Merge tag 'mlx5-fixes-2023-07-26' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5 fixes 2023-07-26

This series provides bug fixes to mlx5 driver.

* tag 'mlx5-fixes-2023-07-26' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux:
  net/mlx5: Unregister devlink params in case interface is down
  net/mlx5: DR, Fix peer domain namespace setting
  net/mlx5: fs_chains: Fix ft prio if ignore_flow_level is not supported
  net/mlx5e: kTLS, Fix protection domain in use syndrome when devlink reload
  net/mlx5: Bridge, set debugfs access right to root-only
  net/mlx5e: xsk: Fix crash on regular rq reactivation
  net/mlx5e: xsk: Fix invalid buffer access for legacy rq
  net/mlx5e: Move representor neigh cleanup to profile cleanup_tx
  net/mlx5e: Fix crash moving to switchdev mode when ntuple offload is set
  net/mlx5e: Don't hold encap tbl lock if there is no encap action
  net/mlx5: Honor user input for migratable port fn attr
  net/mlx5e: fix return value check in mlx5e_ipsec_remove_trailer()
  net/mlx5: fix potential memory leak in mlx5e_init_rep_rx
  net/mlx5: DR, fix memory leak in mlx5dr_cmd_create_reformat_ctx
  net/mlx5e: fix double free in macsec_fs_tx_create_crypto_table_groups
====================

Link: https://lore.kernel.org/r/20230726213206.47022-1-saeed@kernel.orgSigned-off-by: Jakub Kicinski <kuba@kernel.org>

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

@@ -1030,9 +1030,6 @@ int mlx5e_tc_tun_encap_dests_set(struct mlx5e_priv *priv,
 	int out_index;
 	int err = 0;
 
-	if (!mlx5e_is_eswitch_flow(flow))
-		return 0;
-
 	parse_attr = attr->parse_attr;
 	esw_attr = attr->esw_attr;
 	*vf_tun = false;

drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c

@@ -323,8 +323,11 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq,
 	net_prefetch(mxbuf->xdp.data);
 
 	prog = rcu_dereference(rq->xdp_prog);
-	if (likely(prog && mlx5e_xdp_handle(rq, prog, mxbuf)))
+	if (likely(prog && mlx5e_xdp_handle(rq, prog, mxbuf))) {
+		if (likely(__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)))
+			wi->flags |= BIT(MLX5E_WQE_FRAG_SKIP_RELEASE);
 		return NULL; /* page/packet was consumed by XDP */
+	}
 
 	/* XDP_PASS: copy the data from the UMEM to a new SKB. The frame reuse
 	 * will be handled by mlx5e_free_rx_wqe.

drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c

@@ -58,7 +58,9 @@ static int mlx5e_ipsec_remove_trailer(struct sk_buff *skb, struct xfrm_state *x)
 
 	trailer_len = alen + plen + 2;
 
-	pskb_trim(skb, skb->len - trailer_len);
+	ret = pskb_trim(skb, skb->len - trailer_len);
+	if (unlikely(ret))
+		return ret;
 	if (skb->protocol == htons(ETH_P_IP)) {
 		ipv4hdr->tot_len = htons(ntohs(ipv4hdr->tot_len) - trailer_len);
 		ip_send_check(ipv4hdr);

drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c

@@ -188,7 +188,6 @@ static void mlx5e_tls_debugfs_init(struct mlx5e_tls *tls,
 
 int mlx5e_ktls_init(struct mlx5e_priv *priv)
 {
-	struct mlx5_crypto_dek_pool *dek_pool;
 	struct mlx5e_tls *tls;
 
 	if (!mlx5e_is_ktls_device(priv->mdev))
@@ -199,12 +198,6 @@ int mlx5e_ktls_init(struct mlx5e_priv *priv)
 		return -ENOMEM;
 	tls->mdev = priv->mdev;
 
-	dek_pool = mlx5_crypto_dek_pool_create(priv->mdev, MLX5_ACCEL_OBJ_TLS_KEY);
-	if (IS_ERR(dek_pool)) {
-		kfree(tls);
-		return PTR_ERR(dek_pool);
-	}
-	tls->dek_pool = dek_pool;
 	priv->tls = tls;
 
 	mlx5e_tls_debugfs_init(tls, priv->dfs_root);
@@ -222,7 +215,6 @@ void mlx5e_ktls_cleanup(struct mlx5e_priv *priv)
 	debugfs_remove_recursive(tls->debugfs.dfs);
 	tls->debugfs.dfs = NULL;
 
