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

Pull networking updates from David Miller:

 1) Add TX fast path in mac80211, from Johannes Berg.

 2) Add TSO/GRO support to ibmveth, from Thomas Falcon

 3) Move away from cached routes in ipv6, just like ipv4, from Martin
    KaFai Lau.

 4) Lots of new rhashtable tests, from Thomas Graf.

 5) Run ingress qdisc lockless, from Alexei Starovoitov.

 6) Allow servers to fetch TCP packet headers for SYN packets of new
    connections, for fingerprinting.  From Eric Dumazet.

 7) Add mode parameter to pktgen, for testing receive.  From Alexei
    Starovoitov.

 8) Cache access optimizations via simplifications of build_skb(), from
    Alexander Duyck.

 9) Move page frag allocator under mm/, also from Alexander.

10) Add xmit_more support to hv_netvsc, from KY Srinivasan.

11) Add a counter guard in case we try to perform endless reclassify
    loops in the packet scheduler.

12) Extern flow dissector to be programmable and use it in new "Flower"
    classifier.  From Jiri Pirko.

13) AF_PACKET fanout rollover fixes, performance improvements, and new
    statistics.  From Willem de Bruijn.

14) Add netdev driver for GENEVE tunnels, from John W Linville.

15) Add ingress netfilter hooks and filtering, from Pablo Neira Ayuso.

16) Fix handling of epoll edge triggers in TCP, from Eric Dumazet.

17) Add an ECN retry fallback for the initial TCP handshake, from Daniel
    Borkmann.

18) Add tail call support to BPF, from Alexei Starovoitov.

19) Add several pktgen helper scripts, from Jesper Dangaard Brouer.

20) Add zerocopy support to AF_UNIX, from Hannes Frederic Sowa.

21) Favor even port numbers for allocation to connect() requests, and
    odd port numbers for bind(0), in an effort to help avoid
    ip_local_port_range exhaustion.  From Eric Dumazet.

22) Add Cavium ThunderX driver, from Sunil Goutham.

23) Allow bpf programs to access skb_iif and dev->ifindex SKB metadata,
    from Alexei Starovoitov.

24) Add support for T6 chips in cxgb4vf driver, from Hariprasad Shenai.

25) Double TCP Small Queues default to 256K to accomodate situations
    like the XEN driver and wireless aggregation.  From Wei Liu.

26) Add more entropy inputs to flow dissector, from Tom Herbert.

27) Add CDG congestion control algorithm to TCP, from Kenneth Klette
    Jonassen.

28) Convert ipset over to RCU locking, from Jozsef Kadlecsik.

29) Track and act upon link status of ipv4 route nexthops, from Andy
    Gospodarek.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1670 commits)
  bridge: vlan: flush the dynamically learned entries on port vlan delete
  bridge: multicast: add a comment to br_port_state_selection about blocking state
  net: inet_diag: export IPV6_V6ONLY sockopt
  stmmac: troubleshoot unexpected bits in des0 & des1
  net: ipv4 sysctl option to ignore routes when nexthop link is down
  net: track link-status of ipv4 nexthops
  net: switchdev: ignore unsupported bridge flags
  net: Cavium: Fix MAC address setting in shutdown state
  drivers: net: xgene: fix for ACPI support without ACPI
  ip: report the original address of ICMP messages
  net/mlx5e: Prefetch skb data on RX
  net/mlx5e: Pop cq outside mlx5e_get_cqe
  net/mlx5e: Remove mlx5e_cq.sqrq back-pointer
  net/mlx5e: Remove extra spaces
  net/mlx5e: Avoid TX CQE generation if more xmit packets expected
  net/mlx5e: Avoid redundant dev_kfree_skb() upon NOP completion
  net/mlx5e: Remove re-assignment of wq type in mlx5e_enable_rq()
  net/mlx5e: Use skb_shinfo(skb)->gso_segs rather than counting them
  net/mlx5e: Static mapping of netdev priv resources to/from netdev TX queues
  net/mlx4_en: Use HW counters for rx/tx bytes/packets in PF device
  ...

