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

Pull networking changes from David Miller:

1) Allow to dump, monitor, and change the bridge multicast database
   using netlink.  From Cong Wang.

2) RFC 5961 TCP blind data injection attack mitigation, from Eric
   Dumazet.

3) Networking user namespace support from Eric W. Biederman.

4) tuntap/virtio-net multiqueue support by Jason Wang.

5) Support for checksum offload of encapsulated packets (basically,
   tunneled traffic can still be checksummed by HW).  From Joseph
   Gasparakis.

6) Allow BPF filter access to VLAN tags, from Eric Dumazet and
   Daniel Borkmann.

7) Bridge port parameters over netlink and BPDU blocking support
   from Stephen Hemminger.

8) Improve data access patterns during inet socket demux by rearranging
   socket layout, from Eric Dumazet.

9) TIPC protocol updates and cleanups from Ying Xue, Paul Gortmaker, and
   Jon Maloy.

10) Update TCP socket hash sizing to be more in line with current day
    realities.  The existing heurstics were choosen a decade ago.
    From Eric Dumazet.

11) Fix races, queue bloat, and excessive wakeups in ATM and
    associated drivers, from Krzysztof Mazur and David Woodhouse.

12) Support DOVE (Distributed Overlay Virtual Ethernet) extensions
    in VXLAN driver, from David Stevens.

13) Add "oops_only" mode to netconsole, from Amerigo Wang.

14) Support set and query of VEB/VEPA bridge mode via PF_BRIDGE, also
    allow DCB netlink to work on namespaces other than the initial
    namespace.  From John Fastabend.

15) Support PTP in the Tigon3 driver, from Matt Carlson.

16) tun/vhost zero copy fixes and improvements, plus turn it on
    by default, from Michael S. Tsirkin.

17) Support per-association statistics in SCTP, from Michele
    Baldessari.

And many, many, driver updates, cleanups, and improvements.  Too
numerous to mention individually.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1722 commits)
  net/mlx4_en: Add support for destination MAC in steering rules
  net/mlx4_en: Use generic etherdevice.h functions.
  net: ethtool: Add destination MAC address to flow steering API
  bridge: add support of adding and deleting mdb entries
  bridge: notify mdb changes via netlink
  ndisc: Unexport ndisc_{build,send}_skb().
  uapi: add missing netconf.h to export list
  pkt_sched: avoid requeues if possible
  solos-pci: fix double-free of TX skb in DMA mode
  bnx2: Fix accidental reversions.
  bna: Driver Version Updated to 3.1.2.1
  bna: Firmware update
  bna: Add RX State
  bna: Rx Page Based Allocation
  bna: TX Intr Coalescing Fix
  bna: Tx and Rx Optimizations
  bna: Code Cleanup and Enhancements
  ath9k: check pdata variable before dereferencing it
  ath5k: RX timestamp is reported at end of frame
  ath9k_htc: RX timestamp is reported at end of frame
  ...

1 files changed, 328 insertions, 78 deletions

diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index 2ea012849825..bfe9208c4b18 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -37,6 +37,7 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/pm_runtime.h>
+#include <linux/highmem.h>
 
 #include "igb.h"
 
@@ -1623,6 +1624,20 @@ static int igb_setup_loopback_test(struct igb_adapter *adapter)
 		reg &= ~E1000_CONNSW_ENRGSRC;
 		wr32(E1000_CONNSW, reg);
 
+		/* Unset sigdetect for SERDES loopback on
+		 * 82580 and i350 devices.
+		 */
+		switch (hw->mac.type) {
+		case e1000_82580:
+		case e1000_i350:
+			reg = rd32(E1000_PCS_CFG0);
+			reg |= E1000_PCS_CFG_IGN_SD;
+			wr32(E1000_PCS_CFG0, reg);
+			break;
+		default:
+			break;
+		}
+
 		/* Set PCS register for forced speed */
 		reg = rd32(E1000_PCS_LCTL);
 		reg &= ~E1000_PCS_LCTL_AN_ENABLE;     /* Disable Autoneg*/
@@ -1685,16 +1700,24 @@ static void igb_create_lbtest_frame(struct sk_buff *skb,
 	memset(&skb->data[frame_size + 12], 0xAF, 1);
 }
 
