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

Pull networking updates from David Miller:

 1) Unified UDP encapsulation offload methods for drivers, from
    Alexander Duyck.

 2) Make DSA binding more sane, from Andrew Lunn.

 3) Support QCA9888 chips in ath10k, from Anilkumar Kolli.

 4) Several workqueue usage cleanups, from Bhaktipriya Shridhar.

 5) Add XDP (eXpress Data Path), essentially running BPF programs on RX
    packets as soon as the device sees them, with the option to mirror
    the packet on TX via the same interface.  From Brenden Blanco and
    others.

 6) Allow qdisc/class stats dumps to run lockless, from Eric Dumazet.

 7) Add VLAN support to b53 and bcm_sf2, from Florian Fainelli.

 8) Simplify netlink conntrack entry layout, from Florian Westphal.

 9) Add ipv4 forwarding support to mlxsw spectrum driver, from Ido
    Schimmel, Yotam Gigi, and Jiri Pirko.

10) Add SKB array infrastructure and convert tun and macvtap over to it.
    From Michael S Tsirkin and Jason Wang.

11) Support qdisc packet injection in pktgen, from John Fastabend.

12) Add neighbour monitoring framework to TIPC, from Jon Paul Maloy.

13) Add NV congestion control support to TCP, from Lawrence Brakmo.

14) Add GSO support to SCTP, from Marcelo Ricardo Leitner.

15) Allow GRO and RPS to function on macsec devices, from Paolo Abeni.

16) Support MPLS over IPV4, from Simon Horman.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1622 commits)
  xgene: Fix build warning with ACPI disabled.
  be2net: perform temperature query in adapter regardless of its interface state
  l2tp: Correctly return -EBADF from pppol2tp_getname.
  net/mlx5_core/health: Remove deprecated create_singlethread_workqueue
  net: ipmr/ip6mr: update lastuse on entry change
  macsec: ensure rx_sa is set when validation is disabled
  tipc: dump monitor attributes
  tipc: add a function to get the bearer name
  tipc: get monitor threshold for the cluster
  tipc: make cluster size threshold for monitoring configurable
  tipc: introduce constants for tipc address validation
  net: neigh: disallow transition to NUD_STALE if lladdr is unchanged in neigh_update()
  MAINTAINERS: xgene: Add driver and documentation path
  Documentation: dtb: xgene: Add MDIO node
  dtb: xgene: Add MDIO node
  drivers: net: xgene: ethtool: Use phy_ethtool_gset and sset
  drivers: net: xgene: Use exported functions
  drivers: net: xgene: Enable MDIO driver
  drivers: net: xgene: Add backward compatibility
  drivers: net: phy: xgene: Add MDIO driver
  ...

1 files changed, 172 insertions, 23 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 8359e9e51b3b..4198e9bf89d0 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -31,6 +31,7 @@
  *
  */
 
+#include <linux/bpf.h>
 #include <linux/etherdevice.h>
 #include <linux/tcp.h>
 #include <linux/if_vlan.h>
@@ -67,6 +68,17 @@ int mlx4_en_setup_tc(struct net_device *dev, u8 up)
 		offset += priv->num_tx_rings_p_up;
 	}
 
+#ifdef CONFIG_MLX4_EN_DCB
+	if (!mlx4_is_slave(priv->mdev->dev)) {
+		if (up) {
+			priv->flags |= MLX4_EN_FLAG_DCB_ENABLED;
+		} else {
+			priv->flags &= ~MLX4_EN_FLAG_DCB_ENABLED;
+			priv->cee_params.dcb_cfg.pfc_state = false;
+		}
+	}
+#endif /* CONFIG_MLX4_EN_DCB */
+
 	return 0;
 }
 
@@ -1201,8 +1213,8 @@ static void mlx4_en_netpoll(struct net_device *dev)
 	struct mlx4_en_cq *cq;
 	int i;
 
