Merge branch 'mlx5-fixes'

Saeed Mahameed says:

====================
Mellanox mlx5 fixes and cleanups 2017-01-10

This series includes some mlx5e general cleanups from Daniel, Gil, Hadar
and myself.
Also it includes some critical mlx5e TC offloads fixes from Or Gerlitz.

For -stable:
 - net/mlx5e: Remove WARN_ONCE from adaptive moderation code

   Although this fix doesn't affect any functionality, I thought it is
   better to clean this -WARN_ONCE- up for -stable in case someone hits
   such corner case.

Please apply and let me know if there's any problem.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 75 insertions, 44 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 1236b27b1493..2b7dd315020c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3675,14 +3675,8 @@ static void mlx5e_nic_init(struct mlx5_core_dev *mdev,
 
 static void mlx5e_nic_cleanup(struct mlx5e_priv *priv)
 {
-	struct mlx5_core_dev *mdev = priv->mdev;
-	struct mlx5_eswitch *esw = mdev->priv.eswitch;
-
 	mlx5e_vxlan_cleanup(priv);
 
-	if (MLX5_CAP_GEN(mdev, vport_group_manager))
-		mlx5_eswitch_unregister_vport_rep(esw, 0);
-
 	if (priv->xdp_prog)
 		bpf_prog_put(priv->xdp_prog);
 }
@@ -3807,9 +3801,14 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 
 static void mlx5e_nic_disable(struct mlx5e_priv *priv)
 {
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5_eswitch *esw = mdev->priv.eswitch;
+
 	queue_work(priv->wq, &priv->set_rx_mode_work);
+	if (MLX5_CAP_GEN(mdev, vport_group_manager))
+		mlx5_eswitch_unregister_vport_rep(esw, 0);
 	mlx5e_disable_async_events(priv);
-	mlx5_lag_remove(priv->mdev);
+	mlx5_lag_remove(mdev);
 }
 
 static const struct mlx5e_profile mlx5e_nic_profile = {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c
index 1fffe48a93cc..cbfac06b7ffd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c
@@ -109,7 +109,6 @@ static bool mlx5e_am_on_top(struct mlx5e_rx_am *am)
 	switch (am->tune_state) {
 	case MLX5E_AM_PARKING_ON_TOP:
 	case MLX5E_AM_PARKING_TIRED:
-		WARN_ONCE(true, "mlx5e_am_on_top: PARKING\n");
 		return true;
 	case MLX5E_AM_GOING_RIGHT:
 		return (am->steps_left > 1) && (am->steps_right == 1);
@@ -123,7 +122,6 @@ static void mlx5e_am_turn(struct mlx5e_rx_am *am)
 	switch (am->tune_state) {
 	case MLX5E_AM_PARKING_ON_TOP:
 	case MLX5E_AM_PARKING_TIRED:
-		WARN_ONCE(true, "mlx5e_am_turn: PARKING\n");
 		break;
 	case MLX5E_AM_GOING_RIGHT:
 		am->tune_state = MLX5E_AM_GOING_LEFT;
@@ -144,7 +142,6 @@ static int mlx5e_am_step(struct mlx5e_rx_am *am)
 	switch (am->tune_state) {
 	case MLX5E_AM_PARKING_ON_TOP:
 	case MLX5E_AM_PARKING_TIRED:
-		WARN_ONCE(true, "mlx5e_am_step: PARKING\n");
 		break;
 	case MLX5E_AM_GOING_RIGHT:
 		if (am->profile_ix == (MLX5E_PARAMS_AM_NUM_PROFILES - 1))
@@ -282,10 +279,8 @@ static void mlx5e_am_calc_stats(struct mlx5e_rx_am_sample *start,
 	u32 delta_us = ktime_us_delta(end->time, start->time);
 	unsigned int npkts = end->pkt_ctr - start->pkt_ctr;
 
-	if (!delta_us) {
-		WARN_ONCE(true, "mlx5e_am_calc_stats: delta_us=0\n");
+	if (!delta_us)
 		return;
-	}
 
 	curr_stats->ppms =            (npkts * USEC_PER_MSEC) / delta_us;
 	curr_stats->epms = (MLX5E_AM_NEVENTS * USEC_PER_MSEC) / delta_us;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index f8829b517156..118cea5e5489 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -161,15 +161,21 @@ static void mlx5e_detach_encap(struct mlx5e_priv *priv,
 	}
 }
 
+/* we get here also when setting rule to the FW failed, etc. It means that the
+ * flow rule itself might not exist, but some offloading related to the actions
+ * should be cleaned.
+ */
 static void mlx5e_tc_del_flow(struct mlx5e_priv *priv,
 			      struct mlx5e_tc_flow *flow)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	struct mlx5_fc *counter = NULL;
 