-	mlx5_crypto_dek_pool_destroy(tls->dek_pool);
 	kfree(priv->tls);
 	priv->tls = NULL;
 }

drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c

@@ -908,28 +908,51 @@ static void mlx5e_tls_tx_debugfs_init(struct mlx5e_tls *tls,
 
 int mlx5e_ktls_init_tx(struct mlx5e_priv *priv)
 {
+	struct mlx5_crypto_dek_pool *dek_pool;
 	struct mlx5e_tls *tls = priv->tls;
+	int err;
+
+	if (!mlx5e_is_ktls_device(priv->mdev))
+		return 0;
+
+	/* DEK pool could be used by either or both of TX and RX. But we have to
+	 * put the creation here to avoid syndrome when doing devlink reload.
+	 */
+	dek_pool = mlx5_crypto_dek_pool_create(priv->mdev, MLX5_ACCEL_OBJ_TLS_KEY);
+	if (IS_ERR(dek_pool))
+		return PTR_ERR(dek_pool);
+	tls->dek_pool = dek_pool;
 
 	if (!mlx5e_is_ktls_tx(priv->mdev))
 		return 0;
 
 	priv->tls->tx_pool = mlx5e_tls_tx_pool_init(priv->mdev, &priv->tls->sw_stats);
-	if (!priv->tls->tx_pool)
-		return -ENOMEM;
+	if (!priv->tls->tx_pool) {
+		err = -ENOMEM;
+		goto err_tx_pool_init;
+	}
 
 	mlx5e_tls_tx_debugfs_init(tls, tls->debugfs.dfs);
 
 	return 0;
+
+err_tx_pool_init:
+	mlx5_crypto_dek_pool_destroy(dek_pool);
+	return err;
 }
 
 void mlx5e_ktls_cleanup_tx(struct mlx5e_priv *priv)
 {
 	if (!mlx5e_is_ktls_tx(priv->mdev))
-		return;
+		goto dek_pool_destroy;
 
 	debugfs_remove_recursive(priv->tls->debugfs.dfs_tx);
 	priv->tls->debugfs.dfs_tx = NULL;
 
 	mlx5e_tls_tx_pool_cleanup(priv->tls->tx_pool);
 	priv->tls->tx_pool = NULL;
+
+dek_pool_destroy:
+	if (mlx5e_is_ktls_device(priv->mdev))
+		mlx5_crypto_dek_pool_destroy(priv->tls->dek_pool);
 }

drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c

@@ -161,6 +161,7 @@ static int macsec_fs_tx_create_crypto_table_groups(struct mlx5e_flow_table *ft)
 
 	if (!in) {
 		kfree(ft->g);
+		ft->g = NULL;
 		return -ENOMEM;
 	}
 

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

@@ -135,6 +135,16 @@ static void arfs_del_rules(struct mlx5e_flow_steering *fs);
 
 int mlx5e_arfs_disable(struct mlx5e_flow_steering *fs)
 {
+	/* Moving to switchdev mode, fs->arfs is freed by mlx5e_nic_profile
+	 * cleanup_rx callback and it is not recreated when
+	 * mlx5e_uplink_rep_profile is loaded as mlx5e_create_flow_steering()
+	 * is not called by the uplink_rep profile init_rx callback. Thus, if
+	 * ntuple is set, moving to switchdev flow will enter this function
+	 * with fs->arfs nullified.
+	 */
+	if (!mlx5e_fs_get_arfs(fs))
+		return 0;
+
 	arfs_del_rules(fs);
 
 	return arfs_disable(fs);

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

@@ -1036,7 +1036,23 @@ static int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state, int next_s
 	return err;
 }
 