-	for (i = 0; i < priv->rx_ring_num; i++) {
-		cq = priv->rx_cq[i];
+	for (i = 0; i < priv->tx_ring_num; i++) {
+		cq = priv->tx_cq[i];
 		napi_schedule(&cq->napi);
 	}
 }
@@ -1510,6 +1522,24 @@ static void mlx4_en_free_affinity_hint(struct mlx4_en_priv *priv, int ring_idx)
 	free_cpumask_var(priv->rx_ring[ring_idx]->affinity_mask);
 }
 
+static void mlx4_en_init_recycle_ring(struct mlx4_en_priv *priv,
+				      int tx_ring_idx)
+{
+	struct mlx4_en_tx_ring *tx_ring = priv->tx_ring[tx_ring_idx];
+	int rr_index;
+
+	rr_index = (priv->xdp_ring_num - priv->tx_ring_num) + tx_ring_idx;
+	if (rr_index >= 0) {
+		tx_ring->free_tx_desc = mlx4_en_recycle_tx_desc;
+		tx_ring->recycle_ring = priv->rx_ring[rr_index];
+		en_dbg(DRV, priv,
+		       "Set tx_ring[%d]->recycle_ring = rx_ring[%d]\n",
+		       tx_ring_idx, rr_index);
+	} else {
+		tx_ring->recycle_ring = NULL;
+	}
+}
+
 int mlx4_en_start_port(struct net_device *dev)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
@@ -1632,6 +1662,8 @@ int mlx4_en_start_port(struct net_device *dev)
 		}
 		tx_ring->tx_queue = netdev_get_tx_queue(dev, i);
 
+		mlx4_en_init_recycle_ring(priv, i);
+
 		/* Arm CQ for TX completions */
 		mlx4_en_arm_cq(priv, cq);
 
@@ -1696,10 +1728,9 @@ int mlx4_en_start_port(struct net_device *dev)
 	/* Schedule multicast task to populate multicast list */
 	queue_work(mdev->workqueue, &priv->rx_mode_task);
 
-#ifdef CONFIG_MLX4_EN_VXLAN
 	if (priv->mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)
-		vxlan_get_rx_port(dev);
-#endif
+		udp_tunnel_get_rx_info(dev);
+
 	priv->port_up = true;
 	netif_tx_start_all_queues(dev);
 	netif_device_attach(dev);
@@ -2177,6 +2208,11 @@ static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu)
 		en_err(priv, "Bad MTU size:%d.\n", new_mtu);
 		return -EPERM;
 	}
+	if (priv->xdp_ring_num && MLX4_EN_EFF_MTU(new_mtu) > FRAG_SZ0) {
+		en_err(priv, "MTU size:%d requires frags but XDP running\n",
+		       new_mtu);
+		return -EOPNOTSUPP;
+	}
 	dev->mtu = new_mtu;
 
 	if (netif_running(dev)) {
@@ -2434,7 +2470,6 @@ static int mlx4_en_get_phys_port_id(struct net_device *dev,
 	return 0;
 }
 
-#ifdef CONFIG_MLX4_EN_VXLAN
 static void mlx4_en_add_vxlan_offloads(struct work_struct *work)
 {
 	int ret;
@@ -2484,15 +2519,19 @@ static void mlx4_en_del_vxlan_offloads(struct work_struct *work)
 }
 
 static void mlx4_en_add_vxlan_port(struct  net_device *dev,
-				   sa_family_t sa_family, __be16 port)
+				   struct udp_tunnel_info *ti)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
+	__be16 port = ti->port;
 	__be16 current_port;
 
-	if (priv->mdev->dev->caps.tunnel_offload_mode != MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)
+	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
+		return;
+
+	if (ti->sa_family != AF_INET)
 		return;
 
-	if (sa_family == AF_INET6)
+	if (priv->mdev->dev->caps.tunnel_offload_mode != MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)
 		return;
 
 	current_port = priv->vxlan_port;
@@ -2507,15 +2546,19 @@ static void mlx4_en_add_vxlan_port(struct  net_device *dev,
 }
 
 static void mlx4_en_del_vxlan_port(struct  net_device *dev,
-				   sa_family_t sa_family, __be16 port)
+				   struct udp_tunnel_info *ti)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
+	__be16 port = ti->port;
 	__be16 current_port;
 
