mlx5-fixes-2021-01-07

-----BEGIN PGP SIGNATURE-----
 
 iQEzBAABCAAdFiEEGhZs6bAKwk/OTgTpSD+KveBX+j4FAl/3bZsACgkQSD+KveBX
 +j4powgAnzKVXUxN/R5IJ8z9kONZEvI+9SgHQ/qvzsHY66zy6xHlCdrmRWYI8V1c
 KuZltBQPVCd1fAAWAzzmkEOpClM1IbS6zd0/OoJFHJfZYdFEZStvw4NrazpRNd6E
 rPUgJpxRFjiLbklZhpfZ6yaoAWez/fXPQbXB+ObOs2m/guesCyZy/T7mBTvvovwA
 gmrWoxb6vApJZtgk3bIQKaaevx5/0UFCWqJIoAgKyCzVKf8QvQ0OLRkt27Cn3B08
 lTjtUjiGe4boxVY8F+bEb79BcnezIb/NlafjoJ1gyCgZ5dvHSrfaopiAxIZhxRSX
 bP/W8cCVZvUngclDs/L+cx3Y3btpNA==
 =0qLp
 -----END PGP SIGNATURE-----

Merge tag 'mlx5-fixes-2021-01-07' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5 fixes 2021-01-07

* tag 'mlx5-fixes-2021-01-07' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux:
  net/mlx5e: Fix memleak in mlx5e_create_l2_table_groups
  net/mlx5e: Fix two double free cases
  net/mlx5: Release devlink object if adev fails
  net/mlx5e: ethtool, Fix restriction of autoneg with 56G
  net/mlx5e: In skb build skip setting mark in switchdev mode
  net/mlx5: E-Switch, fix changing vf VLANID
  net/mlx5e: Fix SWP offsets when vlan inserted by driver
  net/mlx5e: CT: Use per flow counter when CT flow accounting is enabled
  net/mlx5: Use port_num 1 instead of 0 when delete a RoCE address
  net/mlx5e: Add missing capability check for uplink follow
  net/mlx5: Check if lag is supported before creating one
====================

Link: https://lore.kernel.org/r/20210107202845.470205-1-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c

@@ -626,6 +626,11 @@ bool mlx5e_rep_tc_update_skb(struct mlx5_cqe64 *cqe,
 	if (!reg_c0)
 		return true;
 
+	/* If reg_c0 is not equal to the default flow tag then skb->mark
+	 * is not supported and must be reset back to 0.
+	 */
+	skb->mark = 0;
+
 	priv = netdev_priv(skb->dev);
 	esw = priv->mdev->priv.eswitch;
 

drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c

@@ -118,16 +118,17 @@ struct mlx5_ct_tuple {
 	u16 zone;
 };
 
-struct mlx5_ct_shared_counter {
+struct mlx5_ct_counter {
 	struct mlx5_fc *counter;
 	refcount_t refcount;
+	bool is_shared;
 };
 
 struct mlx5_ct_entry {
 	struct rhash_head node;
 	struct rhash_head tuple_node;
 	struct rhash_head tuple_nat_node;
-	struct mlx5_ct_shared_counter *shared_counter;
+	struct mlx5_ct_counter *counter;
 	unsigned long cookie;
 	unsigned long restore_cookie;
 	struct mlx5_ct_tuple tuple;
@@ -394,13 +395,14 @@ mlx5_tc_ct_set_tuple_match(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec,
 }
 
 static void
-mlx5_tc_ct_shared_counter_put(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_entry *entry)
+mlx5_tc_ct_counter_put(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_entry *entry)
 {
-	if (!refcount_dec_and_test(&entry->shared_counter->refcount))
+	if (entry->counter->is_shared &&
+	    !refcount_dec_and_test(&entry->counter->refcount))
 		return;
 
-	mlx5_fc_destroy(ct_priv->dev, entry->shared_counter->counter);
+	mlx5_fc_destroy(ct_priv->dev, entry->counter->counter);
-	kfree(entry->shared_counter);
+	kfree(entry->counter);
 }
 
 static void
@@ -699,7 +701,7 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv,
 	attr->dest_ft = ct_priv->post_ct;
 	attr->ft = nat ? ct_priv->ct_nat : ct_priv->ct;
 	attr->outer_match_level = MLX5_MATCH_L4;
-	attr->counter = entry->shared_counter->counter;
+	attr->counter = entry->counter->counter;
 	attr->flags |= MLX5_ESW_ATTR_FLAG_NO_IN_PORT;
 
 	mlx5_tc_ct_set_tuple_match(netdev_priv(ct_priv->netdev), spec, flow_rule);
@@ -732,13 +734,34 @@ err_attr:
 	return err;
 }
 