1 files changed, 121 insertions, 49 deletions

diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 783543ad1fcf..909ad7a0d480 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -456,6 +456,67 @@ static int bcm_sysport_set_wol(struct net_device *dev,
 	return 0;
 }
 
+static int bcm_sysport_get_coalesce(struct net_device *dev,
+				    struct ethtool_coalesce *ec)
+{
+	struct bcm_sysport_priv *priv = netdev_priv(dev);
+	u32 reg;
+
+	reg = tdma_readl(priv, TDMA_DESC_RING_INTR_CONTROL(0));
+
+	ec->tx_coalesce_usecs = (reg >> RING_TIMEOUT_SHIFT) * 8192 / 1000;
+	ec->tx_max_coalesced_frames = reg & RING_INTR_THRESH_MASK;
+
+	reg = rdma_readl(priv, RDMA_MBDONE_INTR);
+
+	ec->rx_coalesce_usecs = (reg >> RDMA_TIMEOUT_SHIFT) * 8192 / 1000;
+	ec->rx_max_coalesced_frames = reg & RDMA_INTR_THRESH_MASK;
+
+	return 0;
+}
+
+static int bcm_sysport_set_coalesce(struct net_device *dev,
+				    struct ethtool_coalesce *ec)
+{
+	struct bcm_sysport_priv *priv = netdev_priv(dev);
+	unsigned int i;
+	u32 reg;
+
+	/* Base system clock is 125Mhz, DMA timeout is this reference clock
+	 * divided by 1024, which yield roughly 8.192 us, our maximum value has
+	 * to fit in the RING_TIMEOUT_MASK (16 bits).
+	 */
+	if (ec->tx_max_coalesced_frames > RING_INTR_THRESH_MASK ||
+	    ec->tx_coalesce_usecs > (RING_TIMEOUT_MASK * 8) + 1 ||
+	    ec->rx_max_coalesced_frames > RDMA_INTR_THRESH_MASK ||
+	    ec->rx_coalesce_usecs > (RDMA_TIMEOUT_MASK * 8) + 1)
+		return -EINVAL;
+
+	if ((ec->tx_coalesce_usecs == 0 && ec->tx_max_coalesced_frames == 0) ||
+	    (ec->rx_coalesce_usecs == 0 && ec->rx_max_coalesced_frames == 0))
+		return -EINVAL;
+
+	for (i = 0; i < dev->num_tx_queues; i++) {
+		reg = tdma_readl(priv, TDMA_DESC_RING_INTR_CONTROL(i));
+		reg &= ~(RING_INTR_THRESH_MASK |
+			 RING_TIMEOUT_MASK << RING_TIMEOUT_SHIFT);
+		reg |= ec->tx_max_coalesced_frames;
+		reg |= DIV_ROUND_UP(ec->tx_coalesce_usecs * 1000, 8192) <<
+			 RING_TIMEOUT_SHIFT;
+		tdma_writel(priv, reg, TDMA_DESC_RING_INTR_CONTROL(i));
+	}
+
+	reg = rdma_readl(priv, RDMA_MBDONE_INTR);
+	reg &= ~(RDMA_INTR_THRESH_MASK |
+		 RDMA_TIMEOUT_MASK << RDMA_TIMEOUT_SHIFT);
+	reg |= ec->rx_max_coalesced_frames;
+	reg |= DIV_ROUND_UP(ec->rx_coalesce_usecs * 1000, 8192) <<
+			    RDMA_TIMEOUT_SHIFT;
+	rdma_writel(priv, reg, RDMA_MBDONE_INTR);
+
+	return 0;
+}
+
 static void bcm_sysport_free_cb(struct bcm_sysport_cb *cb)
 {
 	dev_kfree_skb_any(cb->skb);
@@ -463,67 +524,70 @@ static void bcm_sysport_free_cb(struct bcm_sysport_cb *cb)
 	dma_unmap_addr_set(cb, dma_addr, 0);
 }
 
-static int bcm_sysport_rx_refill(struct bcm_sysport_priv *priv,
-				 struct bcm_sysport_cb *cb)
+static struct sk_buff *bcm_sysport_rx_refill(struct bcm_sysport_priv *priv,
+					     struct bcm_sysport_cb *cb)
 {
 	struct device *kdev = &priv->pdev->dev;
 	struct net_device *ndev = priv->netdev;
+	struct sk_buff *skb, *rx_skb;
 	dma_addr_t mapping;
-	int ret;
 
-	cb->skb = netdev_alloc_skb(priv->netdev, RX_BUF_LENGTH);
-	if (!cb->skb) {
+	/* Allocate a new SKB for a new packet */
+	skb = netdev_alloc_skb(priv->netdev, RX_BUF_LENGTH);
+	if (!skb) {
+		priv->mib.alloc_rx_buff_failed++;
 		netif_err(priv, rx_err, ndev, "SKB alloc failed\n");
-		return -ENOMEM;
+		return NULL;
 	}
 
