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, 106 insertions, 48 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 3409d86..363d8dc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -190,6 +190,63 @@ int mlx5e_attr_get(struct net_device *dev, struct switchdev_attr *attr)
 	return 0;
 }
 
+static void mlx5e_sqs2vport_stop(struct mlx5_eswitch *esw,
+				 struct mlx5_eswitch_rep *rep)
+{
+	struct mlx5e_rep_sq *rep_sq, *tmp;
+	struct mlx5e_rep_priv *rpriv;
+
+	if (esw->mode != SRIOV_OFFLOADS)
+		return;
+
+	rpriv = mlx5e_rep_to_rep_priv(rep);
+	list_for_each_entry_safe(rep_sq, tmp, &rpriv->vport_sqs_list, list) {
+		mlx5_eswitch_del_send_to_vport_rule(rep_sq->send_to_vport_rule);
+		list_del(&rep_sq->list);
+		kfree(rep_sq);
+	}
+}
+
+static int mlx5e_sqs2vport_start(struct mlx5_eswitch *esw,
+				 struct mlx5_eswitch_rep *rep,
+				 u16 *sqns_array, int sqns_num)
+{
+	struct mlx5_flow_handle *flow_rule;
+	struct mlx5e_rep_priv *rpriv;
+	struct mlx5e_rep_sq *rep_sq;
+	int err;
+	int i;
+
+	if (esw->mode != SRIOV_OFFLOADS)
+		return 0;
+
+	rpriv = mlx5e_rep_to_rep_priv(rep);
+	for (i = 0; i < sqns_num; i++) {
+		rep_sq = kzalloc(sizeof(*rep_sq), GFP_KERNEL);
+		if (!rep_sq) {
+			err = -ENOMEM;
+			goto out_err;
+		}
+
+		/* Add re-inject rule to the PF/representor sqs */
+		flow_rule = mlx5_eswitch_add_send_to_vport_rule(esw,
+								rep->vport,
+								sqns_array[i]);
+		if (IS_ERR(flow_rule)) {
+			err = PTR_ERR(flow_rule);
+			kfree(rep_sq);
+			goto out_err;
+		}
+		rep_sq->send_to_vport_rule = flow_rule;
+		list_add(&rep_sq->list, &rpriv->vport_sqs_list);
+	}
+	return 0;
+
+out_err:
+	mlx5e_sqs2vport_stop(esw, rep);
+	return err;
+}
+
 int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
@@ -210,7 +267,7 @@ int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv)
 			sqs[num_sqs++] = c->sq[tc].sqn;
 	}
 
-	err = mlx5_eswitch_sqs2vport_start(esw, rep, sqs, num_sqs);
+	err = mlx5e_sqs2vport_start(esw, rep, sqs, num_sqs);
 	kfree(sqs);
 
 out:
@@ -225,7 +282,7 @@ void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv)
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	struct mlx5_eswitch_rep *rep = rpriv->rep;
 
-	mlx5_eswitch_sqs2vport_stop(esw, rep);
+	mlx5e_sqs2vport_stop(esw, rep);
 }
 
 static void mlx5e_rep_neigh_update_init_interval(struct mlx5e_rep_priv *rpriv)
@@ -238,7 +295,7 @@ static void mlx5e_rep_neigh_update_init_interval(struct mlx5e_rep_priv *rpriv)
 #endif
 	unsigned long ipv4_interval = NEIGH_VAR(&arp_tbl.parms,
 						DELAY_PROBE_TIME);
-	struct net_device *netdev = rpriv->rep->netdev;
+	struct net_device *netdev = rpriv->netdev;
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
 	rpriv->neigh_update.min_interval = min_t(unsigned long, ipv6_interval, ipv4_interval);
@@ -259,7 +316,7 @@ static void mlx5e_rep_neigh_stats_work(struct work_struct *work)
 {
 	struct mlx5e_rep_priv *rpriv = container_of(work, struct mlx5e_rep_priv,
 						    neigh_update.neigh_stats_work.work);
-	struct net_device *netdev = rpriv->rep->netdev;
+	struct net_device *netdev = rpriv->netdev;
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5e_neigh_hash_entry *nhe;
 