-static struct mlx5_ct_shared_counter *
+static struct mlx5_ct_counter *
+mlx5_tc_ct_counter_create(struct mlx5_tc_ct_priv *ct_priv)
+{
+	struct mlx5_ct_counter *counter;
+	int ret;
+
+	counter = kzalloc(sizeof(*counter), GFP_KERNEL);
+	if (!counter)
+		return ERR_PTR(-ENOMEM);
+
+	counter->is_shared = false;
+	counter->counter = mlx5_fc_create(ct_priv->dev, true);
+	if (IS_ERR(counter->counter)) {
+		ct_dbg("Failed to create counter for ct entry");
+		ret = PTR_ERR(counter->counter);
+		kfree(counter);
+		return ERR_PTR(ret);
+	}
+
+	return counter;
+}
+
+static struct mlx5_ct_counter *
 mlx5_tc_ct_shared_counter_get(struct mlx5_tc_ct_priv *ct_priv,
 			      struct mlx5_ct_entry *entry)
 {
 	struct mlx5_ct_tuple rev_tuple = entry->tuple;
-	struct mlx5_ct_shared_counter *shared_counter;
+	struct mlx5_ct_counter *shared_counter;
-	struct mlx5_core_dev *dev = ct_priv->dev;
 	struct mlx5_ct_entry *rev_entry;
 	__be16 tmp_port;
 	int ret;
@@ -767,25 +790,20 @@ mlx5_tc_ct_shared_counter_get(struct mlx5_tc_ct_priv *ct_priv,
 	rev_entry = rhashtable_lookup_fast(&ct_priv->ct_tuples_ht, &rev_tuple,
 					   tuples_ht_params);
 	if (rev_entry) {
-		if (refcount_inc_not_zero(&rev_entry->shared_counter->refcount)) {
+		if (refcount_inc_not_zero(&rev_entry->counter->refcount)) {
 			mutex_unlock(&ct_priv->shared_counter_lock);
-			return rev_entry->shared_counter;
+			return rev_entry->counter;
 		}
 	}
 	mutex_unlock(&ct_priv->shared_counter_lock);
 
-	shared_counter = kzalloc(sizeof(*shared_counter), GFP_KERNEL);
+	shared_counter = mlx5_tc_ct_counter_create(ct_priv);
-	if (!shared_counter)
+	if (IS_ERR(shared_counter)) {
-		return ERR_PTR(-ENOMEM);
+		ret = PTR_ERR(shared_counter);
-
-	shared_counter->counter = mlx5_fc_create(dev, true);
-	if (IS_ERR(shared_counter->counter)) {
-		ct_dbg("Failed to create counter for ct entry");
-		ret = PTR_ERR(shared_counter->counter);
-		kfree(shared_counter);
 		return ERR_PTR(ret);
 	}
 
+	shared_counter->is_shared = true;
 	refcount_set(&shared_counter->refcount, 1);
 	return shared_counter;
 }
@@ -798,10 +816,13 @@ mlx5_tc_ct_entry_add_rules(struct mlx5_tc_ct_priv *ct_priv,
 {
 	int err;
 
-	entry->shared_counter = mlx5_tc_ct_shared_counter_get(ct_priv, entry);
+	if (nf_ct_acct_enabled(dev_net(ct_priv->netdev)))
-	if (IS_ERR(entry->shared_counter)) {
+		entry->counter = mlx5_tc_ct_counter_create(ct_priv);
-		err = PTR_ERR(entry->shared_counter);
+	else
-		ct_dbg("Failed to create counter for ct entry");
+		entry->counter = mlx5_tc_ct_shared_counter_get(ct_priv, entry);
+
+	if (IS_ERR(entry->counter)) {
+		err = PTR_ERR(entry->counter);
 		return err;
 	}
 
@@ -820,7 +841,7 @@ mlx5_tc_ct_entry_add_rules(struct mlx5_tc_ct_priv *ct_priv,
 err_nat:
 	mlx5_tc_ct_entry_del_rule(ct_priv, entry, false);
 err_orig:
-	mlx5_tc_ct_shared_counter_put(ct_priv, entry);
+	mlx5_tc_ct_counter_put(ct_priv, entry);
 	return err;
 }
 
