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

Pull networking changes from David Miller:

 1) GRE now works over ipv6, from Dmitry Kozlov.

 2) Make SCTP more network namespace aware, from Eric Biederman.

 3) TEAM driver now works with non-ethernet devices, from Jiri Pirko.

 4) Make openvswitch network namespace aware, from Pravin B Shelar.

 5) IPV6 NAT implementation, from Patrick McHardy.

 6) Server side support for TCP Fast Open, from Jerry Chu and others.

 7) Packet BPF filter supports MOD and XOR, from Eric Dumazet and Daniel
    Borkmann.

 8) Increate the loopback default MTU to 64K, from Eric Dumazet.

 9) Use a per-task rather than per-socket page fragment allocator for
    outgoing networking traffic.  This benefits processes that have very
    many mostly idle sockets, which is quite common.

    From Eric Dumazet.

10) Use up to 32K for page fragment allocations, with fallbacks to
    smaller sizes when higher order page allocations fail.  Benefits are
    a) less segments for driver to process b) less calls to page
    allocator c) less waste of space.

    From Eric Dumazet.

11) Allow GRO to be used on GRE tunnels, from Eric Dumazet.

12) VXLAN device driver, one way to handle VLAN issues such as the
    limitation of 4096 VLAN IDs yet still have some level of isolation.
    From Stephen Hemminger.

13) As usual there is a large boatload of driver changes, with the scale
    perhaps tilted towards the wireless side this time around.

Fix up various fairly trivial conflicts, mostly caused by the user
namespace changes.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1012 commits)
  hyperv: Add buffer for extended info after the RNDIS response message.
  hyperv: Report actual status in receive completion packet
  hyperv: Remove extra allocated space for recv_pkt_list elements
  hyperv: Fix page buffer handling in rndis_filter_send_request()
  hyperv: Fix the missing return value in rndis_filter_set_packet_filter()
  hyperv: Fix the max_xfer_size in RNDIS initialization
  vxlan: put UDP socket in correct namespace
  vxlan: Depend on CONFIG_INET
  sfc: Fix the reported priorities of different filter types
  sfc: Remove EFX_FILTER_FLAG_RX_OVERRIDE_IP
  sfc: Fix loopback self-test with separate_tx_channels=1
  sfc: Fix MCDI structure field lookup
  sfc: Add parentheses around use of bitfield macro arguments
  sfc: Fix null function pointer in efx_sriov_channel_type
  vxlan: virtual extensible lan
  igmp: export symbol ip_mc_leave_group
  netlink: add attributes to fdb interface
  tg3: unconditionally select HWMON support when tg3 is enabled.
  Revert "net: ti cpsw ethernet: allow reading phy interface mode from DT"
  gre: fix sparse warning
  ...

1 files changed, 64 insertions, 41 deletions

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
index 4fea8716ab64..dce48bf64d96 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
@@ -346,6 +346,10 @@ void ixgbe_restore_vf_multicasts(struct ixgbe_adapter *adapter)
 static int ixgbe_set_vf_vlan(struct ixgbe_adapter *adapter, int add, int vid,
 			     u32 vf)
 {
+	/* VLAN 0 is a special case, don't allow it to be removed */
+	if (!vid && !add)
+		return 0;
+
 	return adapter->hw.mac.ops.set_vfta(&adapter->hw, vid, vf, (bool)add);
 }
 
@@ -414,6 +418,7 @@ static inline void ixgbe_vf_reset_event(struct ixgbe_adapter *adapter, u32 vf)
 				  VLAN_PRIO_SHIFT)), vf);
 		ixgbe_set_vmolr(hw, vf, false);
 	} else {
+		ixgbe_set_vf_vlan(adapter, true, 0, vf);
 		ixgbe_set_vmvir(adapter, 0, vf);
 		ixgbe_set_vmolr(hw, vf, true);
 	}
@@ -810,9 +815,9 @@ out:
        return err;
 }
 
-static int ixgbe_link_mbps(int internal_link_speed)
+static int ixgbe_link_mbps(struct ixgbe_adapter *adapter)
 {
-	switch (internal_link_speed) {
+	switch (adapter->link_speed) {
 	case IXGBE_LINK_SPEED_100_FULL:
 		return 100;
 	case IXGBE_LINK_SPEED_1GB_FULL:
@@ -824,27 +829,30 @@ static int ixgbe_link_mbps(int internal_link_speed)
 	}
 }
 
-static void ixgbe_set_vf_rate_limit(struct ixgbe_hw *hw, int vf, int tx_rate,
-				    int link_speed)
+static void ixgbe_set_vf_rate_limit(struct ixgbe_adapter *adapter, int vf)
 {
-	int rf_dec, rf_int;
-	u32 bcnrc_val;
+	struct ixgbe_ring_feature *vmdq = &adapter->ring_feature[RING_F_VMDQ];
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 bcnrc_val = 0;
+	u16 queue, queues_per_pool;
+	u16 tx_rate = adapter->vfinfo[vf].tx_rate;
+
+	if (tx_rate) {
+		/* start with base link speed value */
+		bcnrc_val = adapter->vf_rate_link_speed;
 
