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

Pull networking updates from David Miller:
 "Another merge window, another set of networking changes.  I've heard
  rumblings that the lightweight tunnels infrastructure has been voted
  networking change of the year.  But what do I know?

   1) Add conntrack support to openvswitch, from Joe Stringer.

   2) Initial support for VRF (Virtual Routing and Forwarding), which
      allows the segmentation of routing paths without using multiple
      devices.  There are some semantic kinks to work out still, but
      this is a reasonably strong foundation.  From David Ahern.

   3) Remove spinlock fro act_bpf fast path, from Alexei Starovoitov.

   4) Ignore route nexthops with a link down state in ipv6, just like
      ipv4.  From Andy Gospodarek.

   5) Remove spinlock from fast path of act_gact and act_mirred, from
      Eric Dumazet.

   6) Document the DSA layer, from Florian Fainelli.

   7) Add netconsole support to bcmgenet, systemport, and DSA.  Also
      from Florian Fainelli.

   8) Add Mellanox Switch Driver and core infrastructure, from Jiri
      Pirko.

   9) Add support for "light weight tunnels", which allow for
      encapsulation and decapsulation without bearing the overhead of a
      full blown netdevice.  From Thomas Graf, Jiri Benc, and a cast of
      others.

  10) Add Identifier Locator Addressing support for ipv6, from Tom
      Herbert.

  11) Support fragmented SKBs in iwlwifi, from Johannes Berg.

  12) Allow perf PMUs to be accessed from eBPF programs, from Kaixu Xia.

  13) Add BQL support to 3c59x driver, from Loganaden Velvindron.

  14) Stop using a zero TX queue length to mean that a device shouldn't
      have a qdisc attached, use an explicit flag instead.  From Phil
      Sutter.

  15) Use generic geneve netdevice infrastructure in openvswitch, from
      Pravin B Shelar.

  16) Add infrastructure to avoid re-forwarding a packet in software
      that was already forwarded by a hardware switch.  From Scott
      Feldman.

  17) Allow AF_PACKET fanout function to be implemented in a bpf
      program, from Willem de Bruijn"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1458 commits)
  netfilter: nf_conntrack: make nf_ct_zone_dflt built-in
  netfilter: nf_dup{4, 6}: fix build error when nf_conntrack disabled
  net: fec: clear receive interrupts before processing a packet
  ipv6: fix exthdrs offload registration in out_rt path
  xen-netback: add support for multicast control
  bgmac: Update fixed_phy_register()
  sock, diag: fix panic in sock_diag_put_filterinfo
  flow_dissector: Use 'const' where possible.
  flow_dissector: Fix function argument ordering dependency
  ixgbe: Resolve "initialized field overwritten" warnings
  ixgbe: Remove bimodal SR-IOV disabling
  ixgbe: Add support for reporting 2.5G link speed
  ixgbe: fix bounds checking in ixgbe_setup_tc for 82598
  ixgbe: support for ethtool set_rxfh
  ixgbe: Avoid needless PHY access on copper phys
  ixgbe: cleanup to use cached mask value
  ixgbe: Remove second instance of lan_id variable
  ixgbe: use kzalloc for allocating one thing
  flow: Move __get_hash_from_flowi{4,6} into flow_dissector.c
  ixgbe: Remove unused PCI bus types
  ...

1 files changed, 133 insertions, 66 deletions

diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index 395f32f..7e91d82 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -366,15 +366,32 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget)
  **/
 static void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector)
 {
-	u32 val = I40E_VFINT_DYN_CTLN_INTENA_MASK |
-		  I40E_VFINT_DYN_CTLN1_ITR_INDX_MASK | /* set noitr */
-		  I40E_VFINT_DYN_CTLN_SWINT_TRIG_MASK |
-		  I40E_VFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK;
-		  /* allow 00 to be written to the index */
-
-	wr32(&vsi->back->hw,
-	     I40E_VFINT_DYN_CTLN1(q_vector->v_idx + vsi->base_vector - 1),
-	     val);
+	u16 flags = q_vector->tx.ring[0].flags;
+
+	if (flags & I40E_TXR_FLAGS_WB_ON_ITR) {
+		u32 val;
+
+		if (q_vector->arm_wb_state)
+			return;
+
+		val = I40E_VFINT_DYN_CTLN1_WB_ON_ITR_MASK;
+
+		wr32(&vsi->back->hw,
+		     I40E_VFINT_DYN_CTLN1(q_vector->v_idx +
+					  vsi->base_vector - 1),
+		     val);
+		q_vector->arm_wb_state = true;
+	} else {
+		u32 val = I40E_VFINT_DYN_CTLN1_INTENA_MASK |
+			  I40E_VFINT_DYN_CTLN1_ITR_INDX_MASK | /* set noitr */
+			  I40E_VFINT_DYN_CTLN1_SWINT_TRIG_MASK |
+			  I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_MASK;
+			  /* allow 00 to be written to the index */
+
+		wr32(&vsi->back->hw,
+		     I40E_VFINT_DYN_CTLN1(q_vector->v_idx +
+					  vsi->base_vector - 1), val);
+	}
 }
 