-	mapping = dma_map_single(kdev, cb->skb->data,
+	mapping = dma_map_single(kdev, skb->data,
 				 RX_BUF_LENGTH, DMA_FROM_DEVICE);
-	ret = dma_mapping_error(kdev, mapping);
-	if (ret) {
+	if (dma_mapping_error(kdev, mapping)) {
 		priv->mib.rx_dma_failed++;
-		bcm_sysport_free_cb(cb);
+		dev_kfree_skb_any(skb);
 		netif_err(priv, rx_err, ndev, "DMA mapping failure\n");
-		return ret;
+		return NULL;
 	}
 
-	dma_unmap_addr_set(cb, dma_addr, mapping);
-	dma_desc_set_addr(priv, priv->rx_bd_assign_ptr, mapping);
+	/* Grab the current SKB on the ring */
+	rx_skb = cb->skb;
+	if (likely(rx_skb))
+		dma_unmap_single(kdev, dma_unmap_addr(cb, dma_addr),
+				 RX_BUF_LENGTH, DMA_FROM_DEVICE);
 
-	priv->rx_bd_assign_index++;
-	priv->rx_bd_assign_index &= (priv->num_rx_bds - 1);
-	priv->rx_bd_assign_ptr = priv->rx_bds +
-		(priv->rx_bd_assign_index * DESC_SIZE);
+	/* Put the new SKB on the ring */
+	cb->skb = skb;
+	dma_unmap_addr_set(cb, dma_addr, mapping);
+	dma_desc_set_addr(priv, cb->bd_addr, mapping);
 
 	netif_dbg(priv, rx_status, ndev, "RX refill\n");
 
-	return 0;
+	/* Return the current SKB to the caller */
+	return rx_skb;
 }
 
 static int bcm_sysport_alloc_rx_bufs(struct bcm_sysport_priv *priv)
 {
 	struct bcm_sysport_cb *cb;
-	int ret = 0;
+	struct sk_buff *skb;
 	unsigned int i;
 
 	for (i = 0; i < priv->num_rx_bds; i++) {
-		cb = &priv->rx_cbs[priv->rx_bd_assign_index];
-		if (cb->skb)
-			continue;
-
-		ret = bcm_sysport_rx_refill(priv, cb);
-		if (ret)
-			break;
+		cb = &priv->rx_cbs[i];
+		skb = bcm_sysport_rx_refill(priv, cb);
+		if (skb)
+			dev_kfree_skb(skb);
+		if (!cb->skb)
+			return -ENOMEM;
 	}
 
-	return ret;
+	return 0;
 }
 
 /* Poll the hardware for up to budget packets to process */
 static unsigned int bcm_sysport_desc_rx(struct bcm_sysport_priv *priv,
 					unsigned int budget)
 {
-	struct device *kdev = &priv->pdev->dev;
 	struct net_device *ndev = priv->netdev;
 	unsigned int processed = 0, to_process;
 	struct bcm_sysport_cb *cb;
@@ -531,7 +595,6 @@ static unsigned int bcm_sysport_desc_rx(struct bcm_sysport_priv *priv,
 	unsigned int p_index;
 	u16 len, status;
 	struct bcm_rsb *rsb;
-	int ret;
 
 	/* Determine how much we should process since last call */
 	p_index = rdma_readl(priv, RDMA_PROD_INDEX);
@@ -549,13 +612,8 @@ static unsigned int bcm_sysport_desc_rx(struct bcm_sysport_priv *priv,
 
 	while ((processed < to_process) && (processed < budget)) {
 		cb = &priv->rx_cbs[priv->rx_read_ptr];
-		skb = cb->skb;
+		skb = bcm_sysport_rx_refill(priv, cb);
 
-		processed++;
-		priv->rx_read_ptr++;
-
-		if (priv->rx_read_ptr == priv->num_rx_bds)
-			priv->rx_read_ptr = 0;
 
 		/* We do not have a backing SKB, so we do not a corresponding
 		 * DMA mapping for this incoming packet since
@@ -566,12 +624,9 @@ static unsigned int bcm_sysport_desc_rx(struct bcm_sysport_priv *priv,
 			netif_err(priv, rx_err, ndev, "out of memory!\n");
 			ndev->stats.rx_dropped++;
 			ndev->stats.rx_errors++;
-			goto refill;
+			goto next;
 		}
 