-static int mlx5e_rq_to_ready(struct mlx5e_rq *rq, int curr_state)
+static void mlx5e_flush_rq_cq(struct mlx5e_rq *rq)
+{
+	struct mlx5_cqwq *cqwq = &rq->cq.wq;
+	struct mlx5_cqe64 *cqe;
+
+	if (test_bit(MLX5E_RQ_STATE_MINI_CQE_ENHANCED, &rq->state)) {
+		while ((cqe = mlx5_cqwq_get_cqe_enahnced_comp(cqwq)))
+			mlx5_cqwq_pop(cqwq);
+	} else {
+		while ((cqe = mlx5_cqwq_get_cqe(cqwq)))
+			mlx5_cqwq_pop(cqwq);
+	}
+
+	mlx5_cqwq_update_db_record(cqwq);
+}
+
+int mlx5e_flush_rq(struct mlx5e_rq *rq, int curr_state)
 {
 	struct net_device *dev = rq->netdev;
 	int err;
@@ -1046,6 +1062,10 @@ static int mlx5e_rq_to_ready(struct mlx5e_rq *rq, int curr_state)
 		netdev_err(dev, "Failed to move rq 0x%x to reset\n", rq->rqn);
 		return err;
 	}
+
+	mlx5e_free_rx_descs(rq);
+	mlx5e_flush_rq_cq(rq);
+
 	err = mlx5e_modify_rq_state(rq, MLX5_RQC_STATE_RST, MLX5_RQC_STATE_RDY);
 	if (err) {
 		netdev_err(dev, "Failed to move rq 0x%x to ready\n", rq->rqn);
@@ -1055,13 +1075,6 @@ static int mlx5e_rq_to_ready(struct mlx5e_rq *rq, int curr_state)
 	return 0;
 }
 
-int mlx5e_flush_rq(struct mlx5e_rq *rq, int curr_state)
-{
-	mlx5e_free_rx_descs(rq);
-
-	return mlx5e_rq_to_ready(rq, curr_state);
-}
-
 static int mlx5e_modify_rq_vsd(struct mlx5e_rq *rq, bool vsd)
 {
 	struct mlx5_core_dev *mdev = rq->mdev;

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

@@ -1012,7 +1012,7 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv)
 	err = mlx5e_open_drop_rq(priv, &priv->drop_rq);
 	if (err) {
 		mlx5_core_err(mdev, "open drop rq failed, %d\n", err);
-		return err;
+		goto err_rx_res_free;
 	}
 
 	err = mlx5e_rx_res_init(priv->rx_res, priv->mdev, 0,
@@ -1046,6 +1046,7 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv)
 	mlx5e_rx_res_destroy(priv->rx_res);
 err_close_drop_rq:
 	mlx5e_close_drop_rq(&priv->drop_rq);
+err_rx_res_free:
 	mlx5e_rx_res_free(priv->rx_res);
 	priv->rx_res = NULL;
 err_free_fs:
@@ -1159,6 +1160,10 @@ static int mlx5e_init_rep_tx(struct mlx5e_priv *priv)
 		return err;
 	}
 
+	err = mlx5e_rep_neigh_init(rpriv);
+	if (err)
+		goto err_neigh_init;
+
 	if (rpriv->rep->vport == MLX5_VPORT_UPLINK) {
 		err = mlx5e_init_uplink_rep_tx(rpriv);
 		if (err)
@@ -1175,6 +1180,8 @@ static int mlx5e_init_rep_tx(struct mlx5e_priv *priv)
 	if (rpriv->rep->vport == MLX5_VPORT_UPLINK)
 		mlx5e_cleanup_uplink_rep_tx(rpriv);
 err_init_tx:
+	mlx5e_rep_neigh_cleanup(rpriv);
+err_neigh_init:
 	mlx5e_destroy_tises(priv);
 	return err;
 }
@@ -1188,22 +1195,17 @@ static void mlx5e_cleanup_rep_tx(struct mlx5e_priv *priv)
 	if (rpriv->rep->vport == MLX5_VPORT_UPLINK)
 		mlx5e_cleanup_uplink_rep_tx(rpriv);
 
+	mlx5e_rep_neigh_cleanup(rpriv);
 	mlx5e_destroy_tises(priv);
 }
 
 static void mlx5e_rep_enable(struct mlx5e_priv *priv)
 {
-	struct mlx5e_rep_priv *rpriv = priv->ppriv;
-
 	mlx5e_set_netdev_mtu_boundaries(priv);
-	mlx5e_rep_neigh_init(rpriv);
 }
 
 static void mlx5e_rep_disable(struct mlx5e_priv *priv)
 {
-	struct mlx5e_rep_priv *rpriv = priv->ppriv;
-
-	mlx5e_rep_neigh_cleanup(rpriv);
 }
 
 static int mlx5e_update_rep_rx(struct mlx5e_priv *priv)
@@ -1253,7 +1255,6 @@ static int uplink_rep_async_event(struct notifier_block *nb, unsigned long event
 