 /**
@@ -404,7 +421,7 @@ static void i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
 	 *  20-1249MB/s bulk   (8000 ints/s)
 	 */
 	bytes_per_int = rc->total_bytes / rc->itr;
-	switch (rc->itr) {
+	switch (new_latency_range) {
 	case I40E_LOWEST_LATENCY:
 		if (bytes_per_int > 10)
 			new_latency_range = I40E_LOW_LATENCY;
@@ -417,9 +434,14 @@ static void i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
 		break;
 	case I40E_BULK_LATENCY:
 		if (bytes_per_int <= 20)
-			rc->latency_range = I40E_LOW_LATENCY;
+			new_latency_range = I40E_LOW_LATENCY;
+		break;
+	default:
+		if (bytes_per_int <= 20)
+			new_latency_range = I40E_LOW_LATENCY;
 		break;
 	}
+	rc->latency_range = new_latency_range;
 
 	switch (new_latency_range) {
 	case I40E_LOWEST_LATENCY:
@@ -435,42 +457,14 @@ static void i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
 		break;
 	}
 
-	if (new_itr != rc->itr) {
-		/* do an exponential smoothing */
-		new_itr = (10 * new_itr * rc->itr) /
-			  ((9 * new_itr) + rc->itr);
-		rc->itr = new_itr & I40E_MAX_ITR;
-	}
+	if (new_itr != rc->itr)
+		rc->itr = new_itr;
 
 	rc->total_bytes = 0;
 	rc->total_packets = 0;
 }
 
-/**
- * i40e_update_dynamic_itr - Adjust ITR based on bytes per int
- * @q_vector: the vector to adjust
- **/
-static void i40e_update_dynamic_itr(struct i40e_q_vector *q_vector)
-{
-	u16 vector = q_vector->vsi->base_vector + q_vector->v_idx;
-	struct i40e_hw *hw = &q_vector->vsi->back->hw;
-	u32 reg_addr;
-	u16 old_itr;
-
-	reg_addr = I40E_VFINT_ITRN1(I40E_RX_ITR, vector - 1);
-	old_itr = q_vector->rx.itr;
-	i40e_set_new_dynamic_itr(&q_vector->rx);
-	if (old_itr != q_vector->rx.itr)
-		wr32(hw, reg_addr, q_vector->rx.itr);
-
-	reg_addr = I40E_VFINT_ITRN1(I40E_TX_ITR, vector - 1);
-	old_itr = q_vector->tx.itr;
-	i40e_set_new_dynamic_itr(&q_vector->tx);
-	if (old_itr != q_vector->tx.itr)
-		wr32(hw, reg_addr, q_vector->tx.itr);
-}
-
-/**
+/*
  * i40evf_setup_tx_descriptors - Allocate the Tx descriptors
  * @tx_ring: the tx ring to set up
  *
@@ -873,7 +867,7 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 		return;
 
 	/* did the hardware decode the packet and checksum? */
-	if (!(rx_status & (1 << I40E_RX_DESC_STATUS_L3L4P_SHIFT)))
+	if (!(rx_status & BIT(I40E_RX_DESC_STATUS_L3L4P_SHIFT)))
 		return;
 