-	if (tx_rate != 0) {
 		/* Calculate the rate factor values to set */
-		rf_int = link_speed / tx_rate;
-		rf_dec = (link_speed - (rf_int * tx_rate));
-		rf_dec = (rf_dec * (1<<IXGBE_RTTBCNRC_RF_INT_SHIFT)) / tx_rate;
-
-		bcnrc_val = IXGBE_RTTBCNRC_RS_ENA;
-		bcnrc_val |= ((rf_int<<IXGBE_RTTBCNRC_RF_INT_SHIFT) &
-		               IXGBE_RTTBCNRC_RF_INT_MASK);
-		bcnrc_val |= (rf_dec & IXGBE_RTTBCNRC_RF_DEC_MASK);
-	} else {
-		bcnrc_val = 0;
+		bcnrc_val <<= IXGBE_RTTBCNRC_RF_INT_SHIFT;
+		bcnrc_val /= tx_rate;
+
+		/* clear everything but the rate factor */
+		bcnrc_val &= IXGBE_RTTBCNRC_RF_INT_MASK |
+			     IXGBE_RTTBCNRC_RF_DEC_MASK;
+
+		/* enable the rate scheduler */
+		bcnrc_val |= IXGBE_RTTBCNRC_RS_ENA;
 	}
 
-	IXGBE_WRITE_REG(hw, IXGBE_RTTDQSEL, 2*vf); /* vf Y uses queue 2*Y */
 	/*
 	 * Set global transmit compensation time to the MMW_SIZE in RTTBCNRM
 	 * register. Typically MMW_SIZE=0x014 if 9728-byte jumbo is supported
@@ -861,53 +869,68 @@ static void ixgbe_set_vf_rate_limit(struct ixgbe_hw *hw, int vf, int tx_rate,
 		break;
 	}
 
-	IXGBE_WRITE_REG(hw, IXGBE_RTTBCNRC, bcnrc_val);
+	/* determine how many queues per pool based on VMDq mask */
+	queues_per_pool = __ALIGN_MASK(1, ~vmdq->mask);
+
+	/* write value for all Tx queues belonging to VF */
+	for (queue = 0; queue < queues_per_pool; queue++) {
+		unsigned int reg_idx = (vf * queues_per_pool) + queue;
+
+		IXGBE_WRITE_REG(hw, IXGBE_RTTDQSEL, reg_idx);
+		IXGBE_WRITE_REG(hw, IXGBE_RTTBCNRC, bcnrc_val);
+	}
 }
 
 void ixgbe_check_vf_rate_limit(struct ixgbe_adapter *adapter)
 {
-	int actual_link_speed, i;
-	bool reset_rate = false;
+	int i;
 
 	/* VF Tx rate limit was not set */
-	if (adapter->vf_rate_link_speed == 0)
+	if (!adapter->vf_rate_link_speed)
 		return;
 
-	actual_link_speed = ixgbe_link_mbps(adapter->link_speed);
-	if (actual_link_speed != adapter->vf_rate_link_speed) {
-		reset_rate = true;
+	if (ixgbe_link_mbps(adapter) != adapter->vf_rate_link_speed) {
 		adapter->vf_rate_link_speed = 0;
 		dev_info(&adapter->pdev->dev,
-		         "Link speed has been changed. VF Transmit rate "
-		         "is disabled\n");
+			 "Link speed has been changed. VF Transmit rate is disabled\n");
 	}
 
 	for (i = 0; i < adapter->num_vfs; i++) {
-		if (reset_rate)
+		if (!adapter->vf_rate_link_speed)
 			adapter->vfinfo[i].tx_rate = 0;
 
-		ixgbe_set_vf_rate_limit(&adapter->hw, i,
-					adapter->vfinfo[i].tx_rate,
-					actual_link_speed);
+		ixgbe_set_vf_rate_limit(adapter, i);
 	}
 }
 
 int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int tx_rate)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
-	struct ixgbe_hw *hw = &adapter->hw;
-	int actual_link_speed;
+	int link_speed;
+
+	/* verify VF is active */
+	if (vf >= adapter->num_vfs)
+		return -EINVAL;
 
-	actual_link_speed = ixgbe_link_mbps(adapter->link_speed);
-	if ((vf >= adapter->num_vfs) || (!adapter->link_up) ||
-	    (tx_rate > actual_link_speed) || (actual_link_speed != 10000) ||
-	    ((tx_rate != 0) && (tx_rate <= 10)))
-	    /* rate limit cannot be set to 10Mb or less in 10Gb adapters */
+	/* verify link is up */
+	if (!adapter->link_up)
 		return -EINVAL;
 
-	adapter->vf_rate_link_speed = actual_link_speed;
-	adapter->vfinfo[vf].tx_rate = (u16)tx_rate;
-	ixgbe_set_vf_rate_limit(hw, vf, tx_rate, actual_link_speed);
+	/* verify we are linked at 10Gbps */
+	link_speed = ixgbe_link_mbps(adapter);
+	if (link_speed != 10000)
+		return -EINVAL;
+
+	/* rate limit cannot be less than 10Mbs or greater than link speed */
+	if (tx_rate && ((tx_rate <= 10) || (tx_rate > link_speed)))
+		return -EINVAL;
+
+	/* store values */
+	adapter->vf_rate_link_speed = link_speed;
+	adapter->vfinfo[vf].tx_rate = tx_rate;
+
+	/* update hardware configuration */
+	ixgbe_set_vf_rate_limit(adapter, vf);
 
 	return 0;
 }