 static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv)
 {
-	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	struct net_device *netdev = priv->netdev;
 	struct mlx5_core_dev *mdev = priv->mdev;
 	u16 max_mtu;
@@ -1275,7 +1276,6 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv)
 	mlx5_notifier_register(mdev, &priv->events_nb);
 	mlx5e_dcbnl_initialize(priv);
 	mlx5e_dcbnl_init_app(priv);
-	mlx5e_rep_neigh_init(rpriv);
 	mlx5e_rep_bridge_init(priv);
 
 	netdev->wanted_features |= NETIF_F_HW_TC;
@@ -1290,7 +1290,6 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv)
 
 static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv)
 {
-	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	struct mlx5_core_dev *mdev = priv->mdev;
 
 	rtnl_lock();
@@ -1300,7 +1299,6 @@ static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv)
 	rtnl_unlock();
 
 	mlx5e_rep_bridge_cleanup(priv);
-	mlx5e_rep_neigh_cleanup(rpriv);
 	mlx5e_dcbnl_delete_app(priv);
 	mlx5_notifier_unregister(mdev, &priv->events_nb);
 	mlx5e_rep_tc_disable(priv);

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

@@ -1725,6 +1725,19 @@ verify_attr_actions(u32 actions, struct netlink_ext_ack *extack)
 	return 0;
 }
 
+static bool
+has_encap_dests(struct mlx5_flow_attr *attr)
+{
+	struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr;
+	int out_index;
+
+	for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++)
+		if (esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP)
+			return true;
+
+	return false;
+}
+
 static int
 post_process_attr(struct mlx5e_tc_flow *flow,
 		  struct mlx5_flow_attr *attr,
@@ -1737,9 +1750,11 @@ post_process_attr(struct mlx5e_tc_flow *flow,
 	if (err)
 		goto err_out;
 
-	err = mlx5e_tc_tun_encap_dests_set(flow->priv, flow, attr, extack, &vf_tun);
-	if (err)
-		goto err_out;
+	if (mlx5e_is_eswitch_flow(flow) && has_encap_dests(attr)) {
+		err = mlx5e_tc_tun_encap_dests_set(flow->priv, flow, attr, extack, &vf_tun);
+		if (err)
+			goto err_out;
+	}
 
 	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) {
 		err = mlx5e_tc_attach_mod_hdr(flow->priv, flow, attr);

drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_debugfs.c

@@ -64,7 +64,7 @@ void mlx5_esw_bridge_debugfs_init(struct net_device *br_netdev, struct mlx5_esw_
 
 	bridge->debugfs_dir = debugfs_create_dir(br_netdev->name,
 						 bridge->br_offloads->debugfs_root);
-	debugfs_create_file("fdb", 0444, bridge->debugfs_dir, bridge,
+	debugfs_create_file("fdb", 0400, bridge->debugfs_dir, bridge,
 			    &mlx5_esw_bridge_debugfs_fops);
 }
 

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

@@ -1436,7 +1436,6 @@ esw_chains_create(struct mlx5_eswitch *esw, struct mlx5_flow_table *miss_fdb)
 
 	esw_init_chains_offload_flags(esw, &attr.flags);
 	attr.ns = MLX5_FLOW_NAMESPACE_FDB;
-	attr.fs_base_prio = FDB_TC_OFFLOAD;
 	attr.max_grp_num = esw->params.large_group_num;
 	attr.default_ft = miss_fdb;
 	attr.mapping = esw->offloads.reg_c0_obj_pool;
@@ -2779,9 +2778,9 @@ static int mlx5_esw_offloads_set_ns_peer(struct mlx5_eswitch *esw,
 					 struct mlx5_eswitch *peer_esw,
 					 bool pair)
 {
-	u8 peer_idx = mlx5_get_dev_index(peer_esw->dev);
+	u16 peer_vhca_id = MLX5_CAP_GEN(peer_esw->dev, vhca_id);
+	u16 vhca_id = MLX5_CAP_GEN(esw->dev, vhca_id);
 	struct mlx5_flow_root_namespace *peer_ns;
-	u8 idx = mlx5_get_dev_index(esw->dev);
 	struct mlx5_flow_root_namespace *ns;
 	int err;
 