 	/* both known and outer_ip must be set for the below code to work */
@@ -888,25 +882,25 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 		ipv6 = true;
 
 	if (ipv4 &&
-	    (rx_error & ((1 << I40E_RX_DESC_ERROR_IPE_SHIFT) |
-			 (1 << I40E_RX_DESC_ERROR_EIPE_SHIFT))))
+	    (rx_error & (BIT(I40E_RX_DESC_ERROR_IPE_SHIFT) |
+			 BIT(I40E_RX_DESC_ERROR_EIPE_SHIFT))))
 		goto checksum_fail;
 
 	/* likely incorrect csum if alternate IP extension headers found */
 	if (ipv6 &&
-	    rx_status & (1 << I40E_RX_DESC_STATUS_IPV6EXADD_SHIFT))
+	    rx_status & BIT(I40E_RX_DESC_STATUS_IPV6EXADD_SHIFT))
 		/* don't increment checksum err here, non-fatal err */
 		return;
 
 	/* there was some L4 error, count error and punt packet to the stack */
-	if (rx_error & (1 << I40E_RX_DESC_ERROR_L4E_SHIFT))
+	if (rx_error & BIT(I40E_RX_DESC_ERROR_L4E_SHIFT))
 		goto checksum_fail;
 
 	/* handle packets that were not able to be checksummed due
 	 * to arrival speed, in this case the stack can compute
 	 * the csum.
 	 */
-	if (rx_error & (1 << I40E_RX_DESC_ERROR_PPRS_SHIFT))
+	if (rx_error & BIT(I40E_RX_DESC_ERROR_PPRS_SHIFT))
 		return;
 
 	/* If VXLAN traffic has an outer UDPv4 checksum we need to check
@@ -1027,7 +1021,7 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget)
 		rx_status = (qword & I40E_RXD_QW1_STATUS_MASK) >>
 			I40E_RXD_QW1_STATUS_SHIFT;
 
-		if (!(rx_status & (1 << I40E_RX_DESC_STATUS_DD_SHIFT)))
+		if (!(rx_status & BIT(I40E_RX_DESC_STATUS_DD_SHIFT)))
 			break;
 
 		/* This memory barrier is needed to keep us from reading
@@ -1063,8 +1057,8 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget)
 
 		rx_error = (qword & I40E_RXD_QW1_ERROR_MASK) >>
 			   I40E_RXD_QW1_ERROR_SHIFT;
-		rx_hbo = rx_error & (1 << I40E_RX_DESC_ERROR_HBO_SHIFT);
-		rx_error &= ~(1 << I40E_RX_DESC_ERROR_HBO_SHIFT);
+		rx_hbo = rx_error & BIT(I40E_RX_DESC_ERROR_HBO_SHIFT);
+		rx_error &= ~BIT(I40E_RX_DESC_ERROR_HBO_SHIFT);
 
 		rx_ptype = (qword & I40E_RXD_QW1_PTYPE_MASK) >>
 			   I40E_RXD_QW1_PTYPE_SHIFT;
@@ -1116,7 +1110,7 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget)
 		I40E_RX_INCREMENT(rx_ring, i);
 
 		if (unlikely(
-		    !(rx_status & (1 << I40E_RX_DESC_STATUS_EOF_SHIFT)))) {
+		    !(rx_status & BIT(I40E_RX_DESC_STATUS_EOF_SHIFT)))) {
 			struct i40e_rx_buffer *next_buffer;
 
 			next_buffer = &rx_ring->rx_bi[i];
@@ -1126,7 +1120,7 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget)
 		}
 
 		/* ERR_MASK will only have valid bits if EOP set */
-		if (unlikely(rx_error & (1 << I40E_RX_DESC_ERROR_RXE_SHIFT))) {
+		if (unlikely(rx_error & BIT(I40E_RX_DESC_ERROR_RXE_SHIFT))) {
 			dev_kfree_skb_any(skb);
 			continue;
 		}
@@ -1141,7 +1135,7 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget)
 
 		i40e_rx_checksum(vsi, skb, rx_status, rx_error, rx_ptype);
 
-		vlan_tag = rx_status & (1 << I40E_RX_DESC_STATUS_L2TAG1P_SHIFT)
+		vlan_tag = rx_status & BIT(I40E_RX_DESC_STATUS_L2TAG1P_SHIFT)
 			 ? le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1)
 			 : 0;
 #ifdef I40E_FCOE
@@ -1202,7 +1196,7 @@ static int i40e_clean_rx_irq_1buf(struct i40e_ring *rx_ring, int budget)
 		rx_status = (qword & I40E_RXD_QW1_STATUS_MASK) >>
 			I40E_RXD_QW1_STATUS_SHIFT;
 
