6 files changed, 146 insertions, 131 deletions

diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c
index 25b6482c5368..59022b744144 100644
--- a/drivers/infiniband/hw/mlx5/devx.c
+++ b/drivers/infiniband/hw/mlx5/devx.c
@@ -233,6 +233,8 @@ static bool is_legacy_obj_event_num(u16 event_num)
 	case MLX5_EVENT_TYPE_SRQ_CATAS_ERROR:
 	case MLX5_EVENT_TYPE_DCT_DRAINED:
 	case MLX5_EVENT_TYPE_COMP:
+	case MLX5_EVENT_TYPE_DCT_KEY_VIOLATION:
+	case MLX5_EVENT_TYPE_XRQ_ERROR:
 		return true;
 	default:
 		return false;
@@ -315,8 +317,10 @@ static u16 get_event_obj_type(unsigned long event_type, struct mlx5_eqe *eqe)
 	case MLX5_EVENT_TYPE_SRQ_CATAS_ERROR:
 		return eqe->data.qp_srq.type;
 	case MLX5_EVENT_TYPE_CQ_ERROR:
+	case MLX5_EVENT_TYPE_XRQ_ERROR:
 		return 0;
 	case MLX5_EVENT_TYPE_DCT_DRAINED:
+	case MLX5_EVENT_TYPE_DCT_KEY_VIOLATION:
 		return MLX5_EVENT_QUEUE_TYPE_DCT;
 	default:
 		return MLX5_GET(affiliated_event_header, &eqe->data, obj_type);
@@ -542,6 +546,8 @@ static u64 devx_get_obj_id(const void *in)
 		break;
 	case MLX5_CMD_OP_ARM_XRQ:
 	case MLX5_CMD_OP_SET_XRQ_DC_PARAMS_ENTRY:
+	case MLX5_CMD_OP_RELEASE_XRQ_ERROR:
+	case MLX5_CMD_OP_MODIFY_XRQ:
 		obj_id = get_enc_obj_id(MLX5_CMD_OP_CREATE_XRQ,
 					MLX5_GET(arm_xrq_in, in, xrqn));
 		break;
@@ -776,6 +782,14 @@ static bool devx_is_obj_create_cmd(const void *in, u16 *opcode)
 			return true;
 		return false;
 	}
+	case MLX5_CMD_OP_CREATE_PSV:
+	{
+		u8 num_psv = MLX5_GET(create_psv_in, in, num_psv);
+
+		if (num_psv == 1)
+			return true;
+		return false;
+	}
 	default:
 		return false;
 	}
@@ -810,6 +824,8 @@ static bool devx_is_obj_modify_cmd(const void *in)
 	case MLX5_CMD_OP_ARM_DCT_FOR_KEY_VIOLATION:
 	case MLX5_CMD_OP_ARM_XRQ:
 	case MLX5_CMD_OP_SET_XRQ_DC_PARAMS_ENTRY:
+	case MLX5_CMD_OP_RELEASE_XRQ_ERROR:
+	case MLX5_CMD_OP_MODIFY_XRQ:
 		return true;
 	case MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY:
 	{
@@ -1216,6 +1232,12 @@ static void devx_obj_build_destroy_cmd(void *in, void *out, void *din,
 	case MLX5_CMD_OP_ALLOC_XRCD:
 		MLX5_SET(general_obj_in_cmd_hdr, din, opcode, MLX5_CMD_OP_DEALLOC_XRCD);
 		break;
+	case MLX5_CMD_OP_CREATE_PSV:
+		MLX5_SET(general_obj_in_cmd_hdr, din, opcode,
+			 MLX5_CMD_OP_DESTROY_PSV);
+		MLX5_SET(destroy_psv_in, din, psvn,
+			 MLX5_GET(create_psv_out, out, psv0_index));
+		break;
 	default:
 		/* The entry must match to one of the devx_is_obj_create_cmd */
 		WARN_ON(true);
@@ -2286,7 +2308,11 @@ static u32 devx_get_obj_id_from_event(unsigned long event_type, void *data)
 	case MLX5_EVENT_TYPE_WQ_ACCESS_ERROR:
 		obj_id = be32_to_cpu(eqe->data.qp_srq.qp_srq_n) & 0xffffff;
 		break;
+	case MLX5_EVENT_TYPE_XRQ_ERROR:
+		obj_id = be32_to_cpu(eqe->data.xrq_err.type_xrqn) & 0xffffff;
+		break;
 	case MLX5_EVENT_TYPE_DCT_DRAINED:
+	case MLX5_EVENT_TYPE_DCT_KEY_VIOLATION:
 		obj_id = be32_to_cpu(eqe->data.dct.dctn) & 0xffffff;
 		break;
 	case MLX5_EVENT_TYPE_CQ_ERROR:
diff --git a/drivers/infiniband/hw/mlx5/flow.c b/drivers/infiniband/hw/mlx5/flow.c
index 1c8f04abee0c..b198ff10cde9 100644
--- a/drivers/infiniband/hw/mlx5/flow.c
+++ b/drivers/infiniband/hw/mlx5/flow.c
@@ -32,6 +32,9 @@ mlx5_ib_ft_type_to_namespace(enum mlx5_ib_uapi_flow_table_type table_type,
 	case MLX5_IB_UAPI_FLOW_TABLE_TYPE_FDB:
 		*namespace = MLX5_FLOW_NAMESPACE_FDB;
 		break;
+	case MLX5_IB_UAPI_FLOW_TABLE_TYPE_RDMA_RX:
+		*namespace = MLX5_FLOW_NAMESPACE_RDMA_RX;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -101,6 +104,11 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_CREATE_FLOW)(
 	if (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_FDB && !dest_devx)
 		return -EINVAL;
 