-	if (priv->mdev->dev->caps.tunnel_offload_mode != MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)
+	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
 		return;
 
-	if (sa_family == AF_INET6)
+	if (ti->sa_family != AF_INET)
+		return;
+
+	if (priv->mdev->dev->caps.tunnel_offload_mode != MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)
 		return;
 
 	current_port = priv->vxlan_port;
@@ -2550,7 +2593,6 @@ static netdev_features_t mlx4_en_features_check(struct sk_buff *skb,
 
 	return features;
 }
-#endif
 
 static int mlx4_en_set_tx_maxrate(struct net_device *dev, int queue_index, u32 maxrate)
 {
@@ -2579,6 +2621,103 @@ static int mlx4_en_set_tx_maxrate(struct net_device *dev, int queue_index, u32 m
 	return err;
 }
 
+static int mlx4_xdp_set(struct net_device *dev, struct bpf_prog *prog)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	struct mlx4_en_dev *mdev = priv->mdev;
+	struct bpf_prog *old_prog;
+	int xdp_ring_num;
+	int port_up = 0;
+	int err;
+	int i;
+
+	xdp_ring_num = prog ? ALIGN(priv->rx_ring_num, MLX4_EN_NUM_UP) : 0;
+
+	/* No need to reconfigure buffers when simply swapping the
+	 * program for a new one.
+	 */
+	if (priv->xdp_ring_num == xdp_ring_num) {
+		if (prog) {
+			prog = bpf_prog_add(prog, priv->rx_ring_num - 1);
+			if (IS_ERR(prog))
+				return PTR_ERR(prog);
+		}
+		for (i = 0; i < priv->rx_ring_num; i++) {
+			/* This xchg is paired with READ_ONCE in the fastpath */
+			old_prog = xchg(&priv->rx_ring[i]->xdp_prog, prog);
+			if (old_prog)
+				bpf_prog_put(old_prog);
+		}
+		return 0;
+	}
+
+	if (priv->num_frags > 1) {
+		en_err(priv, "Cannot set XDP if MTU requires multiple frags\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (priv->tx_ring_num < xdp_ring_num + MLX4_EN_NUM_UP) {
+		en_err(priv,
+		       "Minimum %d tx channels required to run XDP\n",
+		       (xdp_ring_num + MLX4_EN_NUM_UP) / MLX4_EN_NUM_UP);
+		return -EINVAL;
+	}
+
+	if (prog) {
+		prog = bpf_prog_add(prog, priv->rx_ring_num - 1);
+		if (IS_ERR(prog))
+			return PTR_ERR(prog);
+	}
+
+	mutex_lock(&mdev->state_lock);
+	if (priv->port_up) {
+		port_up = 1;
+		mlx4_en_stop_port(dev, 1);
+	}
+
+	priv->xdp_ring_num = xdp_ring_num;
+	netif_set_real_num_tx_queues(dev, priv->tx_ring_num -
+							priv->xdp_ring_num);
+
+	for (i = 0; i < priv->rx_ring_num; i++) {
+		old_prog = xchg(&priv->rx_ring[i]->xdp_prog, prog);
+		if (old_prog)
+			bpf_prog_put(old_prog);
+	}
+
+	if (port_up) {
+		err = mlx4_en_start_port(dev);
+		if (err) {
+			en_err(priv, "Failed starting port %d for XDP change\n",
+			       priv->port);
+			queue_work(mdev->workqueue, &priv->watchdog_task);
+		}
+	}
+
+	mutex_unlock(&mdev->state_lock);
+	return 0;
+}
+
+static bool mlx4_xdp_attached(struct net_device *dev)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+
+	return !!priv->xdp_ring_num;
+}
+
+static int mlx4_xdp(struct net_device *dev, struct netdev_xdp *xdp)
+{
+	switch (xdp->command) {
+	case XDP_SETUP_PROG:
+		return mlx4_xdp_set(dev, xdp->prog);
+	case XDP_QUERY_PROG:
+		xdp->prog_attached = mlx4_xdp_attached(dev);
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+
 static const struct net_device_ops mlx4_netdev_ops = {
 	.ndo_open		= mlx4_en_open,
 	.ndo_stop		= mlx4_en_close,
@@ -2603,12 +2742,11 @@ static const struct net_device_ops mlx4_netdev_ops = {
 	.ndo_rx_flow_steer	= mlx4_en_filter_rfs,
 #endif
 	.ndo_get_phys_port_id	= mlx4_en_get_phys_port_id,
-#ifdef CONFIG_MLX4_EN_VXLAN
-	.ndo_add_vxlan_port	= mlx4_en_add_vxlan_port,
-	.ndo_del_vxlan_port	= mlx4_en_del_vxlan_port,
+	.ndo_udp_tunnel_add	= mlx4_en_add_vxlan_port,
+	.ndo_udp_tunnel_del	= mlx4_en_del_vxlan_port,
 	.ndo_features_check	= mlx4_en_features_check,
-#endif
 	.ndo_set_tx_maxrate	= mlx4_en_set_tx_maxrate,
+	.ndo_xdp		= mlx4_xdp,
 };
 