@@ -355,7 +412,7 @@ static int mlx5e_rep_netevent_event(struct notifier_block *nb,
 	struct mlx5e_rep_priv *rpriv = container_of(nb, struct mlx5e_rep_priv,
 						    neigh_update.netevent_nb);
 	struct mlx5e_neigh_update_table *neigh_update = &rpriv->neigh_update;
-	struct net_device *netdev = rpriv->rep->netdev;
+	struct net_device *netdev = rpriv->netdev;
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5e_neigh_hash_entry *nhe = NULL;
 	struct mlx5e_neigh m_neigh = {};
@@ -483,7 +540,7 @@ out_err:
 static void mlx5e_rep_neigh_cleanup(struct mlx5e_rep_priv *rpriv)
 {
 	struct mlx5e_neigh_update_table *neigh_update = &rpriv->neigh_update;
-	struct mlx5e_priv *priv = netdev_priv(rpriv->rep->netdev);
+	struct mlx5e_priv *priv = netdev_priv(rpriv->netdev);
 
 	unregister_netevent_notifier(&neigh_update->netevent_nb);
 
@@ -662,9 +719,6 @@ static int
 mlx5e_rep_setup_tc_cls_flower(struct mlx5e_priv *priv,
 			      struct tc_cls_flower_offload *cls_flower)
 {
-	if (cls_flower->common.chain_index)
-		return -EOPNOTSUPP;
-
 	switch (cls_flower->command) {
 	case TC_CLSFLOWER_REPLACE:
 		return mlx5e_configure_flower(priv, cls_flower);
@@ -682,7 +736,7 @@ static int mlx5e_rep_setup_tc_cb(enum tc_setup_type type, void *type_data,
 {
 	struct mlx5e_priv *priv = cb_priv;
 
-	if (!tc_can_offload(priv->netdev))
+	if (!tc_cls_can_offload_and_chain0(priv->netdev, type_data))
 		return -EOPNOTSUPP;
 
 	switch (type) {
@@ -827,7 +881,7 @@ static void mlx5e_build_rep_params(struct mlx5_core_dev *mdev,
 	params->rq_wq_type  = MLX5_WQ_TYPE_LINKED_LIST;
 	params->log_rq_size = MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE;
 
-	params->rx_am_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
+	params->rx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
 	mlx5e_set_rx_cq_mode_params(params, cq_period_mode);
 
 	params->tx_max_inline         = mlx5e_get_max_inline_cap(mdev);
@@ -906,7 +960,7 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv)
 		err = PTR_ERR(flow_rule);
 		goto err_destroy_direct_tirs;
 	}
-	rep->vport_rx_rule = flow_rule;
+	rpriv->vport_rx_rule = flow_rule;
 
 	err = mlx5e_tc_init(priv);
 	if (err)
@@ -915,7 +969,7 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv)
 	return 0;
 
 err_del_flow_rule:
-	mlx5_del_flow_rules(rep->vport_rx_rule);
+	mlx5_del_flow_rules(rpriv->vport_rx_rule);
 err_destroy_direct_tirs:
 	mlx5e_destroy_direct_tirs(priv);
 err_destroy_direct_rqts:
@@ -926,10 +980,9 @@ err_destroy_direct_rqts:
 static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv)
 {
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
-	struct mlx5_eswitch_rep *rep = rpriv->rep;
 
 	mlx5e_tc_cleanup(priv);
-	mlx5_del_flow_rules(rep->vport_rx_rule);
+	mlx5_del_flow_rules(rpriv->vport_rx_rule);
 	mlx5e_destroy_direct_tirs(priv);
 	mlx5e_destroy_direct_rqts(priv);
 }
@@ -969,10 +1022,10 @@ static const struct mlx5e_profile mlx5e_rep_profile = {
 /* e-Switch vport representors */
 
 static int
-mlx5e_nic_rep_load(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep)
+mlx5e_nic_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 {
-	struct mlx5e_priv *priv = netdev_priv(rep->netdev);
-	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5e_rep_priv *rpriv = mlx5e_rep_to_rep_priv(rep);
+	struct mlx5e_priv *priv = netdev_priv(rpriv->netdev);
 
 	int err;
 
