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, 45 insertions, 31 deletions

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
index 8e2a957..4242f02 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
@@ -46,8 +46,8 @@ static bool ixgbe_cache_ring_dcb_sriov(struct ixgbe_adapter *adapter)
 #endif /* IXGBE_FCOE */
 	struct ixgbe_ring_feature *vmdq = &adapter->ring_feature[RING_F_VMDQ];
 	int i;
-	u16 reg_idx;
-	u8 tcs = netdev_get_num_tc(adapter->netdev);
+	u16 reg_idx, pool;
+	u8 tcs = adapter->hw_tcs;
 
 	/* verify we have DCB queueing enabled before proceeding */
 	if (tcs <= 1)
@@ -58,12 +58,16 @@ static bool ixgbe_cache_ring_dcb_sriov(struct ixgbe_adapter *adapter)
 		return false;
 
 	/* start at VMDq register offset for SR-IOV enabled setups */
+	pool = 0;
 	reg_idx = vmdq->offset * __ALIGN_MASK(1, ~vmdq->mask);
-	for (i = 0; i < adapter->num_rx_queues; i++, reg_idx++) {
+	for (i = 0, pool = 0; i < adapter->num_rx_queues; i++, reg_idx++) {
 		/* If we are greater than indices move to next pool */
-		if ((reg_idx & ~vmdq->mask) >= tcs)
+		if ((reg_idx & ~vmdq->mask) >= tcs) {
+			pool++;
 			reg_idx = __ALIGN_MASK(reg_idx, ~vmdq->mask);
+		}
 		adapter->rx_ring[i]->reg_idx = reg_idx;
+		adapter->rx_ring[i]->netdev = pool ? NULL : adapter->netdev;
 	}
 
 	reg_idx = vmdq->offset * __ALIGN_MASK(1, ~vmdq->mask);
@@ -92,6 +96,7 @@ static bool ixgbe_cache_ring_dcb_sriov(struct ixgbe_adapter *adapter)
 		for (i = fcoe->offset; i < adapter->num_rx_queues; i++) {
 			reg_idx = __ALIGN_MASK(reg_idx, ~vmdq->mask) + fcoe_tc;
 			adapter->rx_ring[i]->reg_idx = reg_idx;
+			adapter->rx_ring[i]->netdev = adapter->netdev;
 			reg_idx++;
 		}
 
@@ -111,9 +116,8 @@ static bool ixgbe_cache_ring_dcb_sriov(struct ixgbe_adapter *adapter)
 static void ixgbe_get_first_reg_idx(struct ixgbe_adapter *adapter, u8 tc,
 				    unsigned int *tx, unsigned int *rx)
 {
-	struct net_device *dev = adapter->netdev;
 	struct ixgbe_hw *hw = &adapter->hw;
-	u8 num_tcs = netdev_get_num_tc(dev);
+	u8 num_tcs = adapter->hw_tcs;
 
 	*tx = 0;
 	*rx = 0;
@@ -168,10 +172,9 @@ static void ixgbe_get_first_reg_idx(struct ixgbe_adapter *adapter, u8 tc,
  **/
 static bool ixgbe_cache_ring_dcb(struct ixgbe_adapter *adapter)
 {
-	struct net_device *dev = adapter->netdev;
+	u8 num_tcs = adapter->hw_tcs;
 	unsigned int tx_idx, rx_idx;
 	int tc, offset, rss_i, i;
-	u8 num_tcs = netdev_get_num_tc(dev);
 
 	/* verify we have DCB queueing enabled before proceeding */
 	if (num_tcs <= 1)
@@ -184,6 +187,7 @@ static bool ixgbe_cache_ring_dcb(struct ixgbe_adapter *adapter)
 		for (i = 0; i < rss_i; i++, tx_idx++, rx_idx++) {
 			adapter->tx_ring[offset + i]->reg_idx = tx_idx;
 			adapter->rx_ring[offset + i]->reg_idx = rx_idx;
+			adapter->rx_ring[offset + i]->netdev = adapter->netdev;
 			adapter->tx_ring[offset + i]->dcb_tc = tc;
 			adapter->rx_ring[offset + i]->dcb_tc = tc;
 		}
@@ -208,14 +212,15 @@ static bool ixgbe_cache_ring_sriov(struct ixgbe_adapter *adapter)
 #endif /* IXGBE_FCOE */
 	struct ixgbe_ring_feature *vmdq = &adapter->ring_feature[RING_F_VMDQ];
 	struct ixgbe_ring_feature *rss = &adapter->ring_feature[RING_F_RSS];
+	u16 reg_idx, pool;
 	int i;
-	u16 reg_idx;
 
 	/* only proceed if VMDq is enabled */
 	if (!(adapter->flags & IXGBE_FLAG_VMDQ_ENABLED))
 		return false;
 