@@ -918,7 +939,7 @@ mlx5_tc_ct_del_ft_entry(struct mlx5_tc_ct_priv *ct_priv,
 	rhashtable_remove_fast(&ct_priv->ct_tuples_ht, &entry->tuple_node,
 			       tuples_ht_params);
 	mutex_unlock(&ct_priv->shared_counter_lock);
-	mlx5_tc_ct_shared_counter_put(ct_priv, entry);
+	mlx5_tc_ct_counter_put(ct_priv, entry);
 
 }
 
@@ -956,7 +977,7 @@ mlx5_tc_ct_block_flow_offload_stats(struct mlx5_ct_ft *ft,
 	if (!entry)
 		return -ENOENT;
 
-	mlx5_fc_query_cached(entry->shared_counter->counter, &bytes, &packets, &lastuse);
+	mlx5_fc_query_cached(entry->counter->counter, &bytes, &packets, &lastuse);
 	flow_stats_update(&f->stats, bytes, packets, 0, lastuse,
 			  FLOW_ACTION_HW_STATS_DELAYED);
 

drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h

@@ -371,6 +371,15 @@ struct mlx5e_swp_spec {
 	u8 tun_l4_proto;
 };
 
+static inline void mlx5e_eseg_swp_offsets_add_vlan(struct mlx5_wqe_eth_seg *eseg)
+{
+	/* SWP offsets are in 2-bytes words */
+	eseg->swp_outer_l3_offset += VLAN_HLEN / 2;
+	eseg->swp_outer_l4_offset += VLAN_HLEN / 2;
+	eseg->swp_inner_l3_offset += VLAN_HLEN / 2;
+	eseg->swp_inner_l4_offset += VLAN_HLEN / 2;
+}
+
 static inline void
 mlx5e_set_eseg_swp(struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg,
 		   struct mlx5e_swp_spec *swp_spec)

drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h

@@ -51,7 +51,7 @@ static inline bool mlx5_geneve_tx_allowed(struct mlx5_core_dev *mdev)
 }
 
 static inline void
-mlx5e_tx_tunnel_accel(struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg)
+mlx5e_tx_tunnel_accel(struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg, u16 ihs)
 {
 	struct mlx5e_swp_spec swp_spec = {};
 	unsigned int offset = 0;
@@ -85,6 +85,8 @@ mlx5e_tx_tunnel_accel(struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg)
 	}
 
 	mlx5e_set_eseg_swp(skb, eseg, &swp_spec);
+	if (skb_vlan_tag_present(skb) &&  ihs)
+		mlx5e_eseg_swp_offsets_add_vlan(eseg);
 }
 
 #else
@@ -163,7 +165,7 @@ static inline unsigned int mlx5e_accel_tx_ids_len(struct mlx5e_txqsq *sq,
 
 static inline bool mlx5e_accel_tx_eseg(struct mlx5e_priv *priv,
 				       struct sk_buff *skb,
-				       struct mlx5_wqe_eth_seg *eseg)
+				       struct mlx5_wqe_eth_seg *eseg, u16 ihs)
 {
 #ifdef CONFIG_MLX5_EN_IPSEC
 	if (xfrm_offload(skb))
@@ -172,7 +174,7 @@ static inline bool mlx5e_accel_tx_eseg(struct mlx5e_priv *priv,
 
 #if IS_ENABLED(CONFIG_GENEVE)
 	if (skb->encapsulation)
-		mlx5e_tx_tunnel_accel(skb, eseg);
+		mlx5e_tx_tunnel_accel(skb, eseg, ihs);
 #endif
 
 	return true;

drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c

@@ -1010,6 +1010,22 @@ static int mlx5e_get_link_ksettings(struct net_device *netdev,
 	return mlx5e_ethtool_get_link_ksettings(priv, link_ksettings);
 }
 
+static int mlx5e_speed_validate(struct net_device *netdev, bool ext,
+				const unsigned long link_modes, u8 autoneg)
+{
+	/* Extended link-mode has no speed limitations. */
+	if (ext)
+		return 0;
+
+	if ((link_modes & MLX5E_PROT_MASK(MLX5E_56GBASE_R4)) &&
+	    autoneg != AUTONEG_ENABLE) {
+		netdev_err(netdev, "%s: 56G link speed requires autoneg enabled\n",
+			   __func__);
+		return -EINVAL;
+	}
+	return 0;
+}
+
 static u32 mlx5e_ethtool2ptys_adver_link(const unsigned long *link_modes)
 {
 	u32 i, ptys_modes = 0;
@@ -1103,13 +1119,9 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 	link_modes = autoneg == AUTONEG_ENABLE ? ethtool2ptys_adver_func(adver) :
 		mlx5e_port_speed2linkmodes(mdev, speed, !ext);
 