@@ -994,10 +1047,10 @@ err_remove_sqs:
 }
 
 static void
-mlx5e_nic_rep_unload(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep)
+mlx5e_nic_rep_unload(struct mlx5_eswitch_rep *rep)
 {
-	struct mlx5e_priv *priv = netdev_priv(rep->netdev);
-	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5e_rep_priv *rpriv = mlx5e_rep_to_rep_priv(rep);
+	struct mlx5e_priv *priv = netdev_priv(rpriv->netdev);
 
 	if (test_bit(MLX5E_STATE_OPENED, &priv->state))
 		mlx5e_remove_sqs_fwd_rules(priv);
@@ -1010,8 +1063,9 @@ mlx5e_nic_rep_unload(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep)
 }
 
 static int
-mlx5e_vport_rep_load(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep)
+mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 {
+	struct mlx5e_rep_priv *uplink_rpriv;
 	struct mlx5e_rep_priv *rpriv;
 	struct net_device *netdev;
 	struct mlx5e_priv *upriv;
@@ -1021,7 +1075,7 @@ mlx5e_vport_rep_load(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep)
 	if (!rpriv)
 		return -ENOMEM;
 
-	netdev = mlx5e_create_netdev(esw->dev, &mlx5e_rep_profile, rpriv);
+	netdev = mlx5e_create_netdev(dev, &mlx5e_rep_profile, rpriv);
 	if (!netdev) {
 		pr_warn("Failed to create representor netdev for vport %d\n",
 			rep->vport);
@@ -1029,8 +1083,10 @@ mlx5e_vport_rep_load(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep)
 		return -EINVAL;
 	}
 
-	rep->netdev = netdev;
+	rpriv->netdev = netdev;
 	rpriv->rep = rep;
+	rep->rep_if[REP_ETH].priv = rpriv;
+	INIT_LIST_HEAD(&rpriv->vport_sqs_list);
 
 	err = mlx5e_attach_netdev(netdev_priv(netdev));
 	if (err) {
@@ -1046,7 +1102,8 @@ mlx5e_vport_rep_load(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep)
 		goto err_detach_netdev;
 	}
 
-	upriv = netdev_priv(mlx5_eswitch_get_uplink_netdev(esw));
+	uplink_rpriv = mlx5_eswitch_get_uplink_priv(dev->priv.eswitch, REP_ETH);
+	upriv = netdev_priv(uplink_rpriv->netdev);
 	err = tc_setup_cb_egdev_register(netdev, mlx5e_setup_tc_block_cb,
 					 upriv);
 	if (err)
@@ -1078,16 +1135,19 @@ err_destroy_netdev:
 }
 
 static void
-mlx5e_vport_rep_unload(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep)
+mlx5e_vport_rep_unload(struct mlx5_eswitch_rep *rep)
 {
-	struct net_device *netdev = rep->netdev;
+	struct mlx5e_rep_priv *rpriv = mlx5e_rep_to_rep_priv(rep);
+	struct net_device *netdev = rpriv->netdev;
 	struct mlx5e_priv *priv = netdev_priv(netdev);
-	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5e_rep_priv *uplink_rpriv;
 	void *ppriv = priv->ppriv;
 	struct mlx5e_priv *upriv;
 