-static int igb_check_lbtest_frame(struct sk_buff *skb, unsigned int frame_size)
+static int igb_check_lbtest_frame(struct igb_rx_buffer *rx_buffer,
+				  unsigned int frame_size)
 {
-	frame_size /= 2;
-	if (*(skb->data + 3) == 0xFF) {
-		if ((*(skb->data + frame_size + 10) == 0xBE) &&
-		   (*(skb->data + frame_size + 12) == 0xAF)) {
-			return 0;
-		}
-	}
-	return 13;
+	unsigned char *data;
+	bool match = true;
+
+	frame_size >>= 1;
+
+	data = kmap(rx_buffer->page);
+
+	if (data[3] != 0xFF ||
+	    data[frame_size + 10] != 0xBE ||
+	    data[frame_size + 12] != 0xAF)
+		match = false;
+
+	kunmap(rx_buffer->page);
+
+	return match;
 }
 
 static int igb_clean_test_rings(struct igb_ring *rx_ring,
@@ -1704,9 +1727,7 @@ static int igb_clean_test_rings(struct igb_ring *rx_ring,
 	union e1000_adv_rx_desc *rx_desc;
 	struct igb_rx_buffer *rx_buffer_info;
 	struct igb_tx_buffer *tx_buffer_info;
-	struct netdev_queue *txq;
 	u16 rx_ntc, tx_ntc, count = 0;
-	unsigned int total_bytes = 0, total_packets = 0;
 
 	/* initialize next to clean and descriptor values */
 	rx_ntc = rx_ring->next_to_clean;
@@ -1717,21 +1738,24 @@ static int igb_clean_test_rings(struct igb_ring *rx_ring,
 		/* check rx buffer */
 		rx_buffer_info = &rx_ring->rx_buffer_info[rx_ntc];
 
-		/* unmap rx buffer, will be remapped by alloc_rx_buffers */
-		dma_unmap_single(rx_ring->dev,
-				 rx_buffer_info->dma,
-				 IGB_RX_HDR_LEN,
-				 DMA_FROM_DEVICE);
-		rx_buffer_info->dma = 0;
+		/* sync Rx buffer for CPU read */
+		dma_sync_single_for_cpu(rx_ring->dev,
+					rx_buffer_info->dma,
+					IGB_RX_BUFSZ,
+					DMA_FROM_DEVICE);
 
 		/* verify contents of skb */
-		if (!igb_check_lbtest_frame(rx_buffer_info->skb, size))
+		if (igb_check_lbtest_frame(rx_buffer_info, size))
 			count++;
 
+		/* sync Rx buffer for device write */
+		dma_sync_single_for_device(rx_ring->dev,
+					   rx_buffer_info->dma,
+					   IGB_RX_BUFSZ,
+					   DMA_FROM_DEVICE);
+
 		/* unmap buffer on tx side */
 		tx_buffer_info = &tx_ring->tx_buffer_info[tx_ntc];
-		total_bytes += tx_buffer_info->bytecount;
-		total_packets += tx_buffer_info->gso_segs;
 		igb_unmap_and_free_tx_resource(tx_ring, tx_buffer_info);
 
 		/* increment rx/tx next to clean counters */
@@ -1746,8 +1770,7 @@ static int igb_clean_test_rings(struct igb_ring *rx_ring,
 		rx_desc = IGB_RX_DESC(rx_ring, rx_ntc);
 	}
 
-	txq = netdev_get_tx_queue(tx_ring->netdev, tx_ring->queue_index);
-	netdev_tx_completed_queue(txq, total_packets, total_bytes);
+	netdev_tx_reset_queue(txring_txq(tx_ring));
 
 	/* re-map buffers to ring, store next to clean values */
 	igb_alloc_rx_buffers(rx_ring, count);
@@ -1957,54 +1980,6 @@ static void igb_diag_test(struct net_device *netdev,
 	msleep_interruptible(4 * 1000);
 }
 