 	/* start at VMDq register offset for SR-IOV enabled setups */
+	pool = 0;
 	reg_idx = vmdq->offset * __ALIGN_MASK(1, ~vmdq->mask);
 	for (i = 0; i < adapter->num_rx_queues; i++, reg_idx++) {
 #ifdef IXGBE_FCOE
@@ -224,15 +229,20 @@ static bool ixgbe_cache_ring_sriov(struct ixgbe_adapter *adapter)
 			break;
 #endif
 		/* If we are greater than indices move to next pool */
-		if ((reg_idx & ~vmdq->mask) >= rss->indices)
+		if ((reg_idx & ~vmdq->mask) >= rss->indices) {
+			pool++;
 			reg_idx = __ALIGN_MASK(reg_idx, ~vmdq->mask);
+		}
 		adapter->rx_ring[i]->reg_idx = reg_idx;
+		adapter->rx_ring[i]->netdev = pool ? NULL : adapter->netdev;
 	}
 
 #ifdef IXGBE_FCOE
 	/* FCoE uses a linear block of queues so just assigning 1:1 */
-	for (; i < adapter->num_rx_queues; i++, reg_idx++)
+	for (; i < adapter->num_rx_queues; i++, reg_idx++) {
 		adapter->rx_ring[i]->reg_idx = reg_idx;
+		adapter->rx_ring[i]->netdev = adapter->netdev;
+	}
 
 #endif
 	reg_idx = vmdq->offset * __ALIGN_MASK(1, ~vmdq->mask);
@@ -269,8 +279,10 @@ static bool ixgbe_cache_ring_rss(struct ixgbe_adapter *adapter)
 {
 	int i, reg_idx;
 
-	for (i = 0; i < adapter->num_rx_queues; i++)
+	for (i = 0; i < adapter->num_rx_queues; i++) {
 		adapter->rx_ring[i]->reg_idx = i;
+		adapter->rx_ring[i]->netdev = adapter->netdev;
+	}
 	for (i = 0, reg_idx = 0; i < adapter->num_tx_queues; i++, reg_idx++)
 		adapter->tx_ring[i]->reg_idx = reg_idx;
 	for (i = 0; i < adapter->num_xdp_queues; i++, reg_idx++)
@@ -340,7 +352,7 @@ static bool ixgbe_set_dcb_sriov_queues(struct ixgbe_adapter *adapter)
 #ifdef IXGBE_FCOE
 	u16 fcoe_i = 0;
 #endif
-	u8 tcs = netdev_get_num_tc(adapter->netdev);
+	u8 tcs = adapter->hw_tcs;
 
 	/* verify we have DCB queueing enabled before proceeding */
 	if (tcs <= 1)
@@ -350,6 +362,9 @@ static bool ixgbe_set_dcb_sriov_queues(struct ixgbe_adapter *adapter)
 	if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED))
 		return false;
 
+	/* limit VMDq instances on the PF by number of Tx queues */
+	vmdq_i = min_t(u16, vmdq_i, MAX_TX_QUEUES / tcs);
+
 	/* Add starting offset to total pool count */
 	vmdq_i += adapter->ring_feature[RING_F_VMDQ].offset;
 
@@ -437,7 +452,7 @@ static bool ixgbe_set_dcb_queues(struct ixgbe_adapter *adapter)
 	int tcs;
 
 	/* Map queue offset and counts onto allocated tx queues */
-	tcs = netdev_get_num_tc(dev);
+	tcs = adapter->hw_tcs;
 
 	/* verify we have DCB queueing enabled before proceeding */
 	if (tcs <= 1)
@@ -512,12 +527,14 @@ static bool ixgbe_set_sriov_queues(struct ixgbe_adapter *adapter)
 #ifdef IXGBE_FCOE
 	u16 fcoe_i = 0;
 #endif
-	bool pools = (find_first_zero_bit(&adapter->fwd_bitmask, 32) > 1);
 
 	/* only proceed if SR-IOV is enabled */
 	if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED))
 		return false;
 
+	/* limit l2fwd RSS based on total Tx queue limit */
+	rss_i = min_t(u16, rss_i, MAX_TX_QUEUES / vmdq_i);
+
 	/* Add starting offset to total pool count */
 	vmdq_i += adapter->ring_feature[RING_F_VMDQ].offset;
 
@@ -525,7 +542,7 @@ static bool ixgbe_set_sriov_queues(struct ixgbe_adapter *adapter)
 	vmdq_i = min_t(u16, IXGBE_MAX_VMDQ_INDICES, vmdq_i);
 