-		if (!(rx_status & (1 << I40E_RX_DESC_STATUS_DD_SHIFT)))
+		if (!(rx_status & BIT(I40E_RX_DESC_STATUS_DD_SHIFT)))
 			break;
 
 		/* This memory barrier is needed to keep us from reading
@@ -1220,7 +1214,7 @@ static int i40e_clean_rx_irq_1buf(struct i40e_ring *rx_ring, int budget)
 
 		rx_error = (qword & I40E_RXD_QW1_ERROR_MASK) >>
 			   I40E_RXD_QW1_ERROR_SHIFT;
-		rx_error &= ~(1 << I40E_RX_DESC_ERROR_HBO_SHIFT);
+		rx_error &= ~BIT(I40E_RX_DESC_ERROR_HBO_SHIFT);
 
 		rx_ptype = (qword & I40E_RXD_QW1_PTYPE_MASK) >>
 			   I40E_RXD_QW1_PTYPE_SHIFT;
@@ -1238,13 +1232,13 @@ static int i40e_clean_rx_irq_1buf(struct i40e_ring *rx_ring, int budget)
 		I40E_RX_INCREMENT(rx_ring, i);
 
 		if (unlikely(
-		    !(rx_status & (1 << I40E_RX_DESC_STATUS_EOF_SHIFT)))) {
+		    !(rx_status & BIT(I40E_RX_DESC_STATUS_EOF_SHIFT)))) {
 			rx_ring->rx_stats.non_eop_descs++;
 			continue;
 		}
 
 		/* ERR_MASK will only have valid bits if EOP set */
-		if (unlikely(rx_error & (1 << I40E_RX_DESC_ERROR_RXE_SHIFT))) {
+		if (unlikely(rx_error & BIT(I40E_RX_DESC_ERROR_RXE_SHIFT))) {
 			dev_kfree_skb_any(skb);
 			/* TODO: shouldn't we increment a counter indicating the
 			 * drop?
@@ -1262,7 +1256,7 @@ static int i40e_clean_rx_irq_1buf(struct i40e_ring *rx_ring, int budget)
 
 		i40e_rx_checksum(vsi, skb, rx_status, rx_error, rx_ptype);
 
-		vlan_tag = rx_status & (1 << I40E_RX_DESC_STATUS_L2TAG1P_SHIFT)
+		vlan_tag = rx_status & BIT(I40E_RX_DESC_STATUS_L2TAG1P_SHIFT)
 			 ? le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1)
 			 : 0;
 		i40e_receive_skb(rx_ring, skb, vlan_tag);
@@ -1281,6 +1275,67 @@ static int i40e_clean_rx_irq_1buf(struct i40e_ring *rx_ring, int budget)
 }
 