-	counter = mlx5_flow_rule_counter(flow->rule);
-
-	mlx5_del_flow_rules(flow->rule);
+	if (!IS_ERR(flow->rule)) {
+		counter = mlx5_flow_rule_counter(flow->rule);
+		mlx5_del_flow_rules(flow->rule);
+		mlx5_fc_destroy(priv->mdev, counter);
+	}
 
 	if (esw && esw->mode == SRIOV_OFFLOADS) {
 		mlx5_eswitch_del_vlan_action(esw, flow->attr);
@@ -177,8 +183,6 @@ static void mlx5e_tc_del_flow(struct mlx5e_priv *priv,
 			mlx5e_detach_encap(priv, flow);
 	}
 
-	mlx5_fc_destroy(priv->mdev, counter);
-
 	if (!mlx5e_tc_num_filters(priv) && (priv->fs.tc.t)) {
 		mlx5_destroy_flow_table(priv->fs.tc.t);
 		priv->fs.tc.t = NULL;
@@ -225,6 +229,11 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
 	void *headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
 				       outer_headers);
 
+	struct flow_dissector_key_control *enc_control =
+		skb_flow_dissector_target(f->dissector,
+					  FLOW_DISSECTOR_KEY_ENC_CONTROL,
+					  f->key);
+
 	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_PORTS)) {
 		struct flow_dissector_key_ports *key =
 			skb_flow_dissector_target(f->dissector,
@@ -237,28 +246,34 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
 
 		/* Full udp dst port must be given */
 		if (memchr_inv(&mask->dst, 0xff, sizeof(mask->dst)))
-			return -EOPNOTSUPP;
-
-		/* udp src port isn't supported */
-		if (memchr_inv(&mask->src, 0, sizeof(mask->src)))
-			return -EOPNOTSUPP;
+			goto vxlan_match_offload_err;
 
 		if (mlx5e_vxlan_lookup_port(priv, be16_to_cpu(key->dst)) &&
 		    MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap))
 			parse_vxlan_attr(spec, f);
-		else
+		else {
+			netdev_warn(priv->netdev,
+				    "%d isn't an offloaded vxlan udp dport\n", be16_to_cpu(key->dst));
 			return -EOPNOTSUPP;
+		}
 
 		MLX5_SET(fte_match_set_lyr_2_4, headers_c,
 			 udp_dport, ntohs(mask->dst));
 		MLX5_SET(fte_match_set_lyr_2_4, headers_v,
 			 udp_dport, ntohs(key->dst));
 
+		MLX5_SET(fte_match_set_lyr_2_4, headers_c,
+			 udp_sport, ntohs(mask->src));
+		MLX5_SET(fte_match_set_lyr_2_4, headers_v,
+			 udp_sport, ntohs(key->src));
 	} else { /* udp dst port must be given */
-			return -EOPNOTSUPP;
+vxlan_match_offload_err:
+		netdev_warn(priv->netdev,
+			    "IP tunnel decap offload supported only for vxlan, must set UDP dport\n");
+		return -EOPNOTSUPP;
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) {
+	if (enc_control->addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
 		struct flow_dissector_key_ipv4_addrs *key =
 			skb_flow_dissector_target(f->dissector,
 						  FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS,
@@ -280,10 +295,10 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
 		MLX5_SET(fte_match_set_lyr_2_4, headers_v,
 			 dst_ipv4_dst_ipv6.ipv4_layout.ipv4,
 			 ntohl(key->dst));
-	}
 
-	MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ethertype);
-	MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype, ETH_P_IP);
+		MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ethertype);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype, ETH_P_IP);
+	}
 
 	/* Enforce DMAC when offloading incoming tunneled flows.
 	 * Flow counters require a match on the DMAC.
@@ -346,6 +361,9 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 			if (parse_tunnel_attr(priv, spec, f))
 				return -EOPNOTSUPP;
 			break;
+		case FLOW_DISSECTOR_KEY_IPV6_ADDRS:
+			netdev_warn(priv->netdev,
+				    "IPv6 tunnel decap offload isn't supported\n");
 		default:
 			return -EOPNOTSUPP;
 		}
@@ -375,6 +393,10 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 			MLX5_SET(fte_match_set_lyr_2_4, headers_c, frag, 1);
 			MLX5_SET(fte_match_set_lyr_2_4, headers_v, frag,
 				 key->flags & FLOW_DIS_IS_FRAGMENT);
+
+			/* the HW doesn't need L3 inline to match on frag=no */
+			if (key->flags & FLOW_DIS_IS_FRAGMENT)
+				*min_inline = MLX5_INLINE_MODE_IP;
 		}
 	}
 