@@ -2789,18 +2788,18 @@ static int mlx5_esw_offloads_set_ns_peer(struct mlx5_eswitch *esw,
 	ns = esw->dev->priv.steering->fdb_root_ns;
 
 	if (pair) {
-		err = mlx5_flow_namespace_set_peer(ns, peer_ns, peer_idx);
+		err = mlx5_flow_namespace_set_peer(ns, peer_ns, peer_vhca_id);
 		if (err)
 			return err;
 
-		err = mlx5_flow_namespace_set_peer(peer_ns, ns, idx);
+		err = mlx5_flow_namespace_set_peer(peer_ns, ns, vhca_id);
 		if (err) {
-			mlx5_flow_namespace_set_peer(ns, NULL, peer_idx);
+			mlx5_flow_namespace_set_peer(ns, NULL, peer_vhca_id);
 			return err;
 		}
 	} else {
-		mlx5_flow_namespace_set_peer(ns, NULL, peer_idx);
-		mlx5_flow_namespace_set_peer(peer_ns, NULL, idx);
+		mlx5_flow_namespace_set_peer(ns, NULL, peer_vhca_id);
+		mlx5_flow_namespace_set_peer(peer_ns, NULL, vhca_id);
 	}
 
 	return 0;
@@ -4196,7 +4195,7 @@ int mlx5_devlink_port_fn_migratable_set(struct devlink_port *port, bool enable,
 	}
 
 	hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability);
-	MLX5_SET(cmd_hca_cap_2, hca_caps, migratable, 1);
+	MLX5_SET(cmd_hca_cap_2, hca_caps, migratable, enable);
 
 	err = mlx5_vport_set_other_func_cap(esw->dev, hca_caps, vport->vport,
 					    MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE2);

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

@@ -140,7 +140,7 @@ static void mlx5_cmd_stub_modify_header_dealloc(struct mlx5_flow_root_namespace
 
 static int mlx5_cmd_stub_set_peer(struct mlx5_flow_root_namespace *ns,
 				  struct mlx5_flow_root_namespace *peer_ns,
-				  u8 peer_idx)
+				  u16 peer_vhca_id)
 {
 	return 0;
 }

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

@@ -94,7 +94,7 @@ struct mlx5_flow_cmds {
 
 	int (*set_peer)(struct mlx5_flow_root_namespace *ns,
 			struct mlx5_flow_root_namespace *peer_ns,
-			u8 peer_idx);
+			u16 peer_vhca_id);
 
 	int (*create_ns)(struct mlx5_flow_root_namespace *ns);
 	int (*destroy_ns)(struct mlx5_flow_root_namespace *ns);

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

@@ -3621,7 +3621,7 @@ void mlx5_destroy_match_definer(struct mlx5_core_dev *dev,
 
 int mlx5_flow_namespace_set_peer(struct mlx5_flow_root_namespace *ns,
 				 struct mlx5_flow_root_namespace *peer_ns,
-				 u8 peer_idx)
+				 u16 peer_vhca_id)
 {
 	if (peer_ns && ns->mode != peer_ns->mode) {
 		mlx5_core_err(ns->dev,
@@ -3629,7 +3629,7 @@ int mlx5_flow_namespace_set_peer(struct mlx5_flow_root_namespace *ns,
 		return -EINVAL;
 	}
 
-	return ns->cmds->set_peer(ns, peer_ns, peer_idx);
+	return ns->cmds->set_peer(ns, peer_ns, peer_vhca_id);
 }
 
 /* This function should be called only at init stage of the namespace.

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

@@ -303,7 +303,7 @@ const struct mlx5_flow_cmds *mlx5_fs_cmd_get_fw_cmds(void);
 
 int mlx5_flow_namespace_set_peer(struct mlx5_flow_root_namespace *ns,
 				 struct mlx5_flow_root_namespace *peer_ns,
-				 u8 peer_idx);
+				 u16 peer_vhca_id);
 
 int mlx5_flow_namespace_set_mode(struct mlx5_flow_namespace *ns,
 				 enum mlx5_flow_steering_mode mode);

drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c

@@ -178,7 +178,7 @@ mlx5_chains_create_table(struct mlx5_fs_chains *chains,
 	if (!mlx5_chains_ignore_flow_level_supported(chains) ||
 	    (chain == 0 && prio == 1 && level == 0)) {
 		ft_attr.level = chains->fs_base_level;
-		ft_attr.prio = chains->fs_base_prio;
+		ft_attr.prio = chains->fs_base_prio + prio - 1;
 		ns = (chains->ns == MLX5_FLOW_NAMESPACE_FDB) ?
 			mlx5_get_fdb_sub_ns(chains->dev, chain) :
 			mlx5_get_flow_namespace(chains->dev, chains->ns);

