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

Pull networking updates from David Miller:

 1) Significantly shrink the core networking routing structures. Result
    of http://vger.kernel.org/~davem/seoul2017_netdev_keynote.pdf

 2) Add netdevsim driver for testing various offloads, from Jakub
    Kicinski.

 3) Support cross-chip FDB operations in DSA, from Vivien Didelot.

 4) Add a 2nd listener hash table for TCP, similar to what was done for
    UDP. From Martin KaFai Lau.

 5) Add eBPF based queue selection to tun, from Jason Wang.

 6) Lockless qdisc support, from John Fastabend.

 7) SCTP stream interleave support, from Xin Long.

 8) Smoother TCP receive autotuning, from Eric Dumazet.

 9) Lots of erspan tunneling enhancements, from William Tu.

10) Add true function call support to BPF, from Alexei Starovoitov.

11) Add explicit support for GRO HW offloading, from Michael Chan.

12) Support extack generation in more netlink subsystems. From Alexander
    Aring, Quentin Monnet, and Jakub Kicinski.

13) Add 1000BaseX, flow control, and EEE support to mvneta driver. From
    Russell King.

14) Add flow table abstraction to netfilter, from Pablo Neira Ayuso.

15) Many improvements and simplifications to the NFP driver bpf JIT,
    from Jakub Kicinski.

16) Support for ipv6 non-equal cost multipath routing, from Ido
    Schimmel.

17) Add resource abstration to devlink, from Arkadi Sharshevsky.

18) Packet scheduler classifier shared filter block support, from Jiri
    Pirko.

19) Avoid locking in act_csum, from Davide Caratti.

20) devinet_ioctl() simplifications from Al viro.

21) More TCP bpf improvements from Lawrence Brakmo.

22) Add support for onlink ipv6 route flag, similar to ipv4, from David
    Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1925 commits)
  tls: Add support for encryption using async offload accelerator
  ip6mr: fix stale iterator
  net/sched: kconfig: Remove blank help texts
  openvswitch: meter: Use 64-bit arithmetic instead of 32-bit
  tcp_nv: fix potential integer overflow in tcpnv_acked
  r8169: fix RTL8168EP take too long to complete driver initialization.
  qmi_wwan: Add support for Quectel EP06
  rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK
  ipmr: Fix ptrdiff_t print formatting
  ibmvnic: Wait for device response when changing MAC
  qlcnic: fix deadlock bug
  tcp: release sk_frag.page in tcp_disconnect
  ipv4: Get the address of interface correctly.
  net_sched: gen_estimator: fix lockdep splat
  net: macb: Handle HRESP error
  net/mlx5e: IPoIB, Fix copy-paste bug in flow steering refactoring
  ipv6: addrconf: break critical section in addrconf_verify_rtnl()
  ipv6: change route cache aging logic
  i40e/i40evf: Update DESC_NEEDED value to reflect larger value
  bnxt_en: cleanup DIM work on device shutdown
  ...

1 files changed, 56 insertions, 16 deletions

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index c208753ff5b7..b88fae785369 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -1744,6 +1744,20 @@ static void igb_configure_cbs(struct igb_adapter *adapter, int queue,
 		 *     value = idleSlope * 61034
 		 *             -----------------                          (E6)
 		 *                  1000000
+		 *
+		 * NOTE: For i210, given the above, we can see that idleslope
+		 *       is represented in 16.38431 kbps units by the value at
+		 *       the TQAVCC register (1Gbps / 61034), which reduces
+		 *       the granularity for idleslope increments.
+		 *       For instance, if you want to configure a 2576kbps
+		 *       idleslope, the value to be written on the register
+		 *       would have to be 157.23. If rounded down, you end
+		 *       up with less bandwidth available than originally
+		 *       required (~2572 kbps). If rounded up, you end up
+		 *       with a higher bandwidth (~2589 kbps). Below the
+		 *       approach we take is to always round up the
+		 *       calculated value, so the resulting bandwidth might
+		 *       be slightly higher for some configurations.
 		 */
 		value = DIV_ROUND_UP_ULL(idleslope * 61034ULL, 1000000);
 
@@ -3200,8 +3214,6 @@ static int igb_enable_sriov(struct pci_dev *pdev, int num_vfs)
 	/* if allocation failed then we do not support SR-IOV */
 	if (!adapter->vf_data) {
 		adapter->vfs_allocated_count = 0;
-		dev_err(&pdev->dev,
-			"Unable to allocate memory for VF Data Storage\n");
 		err = -ENOMEM;
 		goto out;
 	}
@@ -3373,10 +3385,10 @@ static void igb_probe_vfs(struct igb_adapter *adapter)
 #endif /* CONFIG_PCI_IOV */
 }
 
