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

Pull networking fixes from David Miller:
 "I'm sending this out, in particular, to get the iwlwifi fix
  propagated:

   1) Fix build due to missing include in i40e driver, from Lucas
      Tanure.

   2) Memory leak in openvswitch port allocation, from Chirstoph Jaeger.

   3) Check DMA mapping errors in myri10ge, from Stanislaw Gruszka.

   4) Fix various deadlock scenerios in sunvnet driver, from Sowmini
      Varadhan.

   5) Fix cxgb4i build failures with incompatible Kconfig settings of
      the driver vs ipv6, from Anish Bhatt.

   6) Fix generation of ACK packet timestamps in the presence of TSO
      which will be split up, from Willem de Bruijn.

   7) Don't enable sched scan in iwlwifi driver, it causes firmware
      crashes in some revisions.  From Emmanuel Grumbach.

   8) Revert a macvlan simplification that causes crashes.

   9) Handle RTT calculations properly in the presence of repair'd SKBs,
      from Andrey Vagin.

  10) SIT tunnel lookup uses wrong device index in compares, from
      Shmulik Ladkani.

  11) Handle MTU reductions in TCP properly for ipv4 mapped ipv6
      sockets, from Neal Cardwell.

  12) Add missing annotations in rhashtable code, from Thomas Graf.

  13) Fix false interpretation of two RTOs as being from the same TCP
      loss event in the FRTO code, from Neal Cardwell"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (42 commits)
  netlink: Annotate RCU locking for seq_file walker
  rhashtable: fix annotations for rht_for_each_entry_rcu()
  rhashtable: unexport and make rht_obj() static
  rhashtable: RCU annotations for next pointers
  tcp: fix ssthresh and undo for consecutive short FRTO episodes
  tcp: don't allow syn packets without timestamps to pass tcp_tw_recycle logic
  tcp: fix tcp_release_cb() to dispatch via address family for mtu_reduced()
  sit: Fix ipip6_tunnel_lookup device matching criteria
  net: ethernet: ibm: ehea: Remove duplicate object from Makefile
  net: xgene: Check negative return value of xgene_enet_get_ring_size()
  tcp: don't use timestamp from repaired skb-s to calculate RTT (v2)
  net: xilinx: Remove .owner field for driver
  Revert "macvlan: simplify the structure port"
  iwlwifi: mvm: disable scheduled scan to prevent firmware crash
  xen-netback: remove loop waiting function
  xen-netback: don't stop dealloc kthread too early
  xen-netback: move NAPI add/remove calls
  xen-netback: fix debugfs entry creation
  xen-netback: fix debugfs write length check
  net-timestamp: fix missing tcp fragmentation cases
  ...

1 files changed, 23 insertions, 33 deletions

diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index bfd10cb9c8d..e29e15dca86 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -43,6 +43,23 @@
 #define XENVIF_QUEUE_LENGTH 32
 #define XENVIF_NAPI_WEIGHT  64
 
+/* This function is used to set SKBTX_DEV_ZEROCOPY as well as
+ * increasing the inflight counter. We need to increase the inflight
+ * counter because core driver calls into xenvif_zerocopy_callback
+ * which calls xenvif_skb_zerocopy_complete.
+ */
+void xenvif_skb_zerocopy_prepare(struct xenvif_queue *queue,
+				 struct sk_buff *skb)
+{
+	skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY;
+	atomic_inc(&queue->inflight_packets);
+}
+
+void xenvif_skb_zerocopy_complete(struct xenvif_queue *queue)
+{
+	atomic_dec(&queue->inflight_packets);
+}
+
 static inline void xenvif_stop_queue(struct xenvif_queue *queue)
 {
 	struct net_device *dev = queue->vif->dev;
@@ -524,9 +541,6 @@ int xenvif_init_queue(struct xenvif_queue *queue)
 
 	init_timer(&queue->rx_stalled);
 
-	netif_napi_add(queue->vif->dev, &queue->napi, xenvif_poll,
-			XENVIF_NAPI_WEIGHT);
-
 	return 0;
 }
 
@@ -560,6 +574,7 @@ int xenvif_connect(struct xenvif_queue *queue, unsigned long tx_ring_ref,
 
 	init_waitqueue_head(&queue->wq);
 	init_waitqueue_head(&queue->dealloc_wq);
+	atomic_set(&queue->inflight_packets, 0);
 
 	if (tx_evtchn == rx_evtchn) {
 		/* feature-split-event-channels == 0 */
@@ -614,6 +629,9 @@ int xenvif_connect(struct xenvif_queue *queue, unsigned long tx_ring_ref,
 	wake_up_process(queue->task);
 	wake_up_process(queue->dealloc_task);
 
+	netif_napi_add(queue->vif->dev, &queue->napi, xenvif_poll,
+			XENVIF_NAPI_WEIGHT);
+
 	return 0;
 
 err_rx_unbind:
@@ -642,25 +660,6 @@ void xenvif_carrier_off(struct xenvif *vif)
 	rtnl_unlock();
 }
 
-static void xenvif_wait_unmap_timeout(struct xenvif_queue *queue,
-				      unsigned int worst_case_skb_lifetime)
-{
-	int i, unmap_timeout = 0;
-
-	for (i = 0; i < MAX_PENDING_REQS; ++i) {
-		if (queue->grant_tx_handle[i] != NETBACK_INVALID_HANDLE) {
-			unmap_timeout++;
-			schedule_timeout(msecs_to_jiffies(1000));
-			if (unmap_timeout > worst_case_skb_lifetime &&
-			    net_ratelimit())
-				netdev_err(queue->vif->dev,
-					   "Page still granted! Index: %x\n",
-					   i);
-			i = -1;
-		}
-	}
-}
-
 void xenvif_disconnect(struct xenvif *vif)
 {
 	struct xenvif_queue *queue = NULL;
@@ -672,6 +671,8 @@ void xenvif_disconnect(struct xenvif *vif)
 	for (queue_index = 0; queue_index < num_queues; ++queue_index) {
 		queue = &vif->queues[queue_index];
 
+		netif_napi_del(&queue->napi);
+
 		if (queue->task) {
 			del_timer_sync(&queue->rx_stalled);
 			kthread_stop(queue->task);
@@ -704,7 +705,6 @@ void xenvif_disconnect(struct xenvif *vif)
 void xenvif_deinit_queue(struct xenvif_queue *queue)
 {
 	free_xenballooned_pages(MAX_PENDING_REQS, queue->mmap_pages);
-	netif_napi_del(&queue->napi);
 }
 
 void xenvif_free(struct xenvif *vif)
@@ -712,21 +712,11 @@ void xenvif_free(struct xenvif *vif)
 	struct xenvif_queue *queue = NULL;
 	unsigned int num_queues = vif->num_queues;
 	unsigned int queue_index;
-	/* Here we want to avoid timeout messages if an skb can be legitimately
-	 * stuck somewhere else. Realistically this could be an another vif's
-	 * internal or QDisc queue. That another vif also has this
-	 * rx_drain_timeout_msecs timeout, so give it time to drain out.
-	 * Although if that other guest wakes up just before its timeout happens
-	 * and takes only one skb from QDisc, it can hold onto other skbs for a
-	 * longer period.
-	 */
-	unsigned int worst_case_skb_lifetime = (rx_drain_timeout_msecs/1000);
 
 	unregister_netdev(vif->dev);
 
 	for (queue_index = 0; queue_index < num_queues; ++queue_index) {
 		queue = &vif->queues[queue_index];
-		xenvif_wait_unmap_timeout(queue, worst_case_skb_lifetime);
 		xenvif_deinit_queue(queue);
 	}