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

@@ -1506,6 +1506,7 @@ void mlx5_uninit_one(struct mlx5_core_dev *dev)
 	if (!test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) {
 		mlx5_core_warn(dev, "%s: interface is down, NOP\n",
 			       __func__);
+		mlx5_devlink_params_unregister(priv_to_devlink(dev));
 		mlx5_cleanup_once(dev);
 		goto out;
 	}

drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c

@@ -2079,7 +2079,7 @@ mlx5dr_action_create_dest_vport(struct mlx5dr_domain *dmn,
 
 	peer_vport = vhca_id_valid && mlx5_core_is_pf(dmn->mdev) &&
 		(vhca_id != dmn->info.caps.gvmi);
-	vport_dmn = peer_vport ? dmn->peer_dmn[vhca_id] : dmn;
+	vport_dmn = peer_vport ? xa_load(&dmn->peer_dmn_xa, vhca_id) : dmn;
 	if (!vport_dmn) {
 		mlx5dr_dbg(dmn, "No peer vport domain for given vhca_id\n");
 		return NULL;

drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c

@@ -564,11 +564,12 @@ int mlx5dr_cmd_create_reformat_ctx(struct mlx5_core_dev *mdev,
 
 	err = mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out));
 	if (err)
-		return err;
+		goto err_free_in;
 
 	*reformat_id = MLX5_GET(alloc_packet_reformat_context_out, out, packet_reformat_id);
-	kvfree(in);
 
+err_free_in:
+	kvfree(in);
 	return err;
 }
 

drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c

@@ -475,6 +475,7 @@ mlx5dr_domain_create(struct mlx5_core_dev *mdev, enum mlx5dr_domain_type type)
 	mutex_init(&dmn->info.rx.mutex);
 	mutex_init(&dmn->info.tx.mutex);
 	xa_init(&dmn->definers_xa);
+	xa_init(&dmn->peer_dmn_xa);
 
 	if (dr_domain_caps_init(mdev, dmn)) {
 		mlx5dr_err(dmn, "Failed init domain, no caps\n");
@@ -507,6 +508,7 @@ mlx5dr_domain_create(struct mlx5_core_dev *mdev, enum mlx5dr_domain_type type)
 uninit_caps:
 	dr_domain_caps_uninit(dmn);
 def_xa_destroy:
+	xa_destroy(&dmn->peer_dmn_xa);
 	xa_destroy(&dmn->definers_xa);
 	kfree(dmn);
 	return NULL;
@@ -547,6 +549,7 @@ int mlx5dr_domain_destroy(struct mlx5dr_domain *dmn)
 	dr_domain_uninit_csum_recalc_fts(dmn);
 	dr_domain_uninit_resources(dmn);
 	dr_domain_caps_uninit(dmn);
+	xa_destroy(&dmn->peer_dmn_xa);
 	xa_destroy(&dmn->definers_xa);
 	mutex_destroy(&dmn->info.tx.mutex);
 	mutex_destroy(&dmn->info.rx.mutex);
@@ -556,17 +559,21 @@ int mlx5dr_domain_destroy(struct mlx5dr_domain *dmn)
 
 void mlx5dr_domain_set_peer(struct mlx5dr_domain *dmn,
 			    struct mlx5dr_domain *peer_dmn,
-			    u8 peer_idx)
+			    u16 peer_vhca_id)
 {
+	struct mlx5dr_domain *peer;
+
 	mlx5dr_domain_lock(dmn);
 
-	if (dmn->peer_dmn[peer_idx])
-		refcount_dec(&dmn->peer_dmn[peer_idx]->refcount);
+	peer = xa_load(&dmn->peer_dmn_xa, peer_vhca_id);
+	if (peer)
+		refcount_dec(&peer->refcount);
 
-	dmn->peer_dmn[peer_idx] = peer_dmn;
+	WARN_ON(xa_err(xa_store(&dmn->peer_dmn_xa, peer_vhca_id, peer_dmn, GFP_KERNEL)));
 