-static void igb_init_queue_configuration(struct igb_adapter *adapter)
+unsigned int igb_get_max_rss_queues(struct igb_adapter *adapter)
 {
 	struct e1000_hw *hw = &adapter->hw;
-	u32 max_rss_queues;
+	unsigned int max_rss_queues;
 
 	/* Determine the maximum number of RSS queues supported. */
 	switch (hw->mac.type) {
@@ -3407,6 +3419,14 @@ static void igb_init_queue_configuration(struct igb_adapter *adapter)
 		break;
 	}
 
+	return max_rss_queues;
+}
+
+static void igb_init_queue_configuration(struct igb_adapter *adapter)
+{
+	u32 max_rss_queues;
+
+	max_rss_queues = igb_get_max_rss_queues(adapter);
 	adapter->rss_queues = min_t(u32, max_rss_queues, num_online_cpus());
 
 	igb_set_flag_queue_pairs(adapter, max_rss_queues);
@@ -3676,7 +3696,7 @@ static int __igb_close(struct net_device *netdev, bool suspending)
 
 int igb_close(struct net_device *netdev)
 {
-	if (netif_device_present(netdev))
+	if (netif_device_present(netdev) || netdev->dismantle)
 		return __igb_close(netdev, false);
 	return 0;
 }
@@ -8718,7 +8738,8 @@ static void igb_rar_set_index(struct igb_adapter *adapter, u32 index)
 
 	/* Indicate to hardware the Address is Valid. */
 	if (adapter->mac_table[index].state & IGB_MAC_STATE_IN_USE) {
-		rar_high |= E1000_RAH_AV;
+		if (is_valid_ether_addr(addr))
+			rar_high |= E1000_RAH_AV;
 
 		if (hw->mac.type == e1000_82575)
 			rar_high |= E1000_RAH_POOL_1 *
@@ -8756,17 +8777,36 @@ static int igb_set_vf_mac(struct igb_adapter *adapter,
 static int igb_ndo_set_vf_mac(struct net_device *netdev, int vf, u8 *mac)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
-	if (!is_valid_ether_addr(mac) || (vf >= adapter->vfs_allocated_count))
+
+	if (vf >= adapter->vfs_allocated_count)
+		return -EINVAL;
+
+	/* Setting the VF MAC to 0 reverts the IGB_VF_FLAG_PF_SET_MAC
+	 * flag and allows to overwrite the MAC via VF netdev.  This
+	 * is necessary to allow libvirt a way to restore the original
+	 * MAC after unbinding vfio-pci and reloading igbvf after shutting
+	 * down a VM.
+	 */
+	if (is_zero_ether_addr(mac)) {
+		adapter->vf_data[vf].flags &= ~IGB_VF_FLAG_PF_SET_MAC;
+		dev_info(&adapter->pdev->dev,
+			 "remove administratively set MAC on VF %d\n",
+			 vf);
+	} else if (is_valid_ether_addr(mac)) {
+		adapter->vf_data[vf].flags |= IGB_VF_FLAG_PF_SET_MAC;
+		dev_info(&adapter->pdev->dev, "setting MAC %pM on VF %d\n",
+			 mac, vf);
+		dev_info(&adapter->pdev->dev,
+			 "Reload the VF driver to make this change effective.");
+		/* Generate additional warning if PF is down */
+		if (test_bit(__IGB_DOWN, &adapter->state)) {
+			dev_warn(&adapter->pdev->dev,
+				 "The VF MAC address has been set, but the PF device is not up.\n");
+			dev_warn(&adapter->pdev->dev,
+				 "Bring the PF device up before attempting to use the VF device.\n");
+		}
+	} else {
 		return -EINVAL;
-	adapter->vf_data[vf].flags |= IGB_VF_FLAG_PF_SET_MAC;
-	dev_info(&adapter->pdev->dev, "setting MAC %pM on VF %d\n", mac, vf);
-	dev_info(&adapter->pdev->dev,
-		 "Reload the VF driver to make this change effective.");
-	if (test_bit(__IGB_DOWN, &adapter->state)) {
-		dev_warn(&adapter->pdev->dev,
-			 "The VF MAC address has been set, but the PF device is not up.\n");
-		dev_warn(&adapter->pdev->dev,
-			 "Bring the PF device up before attempting to use the VF device.\n");
 	}
 	return igb_set_vf_mac(adapter, vf, mac);
 }