-static int igb_wol_exclusion(struct igb_adapter *adapter,
-			     struct ethtool_wolinfo *wol)
-{
-	struct e1000_hw *hw = &adapter->hw;
-	int retval = 1; /* fail by default */
-
-	switch (hw->device_id) {
-	case E1000_DEV_ID_82575GB_QUAD_COPPER:
-		/* WoL not supported */
-		wol->supported = 0;
-		break;
-	case E1000_DEV_ID_82575EB_FIBER_SERDES:
-	case E1000_DEV_ID_82576_FIBER:
-	case E1000_DEV_ID_82576_SERDES:
-		/* Wake events not supported on port B */
-		if (rd32(E1000_STATUS) & E1000_STATUS_FUNC_1) {
-			wol->supported = 0;
-			break;
-		}
-		/* return success for non excluded adapter ports */
-		retval = 0;
-		break;
-	case E1000_DEV_ID_82576_QUAD_COPPER:
-	case E1000_DEV_ID_82576_QUAD_COPPER_ET2:
-		/* quad port adapters only support WoL on port A */
-		if (!(adapter->flags & IGB_FLAG_QUAD_PORT_A)) {
-			wol->supported = 0;
-			break;
-		}
-		/* return success for non excluded adapter ports */
-		retval = 0;
-		break;
-	default:
-		/* dual port cards only support WoL on port A from now on
-		 * unless it was enabled in the eeprom for port B
-		 * so exclude FUNC_1 ports from having WoL enabled */
-		if ((rd32(E1000_STATUS) & E1000_STATUS_FUNC_MASK) &&
-		    !adapter->eeprom_wol) {
-			wol->supported = 0;
-			break;
-		}
-
-		retval = 0;
-	}
-
-	return retval;
-}
-
 static void igb_get_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
@@ -2014,10 +1989,7 @@ static void igb_get_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 	                 WAKE_PHY;
 	wol->wolopts = 0;
 
-	/* this function will set ->supported = 0 and return 1 if wol is not
-	 * supported by this hardware */
-	if (igb_wol_exclusion(adapter, wol) ||
-	    !device_can_wakeup(&adapter->pdev->dev))
+	if (!(adapter->flags & IGB_FLAG_WOL_SUPPORTED))
 		return;
 
 	/* apply any specific unsupported masks here */
@@ -2045,8 +2017,7 @@ static int igb_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 	if (wol->wolopts & (WAKE_ARP | WAKE_MAGICSECURE))
 		return -EOPNOTSUPP;
 
-	if (igb_wol_exclusion(adapter, wol) ||
-	    !device_can_wakeup(&adapter->pdev->dev))
+	if (!(adapter->flags & IGB_FLAG_WOL_SUPPORTED))
 		return wol->wolopts ? -EOPNOTSUPP : 0;
 
 	/* these settings will always override what we currently have */
@@ -2301,7 +2272,6 @@ static int igb_get_ts_info(struct net_device *dev,
 	struct igb_adapter *adapter = netdev_priv(dev);
 
 	switch (adapter->hw.mac.type) {
-#ifdef CONFIG_IGB_PTP
 	case e1000_82576:
 	case e1000_82580:
 	case e1000_i350:
@@ -2337,12 +2307,288 @@ static int igb_get_ts_info(struct net_device *dev,
 				(1 << HWTSTAMP_FILTER_PTP_V2_EVENT);
 