+	/* Allow only DEVX object or QP as dest when inserting to RDMA_RX */
+	if ((fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_RDMA_RX) &&
+	    ((!dest_devx && !dest_qp) || (dest_devx && dest_qp)))
+		return -EINVAL;
+
 	if (dest_devx) {
 		devx_obj = uverbs_attr_get_obj(
 			attrs, MLX5_IB_ATTR_CREATE_FLOW_DEST_DEVX);
@@ -112,8 +120,9 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_CREATE_FLOW)(
 		 */
 		if (!mlx5_ib_devx_is_flow_dest(devx_obj, &dest_id, &dest_type))
 			return -EINVAL;
-		/* Allow only flow table as dest when inserting to FDB */
-		if (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_FDB &&
+		/* Allow only flow table as dest when inserting to FDB or RDMA_RX */
+		if ((fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_FDB ||
+		     fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_RDMA_RX) &&
 		    dest_type != MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE)
 			return -EINVAL;
 	} else if (dest_qp) {
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index bface798ee59..831539419c30 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -535,7 +535,7 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num,
 	props->max_msg_sz       = 1 << MLX5_CAP_GEN(dev->mdev, log_max_msg);
 	props->pkey_tbl_len     = 1;
 	props->state            = IB_PORT_DOWN;
-	props->phys_state       = 3;
+	props->phys_state       = IB_PORT_PHYS_STATE_DISABLED;
 
 	mlx5_query_nic_vport_qkey_viol_cntr(mdev, &qkey_viol_cntr);
 	props->qkey_viol_cntr = qkey_viol_cntr;
@@ -561,7 +561,7 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num,
 
 	if (netif_running(ndev) && netif_carrier_ok(ndev)) {
 		props->state      = IB_PORT_ACTIVE;
-		props->phys_state = 5;
+		props->phys_state = IB_PORT_PHYS_STATE_LINK_UP;
 	}
 
 	ndev_ib_mtu = iboe_get_mtu(ndev->mtu);
@@ -3971,6 +3971,11 @@ _get_flow_table(struct mlx5_ib_dev *dev,
 		    esw_encap)
 			flags |= MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT;
 		priority = FDB_BYPASS_PATH;
+	} else if (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_RDMA_RX) {
+		max_table_size =
+			BIT(MLX5_CAP_FLOWTABLE_RDMA_RX(dev->mdev,
+						       log_max_ft_size));
+		priority = fs_matcher->priority;
 	}
 
 	max_table_size = min_t(int, max_table_size, MLX5_FS_MAX_ENTRIES);
@@ -3985,6 +3990,8 @@ _get_flow_table(struct mlx5_ib_dev *dev,
 		prio = &dev->flow_db->egress_prios[priority];
 	else if (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_FDB)
 		prio = &dev->flow_db->fdb;
+	else if (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_RDMA_RX)
+		prio = &dev->flow_db->rdma_rx[priority];
 
 	if (!prio)
 		return ERR_PTR(-EINVAL);
@@ -5326,11 +5333,21 @@ static const struct mlx5_ib_counter ext_ppcnt_cnts[] = {
 	INIT_EXT_PPCNT_COUNTER(rx_icrc_encapsulated),
 };
 
+static bool is_mdev_switchdev_mode(const struct mlx5_core_dev *mdev)
+{
+	return MLX5_ESWITCH_MANAGER(mdev) &&
+	       mlx5_ib_eswitch_mode(mdev->priv.eswitch) ==
+		       MLX5_ESWITCH_OFFLOADS;
+}
+
 static void mlx5_ib_dealloc_counters(struct mlx5_ib_dev *dev)
 {
+	int num_cnt_ports;
 	int i;
 