 /**
+ * i40e_update_enable_itr - Update itr and re-enable MSIX interrupt
+ * @vsi: the VSI we care about
+ * @q_vector: q_vector for which itr is being updated and interrupt enabled
+ *
+ **/
+static inline void i40e_update_enable_itr(struct i40e_vsi *vsi,
+					  struct i40e_q_vector *q_vector)
+{
+	struct i40e_hw *hw = &vsi->back->hw;
+	u16 old_itr;
+	int vector;
+	u32 val;
+
+	vector = (q_vector->v_idx + vsi->base_vector);
+	if (ITR_IS_DYNAMIC(vsi->rx_itr_setting)) {
+		old_itr = q_vector->rx.itr;
+		i40e_set_new_dynamic_itr(&q_vector->rx);
+		if (old_itr != q_vector->rx.itr) {
+			val = I40E_VFINT_DYN_CTLN1_INTENA_MASK |
+			I40E_VFINT_DYN_CTLN1_CLEARPBA_MASK |
+			(I40E_RX_ITR <<
+				I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT) |
+			(q_vector->rx.itr <<
+				I40E_VFINT_DYN_CTLN1_INTERVAL_SHIFT);
+		} else {
+			val = I40E_VFINT_DYN_CTLN1_INTENA_MASK |
+			I40E_VFINT_DYN_CTLN1_CLEARPBA_MASK |
+			(I40E_ITR_NONE <<
+				I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT);
+		}
+		if (!test_bit(__I40E_DOWN, &vsi->state))
+			wr32(hw, I40E_VFINT_DYN_CTLN1(vector - 1), val);
+	} else {
+		i40evf_irq_enable_queues(vsi->back, 1
+			<< q_vector->v_idx);
+	}
+	if (ITR_IS_DYNAMIC(vsi->tx_itr_setting)) {
+		old_itr = q_vector->tx.itr;
+		i40e_set_new_dynamic_itr(&q_vector->tx);
+		if (old_itr != q_vector->tx.itr) {
+			val = I40E_VFINT_DYN_CTLN1_INTENA_MASK |
+				I40E_VFINT_DYN_CTLN1_CLEARPBA_MASK |
+				(I40E_TX_ITR <<
+				   I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT) |
+				(q_vector->tx.itr <<
+				   I40E_VFINT_DYN_CTLN1_INTERVAL_SHIFT);
+
+		} else {
+			val = I40E_VFINT_DYN_CTLN1_INTENA_MASK |
+				I40E_VFINT_DYN_CTLN1_CLEARPBA_MASK |
+				(I40E_ITR_NONE <<
+				   I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT);
+		}
+		if (!test_bit(__I40E_DOWN, &vsi->state))
+			wr32(hw, I40E_VFINT_DYN_CTLN1(vector - 1), val);
+	} else {
+		i40evf_irq_enable_queues(vsi->back, BIT(q_vector->v_idx));
+	}
+}
+
+/**
  * i40evf_napi_poll - NAPI polling Rx/Tx cleanup routine
  * @napi: napi struct with our devices info in it
  * @budget: amount of work driver is allowed to do this pass, in packets
@@ -1334,15 +1389,12 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget)
 		return budget;
 	}
 
+	if (vsi->back->flags & I40E_TXR_FLAGS_WB_ON_ITR)
+		q_vector->arm_wb_state = false;
+
 	/* Work is done so exit the polling mode and re-enable the interrupt */
 	napi_complete(napi);
-	if (ITR_IS_DYNAMIC(vsi->rx_itr_setting) ||
-	    ITR_IS_DYNAMIC(vsi->tx_itr_setting))
-		i40e_update_dynamic_itr(q_vector);
-
-	if (!test_bit(__I40E_DOWN, &vsi->state))
-		i40evf_irq_enable_queues(vsi->back, 1 << q_vector->v_idx);
-
+	i40e_update_enable_itr(vsi, q_vector);
 	return 0;
 }
 
@@ -1476,11 +1528,15 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 	struct iphdr *this_ip_hdr;
 	u32 network_hdr_len;
 	u8 l4_hdr = 0;
+	struct udphdr *oudph;
+	struct iphdr *oiph;
 	u32 l4_tunnel = 0;
 
 	if (skb->encapsulation) {
 		switch (ip_hdr(skb)->protocol) {
 		case IPPROTO_UDP:
+			oudph = udp_hdr(skb);
+			oiph = ip_hdr(skb);
 			l4_tunnel = I40E_TXD_CTX_UDP_TUNNELING;
 			*tx_flags |= I40E_TX_FLAGS_VXLAN_TUNNEL;
 			break;
@@ -1519,6 +1575,15 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 		}
 
 
+		if ((tx_ring->flags & I40E_TXR_FLAGS_OUTER_UDP_CSUM) &&
+		    (l4_tunnel == I40E_TXD_CTX_UDP_TUNNELING)        &&
+		    (*cd_tunneling & I40E_TXD_CTX_QW0_EXT_IP_MASK)) {
+			oudph->check = ~csum_tcpudp_magic(oiph->saddr,
+					oiph->daddr,
+					(skb->len - skb_transport_offset(skb)),
+					IPPROTO_UDP, 0);
+			*cd_tunneling |= I40E_TXD_CTX_QW0_L4T_CS_MASK;
+		}
 	} else {
 		network_hdr_len = skb_network_header_len(skb);
 		this_ip_hdr = ip_hdr(skb);
@@ -1841,6 +1906,8 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	    netif_xmit_stopped(netdev_get_tx_queue(tx_ring->netdev,
 						   tx_ring->queue_index)))
 		writel(i, tx_ring->tail);
+	else
+		prefetchw(tx_desc + 1);
 
 	return;