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, 38 insertions, 7 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 29c2a01..006757f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -405,6 +405,21 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev->caps.max_gso_sz	     = dev_cap->max_gso_sz;
 	dev->caps.max_rss_tbl_sz     = dev_cap->max_rss_tbl_sz;
 
+	if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_PHV_EN) {
+		struct mlx4_init_hca_param hca_param;
+
+		memset(&hca_param, 0, sizeof(hca_param));
+		err = mlx4_QUERY_HCA(dev, &hca_param);
+		/* Turn off PHV_EN flag in case phv_check_en is set.
+		 * phv_check_en is a HW check that parse the packet and verify
+		 * phv bit was reported correctly in the wqe. To allow QinQ
+		 * PHV_EN flag should be set and phv_check_en must be cleared
+		 * otherwise QinQ packets will be drop by the HW.
+		 */
+		if (err || hca_param.phv_check_en)
+			dev->caps.flags2 &= ~MLX4_DEV_CAP_FLAG2_PHV_EN;
+	}
+
 	/* Sense port always allowed on supported devices for ConnectX-1 and -2 */
 	if (mlx4_priv(dev)->pci_dev_data & MLX4_PCI_DEV_FORCE_SENSE_PORT)
 		dev->caps.flags |= MLX4_DEV_CAP_FLAG_SENSE_SUPPORT;
@@ -2654,9 +2669,14 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev)
 
 	if (msi_x) {
 		int nreq = dev->caps.num_ports * num_online_cpus() + 1;
+		bool shared_ports = false;
 
 		nreq = min_t(int, dev->caps.num_eqs - dev->caps.reserved_eqs,
 			     nreq);
+		if (nreq > MAX_MSIX) {
+			nreq = MAX_MSIX;
+			shared_ports = true;
+		}
 
 		entries = kcalloc(nreq, sizeof *entries, GFP_KERNEL);
 		if (!entries)
@@ -2679,6 +2699,9 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev)
 		bitmap_zero(priv->eq_table.eq[MLX4_EQ_ASYNC].actv_ports.ports,
 			    dev->caps.num_ports);
 
+		if (MLX4_IS_LEGACY_EQ_MODE(dev->caps))
+			shared_ports = true;
+
 		for (i = 0; i < dev->caps.num_comp_vectors + 1; i++) {
 			if (i == MLX4_EQ_ASYNC)
 				continue;
@@ -2686,7 +2709,7 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev)
 			priv->eq_table.eq[i].irq =
 				entries[i + 1 - !!(i > MLX4_EQ_ASYNC)].vector;
 
-			if (MLX4_IS_LEGACY_EQ_MODE(dev->caps)) {
+			if (shared_ports) {
 				bitmap_fill(priv->eq_table.eq[i].actv_ports.ports,
 					    dev->caps.num_ports);
 				/* We don't set affinity hint when there
@@ -2912,6 +2935,8 @@ static u64 mlx4_enable_sriov(struct mlx4_dev *dev, struct pci_dev *pdev,
 {
 	u64 dev_flags = dev->flags;
 	int err = 0;
+	int fw_enabled_sriov_vfs = min(pci_sriov_get_totalvfs(pdev),
+					MLX4_MAX_NUM_VF);
 
 	if (reset_flow) {
 		dev->dev_vfs = kcalloc(total_vfs, sizeof(*dev->dev_vfs),
@@ -2937,6 +2962,12 @@ static u64 mlx4_enable_sriov(struct mlx4_dev *dev, struct pci_dev *pdev,
 	}
 
 	if (!(dev->flags &  MLX4_FLAG_SRIOV)) {
+		if (total_vfs > fw_enabled_sriov_vfs) {
+			mlx4_err(dev, "requested vfs (%d) > available vfs (%d). Continuing without SR_IOV\n",
+				 total_vfs, fw_enabled_sriov_vfs);
+			err = -ENOMEM;
+			goto disable_sriov;
+		}
 		mlx4_warn(dev, "Enabling SR-IOV with %d VFs\n", total_vfs);
 		err = pci_enable_sriov(pdev, total_vfs);
 	}
@@ -3418,20 +3449,20 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data,
 			goto err_disable_pdev;
 		}
 	}
-	if (total_vfs >= MLX4_MAX_NUM_VF) {
+	if (total_vfs > MLX4_MAX_NUM_VF) {
 		dev_err(&pdev->dev,
-			"Requested more VF's (%d) than allowed (%d)\n",
-			total_vfs, MLX4_MAX_NUM_VF - 1);
+			"Requested more VF's (%d) than allowed by hw (%d)\n",
+			total_vfs, MLX4_MAX_NUM_VF);
 		err = -EINVAL;
 		goto err_disable_pdev;
 	}
 
 	for (i = 0; i < MLX4_MAX_PORTS; i++) {
-		if (nvfs[i] + nvfs[2] >= MLX4_MAX_NUM_VF_P_PORT) {
+		if (nvfs[i] + nvfs[2] > MLX4_MAX_NUM_VF_P_PORT) {
 			dev_err(&pdev->dev,
-				"Requested more VF's (%d) for port (%d) than allowed (%d)\n",
+				"Requested more VF's (%d) for port (%d) than allowed by driver (%d)\n",
 				nvfs[i] + nvfs[2], i + 1,
-				MLX4_MAX_NUM_VF_P_PORT - 1);
+				MLX4_MAX_NUM_VF_P_PORT);
 			err = -EINVAL;
 			goto err_disable_pdev;
 		}