-		dma_unmap_single(kdev, dma_unmap_addr(cb, dma_addr),
-				 RX_BUF_LENGTH, DMA_FROM_DEVICE);
-
 		/* Extract the Receive Status Block prepended */
 		rsb = (struct bcm_rsb *)skb->data;
 		len = (rsb->rx_status_len >> DESC_LEN_SHIFT) & DESC_LEN_MASK;
@@ -583,12 +638,20 @@ static unsigned int bcm_sysport_desc_rx(struct bcm_sysport_priv *priv,
 			  p_index, priv->rx_c_index, priv->rx_read_ptr,
 			  len, status);
 
+		if (unlikely(len > RX_BUF_LENGTH)) {
+			netif_err(priv, rx_status, ndev, "oversized packet\n");
+			ndev->stats.rx_length_errors++;
+			ndev->stats.rx_errors++;
+			dev_kfree_skb_any(skb);
+			goto next;
+		}
+
 		if (unlikely(!(status & DESC_EOP) || !(status & DESC_SOP))) {
 			netif_err(priv, rx_status, ndev, "fragmented packet!\n");
 			ndev->stats.rx_dropped++;
 			ndev->stats.rx_errors++;
-			bcm_sysport_free_cb(cb);
-			goto refill;
+			dev_kfree_skb_any(skb);
+			goto next;
 		}
 
 		if (unlikely(status & (RX_STATUS_ERR | RX_STATUS_OVFLOW))) {
@@ -597,8 +660,8 @@ static unsigned int bcm_sysport_desc_rx(struct bcm_sysport_priv *priv,
 				ndev->stats.rx_over_errors++;
 			ndev->stats.rx_dropped++;
 			ndev->stats.rx_errors++;
-			bcm_sysport_free_cb(cb);
-			goto refill;
+			dev_kfree_skb_any(skb);
+			goto next;
 		}
 
 		skb_put(skb, len);
@@ -625,10 +688,12 @@ static unsigned int bcm_sysport_desc_rx(struct bcm_sysport_priv *priv,
 		ndev->stats.rx_bytes += len;
 
 		napi_gro_receive(&priv->napi, skb);
-refill:
-		ret = bcm_sysport_rx_refill(priv, cb);
-		if (ret)
-			priv->mib.alloc_rx_buff_failed++;
+next:
+		processed++;
+		priv->rx_read_ptr++;
+
+		if (priv->rx_read_ptr == priv->num_rx_bds)
+			priv->rx_read_ptr = 0;
 	}
 
 	return processed;
@@ -1269,14 +1334,14 @@ static inline int tdma_enable_set(struct bcm_sysport_priv *priv,
 
 static int bcm_sysport_init_rx_ring(struct bcm_sysport_priv *priv)
 {
+	struct bcm_sysport_cb *cb;
 	u32 reg;
 	int ret;
+	int i;
 
 	/* Initialize SW view of the RX ring */
 	priv->num_rx_bds = NUM_RX_DESC;
 	priv->rx_bds = priv->base + SYS_PORT_RDMA_OFFSET;
-	priv->rx_bd_assign_ptr = priv->rx_bds;
-	priv->rx_bd_assign_index = 0;
 	priv->rx_c_index = 0;
 	priv->rx_read_ptr = 0;
 	priv->rx_cbs = kcalloc(priv->num_rx_bds, sizeof(struct bcm_sysport_cb),
@@ -1286,6 +1351,11 @@ static int bcm_sysport_init_rx_ring(struct bcm_sysport_priv *priv)
 		return -ENOMEM;
 	}
 
+	for (i = 0; i < priv->num_rx_bds; i++) {
+		cb = priv->rx_cbs + i;
+		cb->bd_addr = priv->rx_bds + i * DESC_SIZE;
+	}
+
 	ret = bcm_sysport_alloc_rx_bufs(priv);
 	if (ret) {
 		netif_err(priv, hw, priv->netdev, "SKB allocation failed\n");
@@ -1641,6 +1711,8 @@ static struct ethtool_ops bcm_sysport_ethtool_ops = {
 	.get_sset_count		= bcm_sysport_get_sset_count,
 	.get_wol		= bcm_sysport_get_wol,
 	.set_wol		= bcm_sysport_set_wol,
+	.get_coalesce		= bcm_sysport_get_coalesce,
+	.set_coalesce		= bcm_sysport_set_coalesce,
 };
 
 static const struct net_device_ops bcm_sysport_netdev_ops = {