-	if ((link_modes & MLX5E_PROT_MASK(MLX5E_56GBASE_R4)) &&
+	err = mlx5e_speed_validate(priv->netdev, ext, link_modes, autoneg);
-	    autoneg != AUTONEG_ENABLE) {
+	if (err)
-		netdev_err(priv->netdev, "%s: 56G link speed requires autoneg enabled\n",
-			   __func__);
-		err = -EINVAL;
 		goto out;
-	}
 
 	link_modes = link_modes & eproto.cap;
 	if (!link_modes) {

drivers/net/ethernet/mellanox/mlx5/core/en_fs.c

@@ -942,6 +942,7 @@ static int mlx5e_create_ttc_table_groups(struct mlx5e_ttc_table *ttc,
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if (!in) {
 		kfree(ft->g);
+		ft->g = NULL;
 		return -ENOMEM;
 	}
 
@@ -1087,6 +1088,7 @@ static int mlx5e_create_inner_ttc_table_groups(struct mlx5e_ttc_table *ttc)
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if (!in) {
 		kfree(ft->g);
+		ft->g = NULL;
 		return -ENOMEM;
 	}
 
@@ -1390,6 +1392,7 @@ err_destroy_groups:
 	ft->g[ft->num_groups] = NULL;
 	mlx5e_destroy_groups(ft);
 	kvfree(in);
+	kfree(ft->g);
 
 	return err;
 }

drivers/net/ethernet/mellanox/mlx5/core/en_main.c

@@ -3161,7 +3161,8 @@ static void mlx5e_modify_admin_state(struct mlx5_core_dev *mdev,
 
 	mlx5_set_port_admin_status(mdev, state);
 
-	if (mlx5_eswitch_mode(mdev) != MLX5_ESWITCH_LEGACY)
+	if (mlx5_eswitch_mode(mdev) == MLX5_ESWITCH_OFFLOADS ||
+	    !MLX5_CAP_GEN(mdev, uplink_follow))
 		return;
 
 	if (state == MLX5_PORT_UP)

drivers/net/ethernet/mellanox/mlx5/core/en_tx.c

@@ -682,9 +682,9 @@ void mlx5e_tx_mpwqe_ensure_complete(struct mlx5e_txqsq *sq)
 
 static bool mlx5e_txwqe_build_eseg(struct mlx5e_priv *priv, struct mlx5e_txqsq *sq,
 				   struct sk_buff *skb, struct mlx5e_accel_tx_state *accel,
-				   struct mlx5_wqe_eth_seg *eseg)
+				   struct mlx5_wqe_eth_seg *eseg, u16 ihs)
 {
-	if (unlikely(!mlx5e_accel_tx_eseg(priv, skb, eseg)))
+	if (unlikely(!mlx5e_accel_tx_eseg(priv, skb, eseg, ihs)))
 		return false;
 
 	mlx5e_txwqe_build_eseg_csum(sq, skb, accel, eseg);
@@ -714,7 +714,8 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
 		if (mlx5e_tx_skb_supports_mpwqe(skb, &attr)) {
 			struct mlx5_wqe_eth_seg eseg = {};
 
-			if (unlikely(!mlx5e_txwqe_build_eseg(priv, sq, skb, &accel, &eseg)))
+			if (unlikely(!mlx5e_txwqe_build_eseg(priv, sq, skb, &accel, &eseg,
+							     attr.ihs)))
 				return NETDEV_TX_OK;
 
 			mlx5e_sq_xmit_mpwqe(sq, skb, &eseg, netdev_xmit_more());
@@ -731,7 +732,7 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* May update the WQE, but may not post other WQEs. */
 	mlx5e_accel_tx_finish(sq, wqe, &accel,
 			      (struct mlx5_wqe_inline_seg *)(wqe->data + wqe_attr.ds_cnt_inl));
-	if (unlikely(!mlx5e_txwqe_build_eseg(priv, sq, skb, &accel, &wqe->eth)))
+	if (unlikely(!mlx5e_txwqe_build_eseg(priv, sq, skb, &accel, &wqe->eth, attr.ihs)))
 		return NETDEV_TX_OK;
 
 	mlx5e_sq_xmit_wqe(sq, skb, &attr, &wqe_attr, wqe, pi, netdev_xmit_more());

drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c

@@ -95,22 +95,21 @@ int esw_acl_egress_lgcy_setup(struct mlx5_eswitch *esw,
 		return 0;
 	}
 