@@ -647,17 +669,14 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
 
 #if IS_ENABLED(CONFIG_INET)
 	rt = ip_route_output_key(dev_net(mirred_dev), fl4);
-	if (IS_ERR(rt)) {
-		pr_warn("%s: no route to %pI4\n", __func__, &fl4->daddr);
-		return -EOPNOTSUPP;
-	}
+	if (IS_ERR(rt))
+		return PTR_ERR(rt);
 #else
 	return -EOPNOTSUPP;
 #endif
 
 	if (!switchdev_port_same_parent_id(priv->netdev, rt->dst.dev)) {
-		pr_warn("%s: Can't offload the flow, netdevices aren't on the same HW e-switch\n",
-			__func__);
+		pr_warn("%s: can't offload, devices not on same HW e-switch\n", __func__);
 		ip_rt_put(rt);
 		return -EOPNOTSUPP;
 	}
@@ -718,12 +737,12 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
 					  struct net_device **out_dev)
 {
 	int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size);
+	struct neighbour *n = NULL;
 	struct flowi4 fl4 = {};
-	struct neighbour *n;
 	char *encap_header;
 	int encap_size;
-	__be32 saddr;
-	int ttl;
+	__be32 saddr = 0;
+	int ttl = 0;
 	int err;
 
 	encap_header = kzalloc(max_encap_size, GFP_KERNEL);
@@ -750,7 +769,8 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
 	e->out_dev = *out_dev;
 
 	if (!(n->nud_state & NUD_VALID)) {
-		err = -ENOTSUPP;
+		pr_warn("%s: can't offload, neighbour to %pI4 invalid\n", __func__, &fl4.daddr);
+		err = -EOPNOTSUPP;
 		goto out;
 	}
 
@@ -772,6 +792,8 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
 	err = mlx5_encap_alloc(priv->mdev, e->tunnel_type,
 			       encap_size, encap_header, &e->encap_id);
 out:
+	if (err && n)
+		neigh_release(n);
 	kfree(encap_header);
 	return err;
 }
@@ -792,9 +814,17 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
 	int tunnel_type;
 	int err;
 
-	/* udp dst port must be given */
+	/* udp dst port must be set */
 	if (!memchr_inv(&key->tp_dst, 0, sizeof(key->tp_dst)))
+		goto vxlan_encap_offload_err;
+
+	/* setting udp src port isn't supported */
+	if (memchr_inv(&key->tp_src, 0, sizeof(key->tp_src))) {
+vxlan_encap_offload_err:
+		netdev_warn(priv->netdev,
+			    "must set udp dst port and not set udp src port\n");
 		return -EOPNOTSUPP;
+	}
 
 	if (mlx5e_vxlan_lookup_port(priv, be16_to_cpu(key->tp_dst)) &&
 	    MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap)) {
@@ -802,6 +832,8 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
 		info.tun_id = tunnel_id_to_key32(key->tun_id);
 		tunnel_type = MLX5_HEADER_TYPE_VXLAN;
 	} else {
+		netdev_warn(priv->netdev,
+			    "%d isn't an offloaded vxlan udp dport\n", be16_to_cpu(key->tp_dst));
 		return -EOPNOTSUPP;
 	}
 
@@ -809,6 +841,9 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
 	case AF_INET:
 		info.daddr = key->u.ipv4.dst;
 		break;
+	case AF_INET6:
+		netdev_warn(priv->netdev,
+			    "IPv6 tunnel encap offload isn't supported\n");
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -986,7 +1021,7 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol,
 
 	if (IS_ERR(flow->rule)) {
 		err = PTR_ERR(flow->rule);
-		goto err_free;
+		goto err_del_rule;
 	}
 
 	err = rhashtable_insert_fast(&tc->ht, &flow->node,
@@ -997,7 +1032,7 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol,
 	goto out;
 
 err_del_rule:
-	mlx5_del_flow_rules(flow->rule);
+	mlx5e_tc_del_flow(priv, flow);
 
 err_free:
 	kfree(flow);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 6547f22e6b9b..d01e9f21d469 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1195,7 +1195,8 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 {
 	int err = 0;
 
-	mlx5_drain_health_wq(dev);
+	if (cleanup)
+		mlx5_drain_health_wq(dev);
 
 	mutex_lock(&dev->intf_state_mutex);
 	if (test_bit(MLX5_INTERFACE_STATE_DOWN, &dev->intf_state)) {
@@ -1359,9 +1360,10 @@ static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev,
 
 	mlx5_enter_error_state(dev);
 	mlx5_unload_one(dev, priv, false);
-	/* In case of kernel call save the pci state */
+	/* In case of kernel call save the pci state and drain the health wq */
 	if (state) {
 		pci_save_state(pdev);
+		mlx5_drain_health_wq(dev);
 		mlx5_pci_disable_device(dev);
 	}