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

Pull networking updates from David Miller:

 1) Add BQL support to via-rhine, from Tino Reichardt.

 2) Integrate SWITCHDEV layer support into the DSA layer, so DSA drivers
    can support hw switch offloading.  From Floria Fainelli.

 3) Allow 'ip address' commands to initiate multicast group join/leave,
    from Madhu Challa.

 4) Many ipv4 FIB lookup optimizations from Alexander Duyck.

 5) Support EBPF in cls_bpf classifier and act_bpf action, from Daniel
    Borkmann.

 6) Remove the ugly compat support in ARP for ugly layers like ax25,
    rose, etc.  And use this to clean up the neigh layer, then use it to
    implement MPLS support.  All from Eric Biederman.

 7) Support L3 forwarding offloading in switches, from Scott Feldman.

 8) Collapse the LOCAL and MAIN ipv4 FIB tables when possible, to speed
    up route lookups even further.  From Alexander Duyck.

 9) Many improvements and bug fixes to the rhashtable implementation,
    from Herbert Xu and Thomas Graf.  In particular, in the case where
    an rhashtable user bulk adds a large number of items into an empty
    table, we expand the table much more sanely.

10) Don't make the tcp_metrics hash table per-namespace, from Eric
    Biederman.

11) Extend EBPF to access SKB fields, from Alexei Starovoitov.

12) Split out new connection request sockets so that they can be
    established in the main hash table.  Much less false sharing since
    hash lookups go direct to the request sockets instead of having to
    go first to the listener then to the request socks hashed
    underneath.  From Eric Dumazet.

13) Add async I/O support for crytpo AF_ALG sockets, from Tadeusz Struk.

14) Support stable privacy address generation for RFC7217 in IPV6.  From
    Hannes Frederic Sowa.

15) Hash network namespace into IP frag IDs, also from Hannes Frederic
    Sowa.

16) Convert PTP get/set methods to use 64-bit time, from Richard
    Cochran.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1816 commits)
  fm10k: Bump driver version to 0.15.2
  fm10k: corrected VF multicast update
  fm10k: mbx_update_max_size does not drop all oversized messages
  fm10k: reset head instead of calling update_max_size
  fm10k: renamed mbx_tx_dropped to mbx_tx_oversized
  fm10k: update xcast mode before synchronizing multicast addresses
  fm10k: start service timer on probe
  fm10k: fix function header comment
  fm10k: comment next_vf_mbx flow
  fm10k: don't handle mailbox events in iov_event path and always process mailbox
  fm10k: use separate workqueue for fm10k driver
  fm10k: Set PF queues to unlimited bandwidth during virtualization
  fm10k: expose tx_timeout_count as an ethtool stat
  fm10k: only increment tx_timeout_count in Tx hang path
  fm10k: remove extraneous "Reset interface" message
  fm10k: separate PF only stats so that VF does not display them
  fm10k: use hw->mac.max_queues for stats
  fm10k: only show actual queues, not the maximum in hardware
  fm10k: allow creation of VLAN on default vid
  fm10k: fix unused warnings
  ...

1 files changed, 21 insertions, 10 deletions

diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c
index 17e276651601..de2850497c09 100644
--- a/drivers/net/ethernet/via/via-rhine.c
+++ b/drivers/net/ethernet/via/via-rhine.c
@@ -70,12 +70,14 @@ static const int multicast_filter_limit = 32;
 /* Operational parameters that are set at compile time. */
 
 /* Keep the ring sizes a power of two for compile efficiency.
-   The compiler will convert <unsigned>'%'<2^N> into a bit mask.
-   Making the Tx ring too large decreases the effectiveness of channel
-   bonding and packet priority.
-   There are no ill effects from too-large receive rings. */
-#define TX_RING_SIZE	16
-#define TX_QUEUE_LEN	10	/* Limit ring entries actually used. */
+ * The compiler will convert <unsigned>'%'<2^N> into a bit mask.
+ * Making the Tx ring too large decreases the effectiveness of channel
+ * bonding and packet priority.
+ * With BQL support, we can increase TX ring safely.
+ * There are no ill effects from too-large receive rings.
+ */
+#define TX_RING_SIZE	64
+#define TX_QUEUE_LEN	(TX_RING_SIZE - 6)	/* Limit ring entries actually used. */
 #define RX_RING_SIZE	64
 