-	if (!IS_ERR_OR_NULL(vport->egress.acl))
+	if (!vport->egress.acl) {
-		return 0;
+		vport->egress.acl = esw_acl_table_create(esw, vport->vport,
+							 MLX5_FLOW_NAMESPACE_ESW_EGRESS,
+							 table_size);
+		if (IS_ERR(vport->egress.acl)) {
+			err = PTR_ERR(vport->egress.acl);
+			vport->egress.acl = NULL;
+			goto out;
+		}
 
-	vport->egress.acl = esw_acl_table_create(esw, vport->vport,
+		err = esw_acl_egress_lgcy_groups_create(esw, vport);
-						 MLX5_FLOW_NAMESPACE_ESW_EGRESS,
+		if (err)
-						 table_size);
+			goto out;
-	if (IS_ERR(vport->egress.acl)) {
-		err = PTR_ERR(vport->egress.acl);
-		vport->egress.acl = NULL;
-		goto out;
 	}
 
-	err = esw_acl_egress_lgcy_groups_create(esw, vport);
-	if (err)
-		goto out;
-
 	esw_debug(esw->dev,
 		  "vport[%d] configure egress rules, vlan(%d) qos(%d)\n",
 		  vport->vport, vport->info.vlan, vport->info.qos);

drivers/net/ethernet/mellanox/mlx5/core/lag.c

@@ -564,7 +564,9 @@ void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev)
 	struct mlx5_core_dev *tmp_dev;
 	int i, err;
 
-	if (!MLX5_CAP_GEN(dev, vport_group_manager))
+	if (!MLX5_CAP_GEN(dev, vport_group_manager) ||
+	    !MLX5_CAP_GEN(dev, lag_master) ||
+	    MLX5_CAP_GEN(dev, num_lag_ports) != MLX5_MAX_PORTS)
 		return;
 
 	tmp_dev = mlx5_get_next_phys_dev(dev);
@@ -582,12 +584,9 @@ void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev)
 	if (mlx5_lag_dev_add_pf(ldev, dev, netdev) < 0)
 		return;
 
-	for (i = 0; i < MLX5_MAX_PORTS; i++) {
+	for (i = 0; i < MLX5_MAX_PORTS; i++)
-		tmp_dev = ldev->pf[i].dev;
+		if (!ldev->pf[i].dev)
-		if (!tmp_dev || !MLX5_CAP_GEN(tmp_dev, lag_master) ||
-		    MLX5_CAP_GEN(tmp_dev, num_lag_ports) != MLX5_MAX_PORTS)
 			break;
-	}
 
 	if (i >= MLX5_MAX_PORTS)
 		ldev->flags |= MLX5_LAG_FLAG_READY;

drivers/net/ethernet/mellanox/mlx5/core/main.c

@@ -1368,8 +1368,10 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 			 MLX5_COREDEV_VF : MLX5_COREDEV_PF;
 
 	dev->priv.adev_idx = mlx5_adev_idx_alloc();
-	if (dev->priv.adev_idx < 0)
+	if (dev->priv.adev_idx < 0) {
-		return dev->priv.adev_idx;
+		err = dev->priv.adev_idx;
+		goto adev_init_err;
+	}
 
 	err = mlx5_mdev_init(dev, prof_sel);
 	if (err)
@@ -1403,6 +1405,7 @@ pci_init_err:
 	mlx5_mdev_uninit(dev);
 mdev_init_err:
 	mlx5_adev_idx_free(dev->priv.adev_idx);
+adev_init_err:
 	mlx5_devlink_free(devlink);
 
 	return err;

drivers/net/ethernet/mellanox/mlx5/core/rdma.c

@@ -116,7 +116,7 @@ free:
 static void mlx5_rdma_del_roce_addr(struct mlx5_core_dev *dev)
 {
 	mlx5_core_roce_gid_set(dev, 0, 0, 0,
-			       NULL, NULL, false, 0, 0);
+			       NULL, NULL, false, 0, 1);
 }
 
 static void mlx5_rdma_make_default_gid(struct mlx5_core_dev *dev, union ib_gid *gid)

include/linux/mlx5/mlx5_ifc.h

@@ -1280,7 +1280,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8	   ece_support[0x1];
 	u8	   reserved_at_a4[0x7];
 	u8         log_max_srq[0x5];
-	u8         reserved_at_b0[0x2];
+	u8         reserved_at_b0[0x1];
+	u8         uplink_follow[0x1];
 	u8         ts_cqe_to_dest_cqn[0x1];
 	u8         reserved_at_b3[0xd];