-	if (dmn->peer_dmn[peer_idx])
-		refcount_inc(&dmn->peer_dmn[peer_idx]->refcount);
+	peer = xa_load(&dmn->peer_dmn_xa, peer_vhca_id);
+	if (peer)
+		refcount_inc(&peer->refcount);
 
 	mlx5dr_domain_unlock(dmn);
 }

drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c

@@ -1652,17 +1652,18 @@ dr_ste_v0_build_src_gvmi_qpn_tag(struct mlx5dr_match_param *value,
 	struct mlx5dr_domain *dmn = sb->dmn;
 	struct mlx5dr_domain *vport_dmn;
 	u8 *bit_mask = sb->bit_mask;
+	struct mlx5dr_domain *peer;
 	bool source_gvmi_set;
 
 	DR_STE_SET_TAG(src_gvmi_qp, tag, source_qp, misc, source_sqn);
 
 	if (sb->vhca_id_valid) {
+		peer = xa_load(&dmn->peer_dmn_xa, id);
 		/* Find port GVMI based on the eswitch_owner_vhca_id */
 		if (id == dmn->info.caps.gvmi)
 			vport_dmn = dmn;
-		else if (id < MLX5_MAX_PORTS && dmn->peer_dmn[id] &&
-			 (id == dmn->peer_dmn[id]->info.caps.gvmi))
-			vport_dmn = dmn->peer_dmn[id];
+		else if (peer && (id == peer->info.caps.gvmi))
+			vport_dmn = peer;
 		else
 			return -EINVAL;
 

drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c

@@ -1984,16 +1984,17 @@ static int dr_ste_v1_build_src_gvmi_qpn_tag(struct mlx5dr_match_param *value,
 	struct mlx5dr_domain *dmn = sb->dmn;
 	struct mlx5dr_domain *vport_dmn;
 	u8 *bit_mask = sb->bit_mask;
+	struct mlx5dr_domain *peer;
 
 	DR_STE_SET_TAG(src_gvmi_qp_v1, tag, source_qp, misc, source_sqn);
 
 	if (sb->vhca_id_valid) {
+		peer = xa_load(&dmn->peer_dmn_xa, id);
 		/* Find port GVMI based on the eswitch_owner_vhca_id */
 		if (id == dmn->info.caps.gvmi)
 			vport_dmn = dmn;
-		else if (id < MLX5_MAX_PORTS && dmn->peer_dmn[id] &&
-			 (id == dmn->peer_dmn[id]->info.caps.gvmi))
-			vport_dmn = dmn->peer_dmn[id];
+		else if (peer && (id == peer->info.caps.gvmi))
+			vport_dmn = peer;
 		else
 			return -EINVAL;
 

drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h

@@ -935,7 +935,6 @@ struct mlx5dr_domain_info {
 };
 
 struct mlx5dr_domain {
-	struct mlx5dr_domain *peer_dmn[MLX5_MAX_PORTS];
 	struct mlx5_core_dev *mdev;
 	u32 pdn;
 	struct mlx5_uars_page *uar;
@@ -956,6 +955,7 @@ struct mlx5dr_domain {
 	struct list_head dbg_tbl_list;
 	struct mlx5dr_dbg_dump_info dump_info;
 	struct xarray definers_xa;
+	struct xarray peer_dmn_xa;
 	/* memory management statistics */
 	u32 num_buddies[DR_ICM_TYPE_MAX];
 };

drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c

@@ -781,14 +781,14 @@ static int mlx5_cmd_dr_update_fte(struct mlx5_flow_root_namespace *ns,
 
 static int mlx5_cmd_dr_set_peer(struct mlx5_flow_root_namespace *ns,
 				struct mlx5_flow_root_namespace *peer_ns,
-				u8 peer_idx)
+				u16 peer_vhca_id)
 {
 	struct mlx5dr_domain *peer_domain = NULL;
 
 	if (peer_ns)
 		peer_domain = peer_ns->fs_dr_domain.dr_domain;
 	mlx5dr_domain_set_peer(ns->fs_dr_domain.dr_domain,
-			       peer_domain, peer_idx);
+			       peer_domain, peer_vhca_id);
 	return 0;
 }
 

drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h

@@ -49,7 +49,7 @@ int mlx5dr_domain_sync(struct mlx5dr_domain *domain, u32 flags);
 
 void mlx5dr_domain_set_peer(struct mlx5dr_domain *dmn,
 			    struct mlx5dr_domain *peer_dmn,
-			    u8 peer_idx);
+			    u16 peer_vhca_id);
 
 struct mlx5dr_table *
 mlx5dr_table_create(struct mlx5dr_domain *domain, u32 level, u32 flags,