 /* Operational parameters that usually are not changed. */
@@ -286,7 +288,7 @@ MODULE_DEVICE_TABLE(pci, rhine_pci_tbl);
  * The .data field is currently only used to store quirks
  */
 static u32 vt8500_quirks = rqWOL | rqForceReset | rq6patterns;
-static struct of_device_id rhine_of_tbl[] = {
+static const struct of_device_id rhine_of_tbl[] = {
 	{ .compatible = "via,vt8500-rhine", .data = &vt8500_quirks },
 	{ }	/* terminate list */
 };
@@ -1295,6 +1297,7 @@ static void alloc_tbufs(struct net_device* dev)
 	}
 	rp->tx_ring[i-1].next_desc = cpu_to_le32(rp->tx_ring_dma);
 
+	netdev_reset_queue(dev);
 }
 
 static void free_tbufs(struct net_device* dev)
@@ -1795,6 +1798,7 @@ static netdev_tx_t rhine_start_tx(struct sk_buff *skb,
 	else
 		rp->tx_ring[entry].tx_status = 0;
 
+	netdev_sent_queue(dev, skb->len);
 	/* lock eth irq */
 	wmb();
 	rp->tx_ring[entry].tx_status |= cpu_to_le32(DescOwn);
@@ -1863,6 +1867,8 @@ static void rhine_tx(struct net_device *dev)
 	struct rhine_private *rp = netdev_priv(dev);
 	struct device *hwdev = dev->dev.parent;
 	int txstatus = 0, entry = rp->dirty_tx % TX_RING_SIZE;
+	unsigned int pkts_compl = 0, bytes_compl = 0;
+	struct sk_buff *skb;
 
 	/* find and cleanup dirty tx descriptors */
 	while (rp->dirty_tx != rp->cur_tx) {
@@ -1871,6 +1877,7 @@ static void rhine_tx(struct net_device *dev)
 			  entry, txstatus);
 		if (txstatus & DescOwn)
 			break;
+		skb = rp->tx_skbuff[entry];
 		if (txstatus & 0x8000) {
 			netif_dbg(rp, tx_done, dev,
 				  "Transmit error, Tx status %08x\n", txstatus);
@@ -1899,7 +1906,7 @@ static void rhine_tx(struct net_device *dev)
 				  (txstatus >> 3) & 0xF, txstatus & 0xF);
 
 			u64_stats_update_begin(&rp->tx_stats.syncp);
-			rp->tx_stats.bytes += rp->tx_skbuff[entry]->len;
+			rp->tx_stats.bytes += skb->len;
 			rp->tx_stats.packets++;
 			u64_stats_update_end(&rp->tx_stats.syncp);
 		}
@@ -1907,13 +1914,17 @@ static void rhine_tx(struct net_device *dev)
 		if (rp->tx_skbuff_dma[entry]) {
 			dma_unmap_single(hwdev,
 					 rp->tx_skbuff_dma[entry],
-					 rp->tx_skbuff[entry]->len,
+					 skb->len,
 					 DMA_TO_DEVICE);
 		}
-		dev_consume_skb_any(rp->tx_skbuff[entry]);
+		bytes_compl += skb->len;
+		pkts_compl++;
+		dev_consume_skb_any(skb);
 		rp->tx_skbuff[entry] = NULL;
 		entry = (++rp->dirty_tx) % TX_RING_SIZE;
 	}
+
+	netdev_completed_queue(dev, pkts_compl, bytes_compl);
 	if ((rp->cur_tx - rp->dirty_tx) < TX_QUEUE_LEN - 4)
 		netif_wake_queue(dev);
 }