-	unregister_netdev(rep->netdev);
-	upriv = netdev_priv(mlx5_eswitch_get_uplink_netdev(esw));
+	unregister_netdev(netdev);
+	uplink_rpriv = mlx5_eswitch_get_uplink_priv(priv->mdev->priv.eswitch,
+						    REP_ETH);
+	upriv = netdev_priv(uplink_rpriv->netdev);
 	tc_setup_cb_egdev_unregister(netdev, mlx5e_setup_tc_block_cb,
 				     upriv);
 	mlx5e_rep_neigh_cleanup(rpriv);
@@ -1102,18 +1162,13 @@ static void mlx5e_rep_register_vf_vports(struct mlx5e_priv *priv)
 	struct mlx5_eswitch *esw   = mdev->priv.eswitch;
 	int total_vfs = MLX5_TOTAL_VPORTS(mdev);
 	int vport;
-	u8 mac[ETH_ALEN];
-
-	mlx5_query_nic_vport_mac_address(mdev, 0, mac);
 
 	for (vport = 1; vport < total_vfs; vport++) {
-		struct mlx5_eswitch_rep rep;
+		struct mlx5_eswitch_rep_if rep_if = {};
 
-		rep.load = mlx5e_vport_rep_load;
-		rep.unload = mlx5e_vport_rep_unload;
-		rep.vport = vport;
-		ether_addr_copy(rep.hw_id, mac);
-		mlx5_eswitch_register_vport_rep(esw, vport, &rep);
+		rep_if.load = mlx5e_vport_rep_load;
+		rep_if.unload = mlx5e_vport_rep_unload;
+		mlx5_eswitch_register_vport_rep(esw, vport, &rep_if, REP_ETH);
 	}
 }
 
@@ -1125,21 +1180,24 @@ static void mlx5e_rep_unregister_vf_vports(struct mlx5e_priv *priv)
 	int vport;
 
 	for (vport = 1; vport < total_vfs; vport++)
-		mlx5_eswitch_unregister_vport_rep(esw, vport);
+		mlx5_eswitch_unregister_vport_rep(esw, vport, REP_ETH);
 }
 
 void mlx5e_register_vport_reps(struct mlx5e_priv *priv)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5_eswitch *esw   = mdev->priv.eswitch;
-	struct mlx5_eswitch_rep rep;
+	struct mlx5_eswitch_rep_if rep_if;
+	struct mlx5e_rep_priv *rpriv;
+
+	rpriv = priv->ppriv;
+	rpriv->netdev = priv->netdev;
 
-	mlx5_query_nic_vport_mac_address(mdev, 0, rep.hw_id);
-	rep.load = mlx5e_nic_rep_load;
-	rep.unload = mlx5e_nic_rep_unload;
-	rep.vport = FDB_UPLINK_VPORT;
-	rep.netdev = priv->netdev;
-	mlx5_eswitch_register_vport_rep(esw, 0, &rep); /* UPLINK PF vport*/
+	rep_if.load = mlx5e_nic_rep_load;
+	rep_if.unload = mlx5e_nic_rep_unload;
+	rep_if.priv = rpriv;
+	INIT_LIST_HEAD(&rpriv->vport_sqs_list);
+	mlx5_eswitch_register_vport_rep(esw, 0, &rep_if, REP_ETH); /* UPLINK PF vport*/
 
 	mlx5e_rep_register_vf_vports(priv); /* VFs vports */
 }
@@ -1150,7 +1208,7 @@ void mlx5e_unregister_vport_reps(struct mlx5e_priv *priv)
 	struct mlx5_eswitch *esw   = mdev->priv.eswitch;
 
 	mlx5e_rep_unregister_vf_vports(priv); /* VFs vports */
-	mlx5_eswitch_unregister_vport_rep(esw, 0); /* UPLINK PF*/
+	mlx5_eswitch_unregister_vport_rep(esw, 0, REP_ETH); /* UPLINK PF*/
 }
 
 void *mlx5e_alloc_nic_rep_priv(struct mlx5_core_dev *mdev)