 static const struct net_device_ops mlx4_netdev_ops_master = {
@@ -2641,12 +2779,11 @@ static const struct net_device_ops mlx4_netdev_ops_master = {
 	.ndo_rx_flow_steer	= mlx4_en_filter_rfs,
 #endif
 	.ndo_get_phys_port_id	= mlx4_en_get_phys_port_id,
-#ifdef CONFIG_MLX4_EN_VXLAN
-	.ndo_add_vxlan_port	= mlx4_en_add_vxlan_port,
-	.ndo_del_vxlan_port	= mlx4_en_del_vxlan_port,
+	.ndo_udp_tunnel_add	= mlx4_en_add_vxlan_port,
+	.ndo_udp_tunnel_del	= mlx4_en_del_vxlan_port,
 	.ndo_features_check	= mlx4_en_features_check,
-#endif
 	.ndo_set_tx_maxrate	= mlx4_en_set_tx_maxrate,
+	.ndo_xdp		= mlx4_xdp,
 };
 
 struct mlx4_en_bond {
@@ -2911,6 +3048,9 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	struct mlx4_en_priv *priv;
 	int i;
 	int err;
+#ifdef CONFIG_MLX4_EN_DCB
+	struct tc_configuration *tc;
+#endif
 
 	dev = alloc_etherdev_mqs(sizeof(struct mlx4_en_priv),
 				 MAX_TX_RINGS, MAX_RX_RINGS);
@@ -2936,10 +3076,8 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	INIT_WORK(&priv->linkstate_task, mlx4_en_linkstate);
 	INIT_DELAYED_WORK(&priv->stats_task, mlx4_en_do_get_stats);
 	INIT_DELAYED_WORK(&priv->service_task, mlx4_en_service_task);
-#ifdef CONFIG_MLX4_EN_VXLAN
 	INIT_WORK(&priv->vxlan_add_task, mlx4_en_add_vxlan_offloads);
 	INIT_WORK(&priv->vxlan_del_task, mlx4_en_del_vxlan_offloads);
-#endif
 #ifdef CONFIG_RFS_ACCEL
 	INIT_LIST_HEAD(&priv->filters);
 	spin_lock_init(&priv->filters_lock);
@@ -2979,6 +3117,17 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	priv->msg_enable = MLX4_EN_MSG_LEVEL;
 #ifdef CONFIG_MLX4_EN_DCB
 	if (!mlx4_is_slave(priv->mdev->dev)) {
+		priv->cee_params.dcbx_cap = DCB_CAP_DCBX_VER_CEE |
+					    DCB_CAP_DCBX_HOST |
+					    DCB_CAP_DCBX_VER_IEEE;
+		priv->flags |= MLX4_EN_DCB_ENABLED;
+		priv->cee_params.dcb_cfg.pfc_state = false;
+
+		for (i = 0; i < MLX4_EN_NUM_UP; i++) {
+			tc = &priv->cee_params.dcb_cfg.tc_config[i];
+			tc->dcb_pfc = pfc_disabled;
+		}
+
 		if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_ETS_CFG) {
 			dev->dcbnl_ops = &mlx4_en_dcbnl_ops;
 		} else {