+						   sent, size);
 		if (err) {
 			kfree_skb(skb);
 			goto out_err;
@@ -1890,6 +1882,11 @@ static long unix_stream_data_wait(struct sock *sk, long timeo,
 	return timeo;
 }
 
+static unsigned int unix_skb_len(const struct sk_buff *skb)
+{
+	return skb->len - UNIXCB(skb).consumed;
+}
+
 static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 			       struct msghdr *msg, size_t size,
 			       int flags)
@@ -1977,8 +1974,8 @@ again:
 		}
 
 		skip = sk_peek_offset(sk, flags);
-		while (skip >= skb->len) {
-			skip -= skb->len;
+		while (skip >= unix_skb_len(skb)) {
+			skip -= unix_skb_len(skb);
 			last = skb;
 			skb = skb_peek_next(skb, &sk->sk_receive_queue);
 			if (!skb)
@@ -2005,8 +2002,9 @@ again:
 			sunaddr = NULL;
 		}
 
-		chunk = min_t(unsigned int, skb->len - skip, size);
-		if (memcpy_toiovec(msg->msg_iov, skb->data + skip, chunk)) {
+		chunk = min_t(unsigned int, unix_skb_len(skb) - skip, size);
+		if (skb_copy_datagram_iovec(skb, UNIXCB(skb).consumed + skip,
+					    msg->msg_iov, chunk)) {
 			if (copied == 0)
 				copied = -EFAULT;
 			break;
@@ -2016,14 +2014,14 @@ again:
 
 		/* Mark read part of skb as used */
 		if (!(flags & MSG_PEEK)) {
-			skb_pull(skb, chunk);
+			UNIXCB(skb).consumed += chunk;
 
 			sk_peek_offset_bwd(sk, chunk);
 
 			if (UNIXCB(skb).fp)
 				unix_detach_fds(siocb->scm, skb);
 
-			if (skb->len)
+			if (unix_skb_len(skb))
 				break;
 
 			skb_unlink(skb, &sk->sk_receive_queue);
@@ -2107,7 +2105,7 @@ long unix_inq_len(struct sock *sk)
 	if (sk->sk_type == SOCK_STREAM ||
 	    sk->sk_type == SOCK_SEQPACKET) {
 		skb_queue_walk(&sk->sk_receive_queue, skb)
-			amount += skb->len;
+			amount += unix_skb_len(skb);
 	} else {
 		skb = skb_peek(&sk->sk_receive_queue);
 		if (skb)