 		return 0;
-#endif /* CONFIG_IGB_PTP */
 	default:
 		return -EOPNOTSUPP;
 	}
 }
 
+static int igb_get_rss_hash_opts(struct igb_adapter *adapter,
+				 struct ethtool_rxnfc *cmd)
+{
+	cmd->data = 0;
+
+	/* Report default options for RSS on igb */
+	switch (cmd->flow_type) {
+	case TCP_V4_FLOW:
+		cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+	case UDP_V4_FLOW:
+		if (adapter->flags & IGB_FLAG_RSS_FIELD_IPV4_UDP)
+			cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+	case SCTP_V4_FLOW:
+	case AH_ESP_V4_FLOW:
+	case AH_V4_FLOW:
+	case ESP_V4_FLOW:
+	case IPV4_FLOW:
+		cmd->data |= RXH_IP_SRC | RXH_IP_DST;
+		break;
+	case TCP_V6_FLOW:
+		cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+	case UDP_V6_FLOW:
+		if (adapter->flags & IGB_FLAG_RSS_FIELD_IPV6_UDP)
+			cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+	case SCTP_V6_FLOW:
+	case AH_ESP_V6_FLOW:
+	case AH_V6_FLOW:
+	case ESP_V6_FLOW:
+	case IPV6_FLOW:
+		cmd->data |= RXH_IP_SRC | RXH_IP_DST;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int igb_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
+			   u32 *rule_locs)
+{
+	struct igb_adapter *adapter = netdev_priv(dev);
+	int ret = -EOPNOTSUPP;
+
+	switch (cmd->cmd) {
+	case ETHTOOL_GRXRINGS:
+		cmd->data = adapter->num_rx_queues;
+		ret = 0;
+		break;
+	case ETHTOOL_GRXFH:
+		ret = igb_get_rss_hash_opts(adapter, cmd);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
+#define UDP_RSS_FLAGS (IGB_FLAG_RSS_FIELD_IPV4_UDP | \
+		       IGB_FLAG_RSS_FIELD_IPV6_UDP)
+static int igb_set_rss_hash_opt(struct igb_adapter *adapter,
+				struct ethtool_rxnfc *nfc)
+{
+	u32 flags = adapter->flags;
+
+	/* RSS does not support anything other than hashing
+	 * to queues on src and dst IPs and ports
+	 */
+	if (nfc->data & ~(RXH_IP_SRC | RXH_IP_DST |
+			  RXH_L4_B_0_1 | RXH_L4_B_2_3))
+		return -EINVAL;
+
+	switch (nfc->flow_type) {
+	case TCP_V4_FLOW:
+	case TCP_V6_FLOW:
+		if (!(nfc->data & RXH_IP_SRC) ||
+		    !(nfc->data & RXH_IP_DST) ||
+		    !(nfc->data & RXH_L4_B_0_1) ||
+		    !(nfc->data & RXH_L4_B_2_3))
+			return -EINVAL;
+		break;
+	case UDP_V4_FLOW:
+		if (!(nfc->data & RXH_IP_SRC) ||
+		    !(nfc->data & RXH_IP_DST))
+			return -EINVAL;
+		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
+		case 0:
+			flags &= ~IGB_FLAG_RSS_FIELD_IPV4_UDP;
+			break;
+		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+			flags |= IGB_FLAG_RSS_FIELD_IPV4_UDP;
+			break;
+		default:
+			return -EINVAL;
+		}
+		break;
+	case UDP_V6_FLOW:
+		if (!(nfc->data & RXH_IP_SRC) ||
+		    !(nfc->data & RXH_IP_DST))
+			return -EINVAL;
+		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
+		case 0:
+			flags &= ~IGB_FLAG_RSS_FIELD_IPV6_UDP;
+			break;
+		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+			flags |= IGB_FLAG_RSS_FIELD_IPV6_UDP;
+			break;
+		default:
+			return -EINVAL;
+		}
+		break;
+	case AH_ESP_V4_FLOW:
+	case AH_V4_FLOW:
+	case ESP_V4_FLOW:
+	case SCTP_V4_FLOW:
+	case AH_ESP_V6_FLOW:
+	case AH_V6_FLOW:
+	case ESP_V6_FLOW:
+	case SCTP_V6_FLOW:
+		if (!(nfc->data & RXH_IP_SRC) ||
+		    !(nfc->data & RXH_IP_DST) ||
+		    (nfc->data & RXH_L4_B_0_1) ||
+		    (nfc->data & RXH_L4_B_2_3))
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* if we changed something we need to update flags */
+	if (flags != adapter->flags) {
+		struct e1000_hw *hw = &adapter->hw;
+		u32 mrqc = rd32(E1000_MRQC);
+
+		if ((flags & UDP_RSS_FLAGS) &&
+		    !(adapter->flags & UDP_RSS_FLAGS))
+			dev_err(&adapter->pdev->dev,
+				"enabling UDP RSS: fragmented packets may arrive out of order to the stack above\n");
+
+		adapter->flags = flags;
+
+		/* Perform hash on these packet types */
+		mrqc |= E1000_MRQC_RSS_FIELD_IPV4 |
+			E1000_MRQC_RSS_FIELD_IPV4_TCP |
