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

Pull networking fixes from David Miller:
 "A bit has accumulated, but it's been a week or so since my last batch
  of post-merge-window fixes, so...

   1) Missing module license in netfilter reject module, from Pablo.
      Lots of people ran into this.

   2) Off by one in mac80211 baserate calculation, from Karl Beldan.

   3) Fix incorrect return value from ax88179_178a driver's set_mac_addr
      op, which broke use of it with bonding.  From Ian Morgan.

   4) Checking of skb_gso_segment()'s return value was not all
      encompassing, it can return an SKB pointer, a pointer error, or
      NULL.  Fix from Florian Westphal.

      This is crummy, and longer term will be fixed to just return error
      pointers or a real SKB.

   6) Encapsulation offloads not being handled by
      skb_gso_transport_seglen().  From Florian Westphal.

   7) Fix deadlock in TIPC stack, from Ying Xue.

   8) Fix performance regression from using rhashtable for netlink
      sockets.  The problem was the synchronize_net() invoked for every
      socket destroy.  From Thomas Graf.

   9) Fix bug in eBPF verifier, and remove the strong dependency of BPF
      on NET.  From Alexei Starovoitov.

  10) In qdisc_create(), use the correct interface to allocate
      ->cpu_bstats, otherwise the u64_stats_sync member isn't
      initialized properly.  From Sabrina Dubroca.

  11) Off by one in ip_set_nfnl_get_byindex(), from Dan Carpenter.

  12) nf_tables_newchain() was erroneously expecting error pointers from
      netdev_alloc_pcpu_stats().  It only returna a valid pointer or
      NULL.  From Sabrina Dubroca.

  13) Fix use-after-free in _decode_session6(), from Li RongQing.

  14) When we set the TX flow hash on a socket, we mistakenly do so
      before we've nailed down the final source port.  Move the setting
      deeper to fix this.  From Sathya Perla.

  15) NAPI budget accounting in amd-xgbe driver was counting descriptors
      instead of full packets, fix from Thomas Lendacky.

  16) Fix total_data_buflen calculation in hyperv driver, from Haiyang
      Zhang.

  17) Fix bcma driver build with OF_ADDRESS disabled, from Hauke
      Mehrtens.

  18) Fix mis-use of per-cpu memory in TCP md5 code.  The problem is
      that something that ends up being vmalloc memory can't be passed
      to the crypto hash routines via scatter-gather lists.  From Eric
      Dumazet.

  19) Fix regression in promiscuous mode enabling in cdc-ether, from
      Olivier Blin.

  20) Bucket eviction and frag entry killing can race with eachother,
      causing an unlink of the object from the wrong list.  Fix from
      Nikolay Aleksandrov.

  21) Missing initialization of spinlock in cxgb4 driver, from Anish
      Bhatt.

  22) Do not cache ipv4 routing failures, otherwise if the sysctl for
      forwarding is subsequently enabled this won't be seen.  From
      Nicolas Cavallari"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (131 commits)
  drivers: net: cpsw: Support ALLMULTI and fix IFF_PROMISC in switch mode
  drivers: net: cpsw: Fix broken loop condition in switch mode
  net: ethtool: Return -EOPNOTSUPP if user space tries to read EEPROM with lengh 0
  stmmac: pci: set default of the filter bins
  net: smc91x: Fix gpios for device tree based booting
  mpls: Allow mpls_gso to be built as module
  mpls: Fix mpls_gso handler.
  r8152: stop submitting intr for -EPROTO
  netfilter: nft_reject_bridge: restrict reject to prerouting and input
  netfilter: nft_reject_bridge: don't use IP stack to reject traffic
  netfilter: nf_reject_ipv6: split nf_send_reset6() in smaller functions
  netfilter: nf_reject_ipv4: split nf_send_reset() in smaller functions
  netfilter: nf_tables_bridge: update hook_mask to allow {pre,post}routing
  drivers/net: macvtap and tun depend on INET
  drivers/net, ipv6: Select IPv6 fragment idents for virtio UFO packets
  drivers/net: Disable UFO through virtio
  net: skb_fclone_busy() needs to detect orphaned skb
  gre: Use inner mac length when computing tunnel length
  mlx4: Avoid leaking steering rules on flow creation error flow
  net/mlx4_en: Don't attempt to TX offload the outer UDP checksum for VXLAN
  ...

1 files changed, 15 insertions, 59 deletions

diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index f379689dde30..895fe84011e7 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -43,6 +43,9 @@
 #define XENVIF_QUEUE_LENGTH 32
 #define XENVIF_NAPI_WEIGHT  64
 
+/* Number of bytes allowed on the internal guest Rx queue. */
+#define XENVIF_RX_QUEUE_BYTES (XEN_NETIF_RX_RING_SIZE/2 * PAGE_SIZE)
+
 /* 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
@@ -60,20 +63,11 @@ 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;
-
-	if (!queue->vif->can_queue)
-		return;
-
-	netif_tx_stop_queue(netdev_get_tx_queue(dev, queue->id));
-}
-
 int xenvif_schedulable(struct xenvif *vif)
 {
 	return netif_running(vif->dev) &&
-		test_bit(VIF_STATUS_CONNECTED, &vif->status);
+		test_bit(VIF_STATUS_CONNECTED, &vif->status) &&
+		!vif->disabled;
 }
 
 static irqreturn_t xenvif_tx_interrupt(int irq, void *dev_id)
@@ -114,16 +108,7 @@ int xenvif_poll(struct napi_struct *napi, int budget)
 static irqreturn_t xenvif_rx_interrupt(int irq, void *dev_id)
 {
 	struct xenvif_queue *queue = dev_id;
-	struct netdev_queue *net_queue =
-		netdev_get_tx_queue(queue->vif->dev, queue->id);
 
