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, 42 insertions, 50 deletions

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 969a85960e9f..831eb4fd197d 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -276,12 +276,12 @@ static void copy_iovec_hdr(const struct iovec *from, struct iovec *to,
  * of used idx. Once lower device DMA done contiguously, we will signal KVM
  * guest used idx.
  */
-static int vhost_zerocopy_signal_used(struct vhost_net *net,
-				      struct vhost_virtqueue *vq)
+static void vhost_zerocopy_signal_used(struct vhost_net *net,
+				       struct vhost_virtqueue *vq)
 {
 	struct vhost_net_virtqueue *nvq =
 		container_of(vq, struct vhost_net_virtqueue, vq);
-	int i;
+	int i, add;
 	int j = 0;
 
 	for (i = nvq->done_idx; i != nvq->upend_idx; i = (i + 1) % UIO_MAXIOV) {
@@ -289,15 +289,17 @@ static int vhost_zerocopy_signal_used(struct vhost_net *net,
 			vhost_net_tx_err(net);
 		if (VHOST_DMA_IS_DONE(vq->heads[i].len)) {
 			vq->heads[i].len = VHOST_DMA_CLEAR_LEN;
-			vhost_add_used_and_signal(vq->dev, vq,
-						  vq->heads[i].id, 0);
 			++j;
 		} else
 			break;
 	}
-	if (j)
-		nvq->done_idx = i;
-	return j;
+	while (j) {
+		add = min(UIO_MAXIOV - nvq->done_idx, j);
+		vhost_add_used_and_signal_n(vq->dev, vq,
+					    &vq->heads[nvq->done_idx], add);
+		nvq->done_idx = (nvq->done_idx + add) % UIO_MAXIOV;
+		j -= add;
+	}
 }
 
 static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success)
@@ -306,6 +308,11 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success)
 	struct vhost_virtqueue *vq = ubufs->vq;
 	int cnt = atomic_read(&ubufs->kref.refcount);
 
+	/* set len to mark this desc buffers done DMA */
+	vq->heads[ubuf->desc].len = success ?
+		VHOST_DMA_DONE_LEN : VHOST_DMA_FAILED_LEN;
+	vhost_net_ubuf_put(ubufs);
+
 	/*
 	 * Trigger polling thread if guest stopped submitting new buffers:
 	 * in this case, the refcount after decrement will eventually reach 1
@@ -316,10 +323,6 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success)
 	 */
 	if (cnt <= 2 || !(cnt % 16))
 		vhost_poll_queue(&vq->poll);
-	/* set len to mark this desc buffers done DMA */
-	vq->heads[ubuf->desc].len = success ?
-		VHOST_DMA_DONE_LEN : VHOST_DMA_FAILED_LEN;
-	vhost_net_ubuf_put(ubufs);
 }
 
 /* Expects to be always run from workqueue - which acts as
@@ -360,6 +363,13 @@ static void handle_tx(struct vhost_net *net)
 		if (zcopy)
 			vhost_zerocopy_signal_used(net, vq);
 
+		/* If more outstanding DMAs, queue the work.
+		 * Handle upend_idx wrap around
+		 */
+		if (unlikely((nvq->upend_idx + vq->num - VHOST_MAX_PEND)
+			      % UIO_MAXIOV == nvq->done_idx))
+			break;
+
 		head = vhost_get_vq_desc(&net->dev, vq, vq->iov,
 					 ARRAY_SIZE(vq->iov),
 					 &out, &in,
@@ -369,17 +379,6 @@ static void handle_tx(struct vhost_net *net)
 			break;
 		/* Nothing new?  Wait for eventfd to tell us they refilled. */
 		if (head == vq->num) {
-			int num_pends;
-
-			/* If more outstanding DMAs, queue the work.
-			 * Handle upend_idx wrap around
-			 */
-			num_pends = likely(nvq->upend_idx >= nvq->done_idx) ?
-				    (nvq->upend_idx - nvq->done_idx) :
-				    (nvq->upend_idx + UIO_MAXIOV -
-				     nvq->done_idx);
-			if (unlikely(num_pends > VHOST_MAX_PEND))
-				break;
 			if (unlikely(vhost_enable_notify(&net->dev, vq))) {
 				vhost_disable_notify(&net->dev, vq);
 				continue;
@@ -402,43 +401,36 @@ static void handle_tx(struct vhost_net *net)
 			       iov_length(nvq->hdr, s), hdr_size);
 			break;
 		}
-		zcopy_used = zcopy && (len >= VHOST_GOODCOPY_LEN ||
-				       nvq->upend_idx != nvq->done_idx);
+
+		zcopy_used = zcopy && len >= VHOST_GOODCOPY_LEN
+				   && (nvq->upend_idx + 1) % UIO_MAXIOV !=
+				      nvq->done_idx
+				   && vhost_net_tx_select_zcopy(net);
 
 		/* use msg_control to pass vhost zerocopy ubuf info to skb */
 		if (zcopy_used) {
+			struct ubuf_info *ubuf;
+			ubuf = nvq->ubuf_info + nvq->upend_idx;
+
 			vq->heads[nvq->upend_idx].id = head;
-			if (!vhost_net_tx_select_zcopy(net) ||
-			    len < VHOST_GOODCOPY_LEN) {
-				/* copy don't need to wait for DMA done */
-				vq->heads[nvq->upend_idx].len =
-							VHOST_DMA_DONE_LEN;
-				msg.msg_control = NULL;
-				msg.msg_controllen = 0;
-				ubufs = NULL;
-			} else {
-				struct ubuf_info *ubuf;
-				ubuf = nvq->ubuf_info + nvq->upend_idx;
-
-				vq->heads[nvq->upend_idx].len =
-					VHOST_DMA_IN_PROGRESS;
-				ubuf->callback = vhost_zerocopy_callback;
-				ubuf->ctx = nvq->ubufs;
-				ubuf->desc = nvq->upend_idx;
-				msg.msg_control = ubuf;
-				msg.msg_controllen = sizeof(ubuf);
-				ubufs = nvq->ubufs;
-				kref_get(&ubufs->kref);
-			}
+			vq->heads[nvq->upend_idx].len = VHOST_DMA_IN_PROGRESS;
+			ubuf->callback = vhost_zerocopy_callback;
+			ubuf->ctx = nvq->ubufs;
+			ubuf->desc = nvq->upend_idx;
+			msg.msg_control = ubuf;
+			msg.msg_controllen = sizeof(ubuf);
+			ubufs = nvq->ubufs;
+			kref_get(&ubufs->kref);
 			nvq->upend_idx = (nvq->upend_idx + 1) % UIO_MAXIOV;
-		} else
+		} else {
 			msg.msg_control = NULL;
+			ubufs = NULL;
+		}
 		/* TODO: Check specific error and bomb out unless ENOBUFS? */
 		err = sock->ops->sendmsg(NULL, sock, &msg, len);
 		if (unlikely(err < 0)) {
 			if (zcopy_used) {
-				if (ubufs)
-					vhost_net_ubuf_put(ubufs);
+				vhost_net_ubuf_put(ubufs);
 				nvq->upend_idx = ((unsigned)nvq->upend_idx - 1)
 					% UIO_MAXIOV;
 			}