+			E1000_MRQC_RSS_FIELD_IPV6 |
+			E1000_MRQC_RSS_FIELD_IPV6_TCP;
+
+		mrqc &= ~(E1000_MRQC_RSS_FIELD_IPV4_UDP |
+			  E1000_MRQC_RSS_FIELD_IPV6_UDP);
+
+		if (flags & IGB_FLAG_RSS_FIELD_IPV4_UDP)
+			mrqc |= E1000_MRQC_RSS_FIELD_IPV4_UDP;
+
+		if (flags & IGB_FLAG_RSS_FIELD_IPV6_UDP)
+			mrqc |= E1000_MRQC_RSS_FIELD_IPV6_UDP;
+
+		wr32(E1000_MRQC, mrqc);
+	}
+
+	return 0;
+}
+
+static int igb_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
+{
+	struct igb_adapter *adapter = netdev_priv(dev);
+	int ret = -EOPNOTSUPP;
+
+	switch (cmd->cmd) {
+	case ETHTOOL_SRXFH:
+		ret = igb_set_rss_hash_opt(adapter, cmd);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
+static int igb_get_eee(struct net_device *netdev, struct ethtool_eee *edata)
+{
+	struct igb_adapter *adapter = netdev_priv(netdev);
+	struct e1000_hw *hw = &adapter->hw;
+	u32 ipcnfg, eeer;
+
+	if ((hw->mac.type < e1000_i350) ||
+	    (hw->phy.media_type != e1000_media_type_copper))
+		return -EOPNOTSUPP;
+
+	edata->supported = (SUPPORTED_1000baseT_Full |
+			    SUPPORTED_100baseT_Full);
+
+	ipcnfg = rd32(E1000_IPCNFG);
+	eeer = rd32(E1000_EEER);
+
+	/* EEE status on negotiated link */
+	if (ipcnfg & E1000_IPCNFG_EEE_1G_AN)
+		edata->advertised = ADVERTISED_1000baseT_Full;
+
+	if (ipcnfg & E1000_IPCNFG_EEE_100M_AN)
+		edata->advertised |= ADVERTISED_100baseT_Full;
+
+	if (eeer & E1000_EEER_EEE_NEG)
+		edata->eee_active = true;
+
+	edata->eee_enabled = !hw->dev_spec._82575.eee_disable;
+
+	if (eeer & E1000_EEER_TX_LPI_EN)
+		edata->tx_lpi_enabled = true;
+
+	/* Report correct negotiated EEE status for devices that
+	 * wrongly report EEE at half-duplex
+	 */
+	if (adapter->link_duplex == HALF_DUPLEX) {
+		edata->eee_enabled = false;
+		edata->eee_active = false;
+		edata->tx_lpi_enabled = false;
+		edata->advertised &= ~edata->advertised;
+	}
+
+	return 0;
+}
+
+static int igb_set_eee(struct net_device *netdev,
+		       struct ethtool_eee *edata)
+{
+	struct igb_adapter *adapter = netdev_priv(netdev);
+	struct e1000_hw *hw = &adapter->hw;
+	struct ethtool_eee eee_curr;
+	s32 ret_val;
+
+	if ((hw->mac.type < e1000_i350) ||
+	    (hw->phy.media_type != e1000_media_type_copper))
+		return -EOPNOTSUPP;
+
+	ret_val = igb_get_eee(netdev, &eee_curr);
+	if (ret_val)
+		return ret_val;
+
+	if (eee_curr.eee_enabled) {
+		if (eee_curr.tx_lpi_enabled != edata->tx_lpi_enabled) {
+			dev_err(&adapter->pdev->dev,
+				"Setting EEE tx-lpi is not supported\n");
+			return -EINVAL;
+		}
+
+		/* Tx LPI timer is not implemented currently */
+		if (edata->tx_lpi_timer) {
+			dev_err(&adapter->pdev->dev,
+				"Setting EEE Tx LPI timer is not supported\n");
+			return -EINVAL;
+		}
+
+		if (eee_curr.advertised != edata->advertised) {
+			dev_err(&adapter->pdev->dev,
+				"Setting EEE Advertisement is not supported\n");
+			return -EINVAL;
+		}
+
+	} else if (!edata->eee_enabled) {
+		dev_err(&adapter->pdev->dev,
+			"Setting EEE options are not supported with EEE disabled\n");
+			return -EINVAL;
+		}
+
+	if (hw->dev_spec._82575.eee_disable != !edata->eee_enabled) {
+		hw->dev_spec._82575.eee_disable = !edata->eee_enabled;
+		igb_set_eee_i350(hw);
+
+		/* reset link */
+		if (!netif_running(netdev))
+			igb_reset(adapter);
+	}
+
+	return 0;
+}
+
 static int igb_ethtool_begin(struct net_device *netdev)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
@@ -2383,6 +2629,10 @@ static const struct ethtool_ops igb_ethtool_ops = {
 	.get_coalesce           = igb_get_coalesce,
 	.set_coalesce           = igb_set_coalesce,
 	.get_ts_info            = igb_get_ts_info,
+	.get_rxnfc		= igb_get_rxnfc,
+	.set_rxnfc		= igb_set_rxnfc,
+	.get_eee		= igb_get_eee,
+	.set_eee		= igb_set_eee,
 	.begin			= igb_ethtool_begin,
 	.complete		= igb_ethtool_complete,
 };