-	/* QUEUE_STATUS_RX_PURGE_EVENT is only set if either QDisc was off OR
-	 * the carrier went down and this queue was previously blocked
-	 */
-	if (unlikely(netif_tx_queue_stopped(net_queue) ||
-		     (!netif_carrier_ok(queue->vif->dev) &&
-		      test_bit(QUEUE_STATUS_RX_STALLED, &queue->status))))
-		set_bit(QUEUE_STATUS_RX_PURGE_EVENT, &queue->status);
 	xenvif_kick_thread(queue);
 
 	return IRQ_HANDLED;
@@ -151,24 +136,13 @@ void xenvif_wake_queue(struct xenvif_queue *queue)
 	netif_tx_wake_queue(netdev_get_tx_queue(dev, id));
 }
 
-/* Callback to wake the queue's thread and turn the carrier off on timeout */
-static void xenvif_rx_stalled(unsigned long data)
-{
-	struct xenvif_queue *queue = (struct xenvif_queue *)data;
-
-	if (xenvif_queue_stopped(queue)) {
-		set_bit(QUEUE_STATUS_RX_PURGE_EVENT, &queue->status);
-		xenvif_kick_thread(queue);
-	}
-}
-
 static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct xenvif *vif = netdev_priv(dev);
 	struct xenvif_queue *queue = NULL;
 	unsigned int num_queues = vif->num_queues;
 	u16 index;
-	int min_slots_needed;
+	struct xenvif_rx_cb *cb;
 
 	BUG_ON(skb->dev != dev);
 
@@ -191,30 +165,10 @@ static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	    !xenvif_schedulable(vif))
 		goto drop;
 
-	/* At best we'll need one slot for the header and one for each
-	 * frag.
-	 */
-	min_slots_needed = 1 + skb_shinfo(skb)->nr_frags;
-
-	/* If the skb is GSO then we'll also need an extra slot for the
-	 * metadata.
-	 */
-	if (skb_is_gso(skb))
-		min_slots_needed++;
+	cb = XENVIF_RX_CB(skb);
+	cb->expires = jiffies + rx_drain_timeout_jiffies;
 
-	/* If the skb can't possibly fit in the remaining slots
-	 * then turn off the queue to give the ring a chance to
-	 * drain.
-	 */
-	if (!xenvif_rx_ring_slots_available(queue, min_slots_needed)) {
-		queue->rx_stalled.function = xenvif_rx_stalled;
-		queue->rx_stalled.data = (unsigned long)queue;
-		xenvif_stop_queue(queue);
-		mod_timer(&queue->rx_stalled,
-			  jiffies + rx_drain_timeout_jiffies);
-	}
-
-	skb_queue_tail(&queue->rx_queue, skb);
+	xenvif_rx_queue_tail(queue, skb);
 	xenvif_kick_thread(queue);
 
 	return NETDEV_TX_OK;
@@ -465,6 +419,8 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
 	vif->queues = NULL;
 	vif->num_queues = 0;
 
+	spin_lock_init(&vif->lock);
+
 	dev->netdev_ops	= &xenvif_netdev_ops;
 	dev->hw_features = NETIF_F_SG |
 		NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
@@ -508,6 +464,8 @@ int xenvif_init_queue(struct xenvif_queue *queue)
 	init_timer(&queue->credit_timeout);
 	queue->credit_window_start = get_jiffies_64();
 
+	queue->rx_queue_max = XENVIF_RX_QUEUE_BYTES;
+
 	skb_queue_head_init(&queue->rx_queue);
 	skb_queue_head_init(&queue->tx_queue);
 
@@ -539,8 +497,6 @@ int xenvif_init_queue(struct xenvif_queue *queue)
 		queue->grant_tx_handle[i] = NETBACK_INVALID_HANDLE;
 	}
 
-	init_timer(&queue->rx_stalled);
-
 	return 0;
 }
 
@@ -551,7 +507,6 @@ void xenvif_carrier_on(struct xenvif *vif)
 		dev_set_mtu(vif->dev, ETH_DATA_LEN);
 	netdev_update_features(vif->dev);
 	set_bit(VIF_STATUS_CONNECTED, &vif->status);
-	netif_carrier_on(vif->dev);
 	if (netif_running(vif->dev))
 		xenvif_up(vif);
 	rtnl_unlock();
@@ -611,6 +566,8 @@ int xenvif_connect(struct xenvif_queue *queue, unsigned long tx_ring_ref,
 		disable_irq(queue->rx_irq);
 	}
 
+	queue->stalled = true;
+
 	task = kthread_create(xenvif_kthread_guest_rx,
 			      (void *)queue, "%s-guest-rx", queue->name);
 	if (IS_ERR(task)) {
@@ -674,7 +631,6 @@ void xenvif_disconnect(struct xenvif *vif)
 		netif_napi_del(&queue->napi);
 
 		if (queue->task) {
-			del_timer_sync(&queue->rx_stalled);
 			kthread_stop(queue->task);
 			queue->task = NULL;
 		}