 	/* 64 pool mode with 2 queues per pool */
-	if ((vmdq_i > 32) || (vmdq_i > 16 && pools)) {
+	if (vmdq_i > 32) {
 		vmdq_m = IXGBE_82599_VMDQ_2Q_MASK;
 		rss_m = IXGBE_RSS_2Q_MASK;
 		rss_i = min_t(u16, rss_i, 2);
@@ -602,6 +619,10 @@ static bool ixgbe_set_sriov_queues(struct ixgbe_adapter *adapter)
 	}
 
 #endif
+	/* populate TC0 for use by pool 0 */
+	netdev_set_tc_queue(adapter->netdev, 0,
+			    adapter->num_rx_queues_per_pool, 0);
+
 	return true;
 }
 
@@ -701,7 +722,7 @@ static void ixgbe_set_num_queues(struct ixgbe_adapter *adapter)
 	adapter->num_rx_queues = 1;
 	adapter->num_tx_queues = 1;
 	adapter->num_xdp_queues = 0;
-	adapter->num_rx_pools = adapter->num_rx_queues;
+	adapter->num_rx_pools = 1;
 	adapter->num_rx_queues_per_pool = 1;
 
 #ifdef CONFIG_IXGBE_DCB
@@ -834,7 +855,7 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter,
 	int node = NUMA_NO_NODE;
 	int cpu = -1;
 	int ring_count, size;
-	u8 tcs = netdev_get_num_tc(adapter->netdev);
+	u8 tcs = adapter->hw_tcs;
 
 	ring_count = txr_count + rxr_count + xdp_count;
 	size = sizeof(struct ixgbe_q_vector) +
@@ -917,11 +938,7 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter,
 
 		/* apply Tx specific ring traits */
 		ring->count = adapter->tx_ring_count;
-		if (adapter->num_rx_pools > 1)
-			ring->queue_index =
-				txr_idx % adapter->num_rx_queues_per_pool;
-		else
-			ring->queue_index = txr_idx;
+		ring->queue_index = txr_idx;
 
 		/* assign ring to adapter */
 		adapter->tx_ring[txr_idx] = ring;
@@ -991,11 +1008,7 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter,
 #endif /* IXGBE_FCOE */
 		/* apply Rx specific ring traits */
 		ring->count = adapter->rx_ring_count;
-		if (adapter->num_rx_pools > 1)
-			ring->queue_index =
-				rxr_idx % adapter->num_rx_queues_per_pool;
-		else
-			ring->queue_index = rxr_idx;
+		ring->queue_index = rxr_idx;
 
 		/* assign ring to adapter */
 		adapter->rx_ring[rxr_idx] = ring;
@@ -1171,7 +1184,7 @@ static void ixgbe_set_interrupt_capability(struct ixgbe_adapter *adapter)
 	 */
 
 	/* Disable DCB unless we only have a single traffic class */
-	if (netdev_get_num_tc(adapter->netdev) > 1) {
+	if (adapter->hw_tcs > 1) {
 		e_dev_warn("Number of DCB TCs exceeds number of available queues. Disabling DCB support.\n");
 		netdev_reset_tc(adapter->netdev);
 
@@ -1183,6 +1196,7 @@ static void ixgbe_set_interrupt_capability(struct ixgbe_adapter *adapter)
 		adapter->dcb_cfg.pfc_mode_enable = false;
 	}
 
+	adapter->hw_tcs = 0;
 	adapter->dcb_cfg.num_tcs.pg_tcs = 1;
 	adapter->dcb_cfg.num_tcs.pfc_tcs = 1;
 
@@ -1268,7 +1282,7 @@ void ixgbe_clear_interrupt_scheme(struct ixgbe_adapter *adapter)
 }
 
 void ixgbe_tx_ctxtdesc(struct ixgbe_ring *tx_ring, u32 vlan_macip_lens,
-		       u32 fcoe_sof_eof, u32 type_tucmd, u32 mss_l4len_idx)
+		       u32 fceof_saidx, u32 type_tucmd, u32 mss_l4len_idx)
 {
 	struct ixgbe_adv_tx_context_desc *context_desc;
 	u16 i = tx_ring->next_to_use;
@@ -1282,7 +1296,7 @@ void ixgbe_tx_ctxtdesc(struct ixgbe_ring *tx_ring, u32 vlan_macip_lens,
 	type_tucmd |= IXGBE_TXD_CMD_DEXT | IXGBE_ADVTXD_DTYP_CTXT;
 
 	context_desc->vlan_macip_lens	= cpu_to_le32(vlan_macip_lens);
-	context_desc->seqnum_seed	= cpu_to_le32(fcoe_sof_eof);
+	context_desc->fceof_saidx	= cpu_to_le32(fceof_saidx);
 	context_desc->type_tucmd_mlhl	= cpu_to_le32(type_tucmd);
 	context_desc->mss_l4len_idx	= cpu_to_le32(mss_l4len_idx);
 }