-	for (i = 0; i < dev->num_ports; i++) {
+	num_cnt_ports = is_mdev_switchdev_mode(dev->mdev) ? 1 : dev->num_ports;
+
+	for (i = 0; i < num_cnt_ports; i++) {
 		if (dev->port[i].cnts.set_id_valid)
 			mlx5_core_dealloc_q_counter(dev->mdev,
 						    dev->port[i].cnts.set_id);
@@ -5432,13 +5449,15 @@ static void mlx5_ib_fill_counters(struct mlx5_ib_dev *dev,
 
 static int mlx5_ib_alloc_counters(struct mlx5_ib_dev *dev)
 {
+	int num_cnt_ports;
 	int err = 0;
 	int i;
 	bool is_shared;
 
 	is_shared = MLX5_CAP_GEN(dev->mdev, log_max_uctx) != 0;
+	num_cnt_ports = is_mdev_switchdev_mode(dev->mdev) ? 1 : dev->num_ports;
 
-	for (i = 0; i < dev->num_ports; i++) {
+	for (i = 0; i < num_cnt_ports; i++) {
 		err = __mlx5_ib_alloc_counters(dev, &dev->port[i].cnts);
 		if (err)
 			goto err_alloc;
@@ -5458,7 +5477,6 @@ static int mlx5_ib_alloc_counters(struct mlx5_ib_dev *dev)
 		}
 		dev->port[i].cnts.set_id_valid = true;
 	}
-
 	return 0;
 
 err_alloc:
@@ -5466,25 +5484,50 @@ err_alloc:
 	return err;
 }
 
+static const struct mlx5_ib_counters *get_counters(struct mlx5_ib_dev *dev,
+						   u8 port_num)
+{
+	return is_mdev_switchdev_mode(dev->mdev) ? &dev->port[0].cnts :
+						   &dev->port[port_num].cnts;
+}
+
+/**
+ * mlx5_ib_get_counters_id - Returns counters id to use for device+port
+ * @dev:	Pointer to mlx5 IB device
+ * @port_num:	Zero based port number
+ *
+ * mlx5_ib_get_counters_id() Returns counters set id to use for given
+ * device port combination in switchdev and non switchdev mode of the
+ * parent device.
+ */
+u16 mlx5_ib_get_counters_id(struct mlx5_ib_dev *dev, u8 port_num)
+{
+	const struct mlx5_ib_counters *cnts = get_counters(dev, port_num);
+
+	return cnts->set_id;
+}
+
 static struct rdma_hw_stats *mlx5_ib_alloc_hw_stats(struct ib_device *ibdev,
 						    u8 port_num)
 {
 	struct mlx5_ib_dev *dev = to_mdev(ibdev);
-	struct mlx5_ib_port *port = &dev->port[port_num - 1];
+	const struct mlx5_ib_counters *cnts;
+	bool is_switchdev = is_mdev_switchdev_mode(dev->mdev);
 
-	/* We support only per port stats */
-	if (port_num == 0)
+	if ((is_switchdev && port_num) || (!is_switchdev && !port_num))
 		return NULL;
 
-	return rdma_alloc_hw_stats_struct(port->cnts.names,
-					  port->cnts.num_q_counters +
-					  port->cnts.num_cong_counters +
-					  port->cnts.num_ext_ppcnt_counters,
+	cnts = get_counters(dev, port_num - 1);
+
+	return rdma_alloc_hw_stats_struct(cnts->names,
+					  cnts->num_q_counters +
+					  cnts->num_cong_counters +
+					  cnts->num_ext_ppcnt_counters,
 					  RDMA_HW_STATS_DEFAULT_LIFESPAN);
 }
 
 static int mlx5_ib_query_q_counters(struct mlx5_core_dev *mdev,
-				    struct mlx5_ib_port *port,
+				    const struct mlx5_ib_counters *cnts,
 				    struct rdma_hw_stats *stats,
 				    u16 set_id)
 {
@@ -5501,8 +5544,8 @@ static int mlx5_ib_query_q_counters(struct mlx5_core_dev *mdev,
 	if (ret)
 		goto free;
 
-	for (i = 0; i < port->cnts.num_q_counters; i++) {
-		val = *(__be32 *)(out + port->cnts.offsets[i]);
+	for (i = 0; i < cnts->num_q_counters; i++) {
+		val = *(__be32 *)(out + cnts->offsets[i]);
 		stats->value[i] = (u64)be32_to_cpu(val);
 	}
 
@@ -5512,10 +5555,10 @@ free:
 }
 
 static int mlx5_ib_query_ext_ppcnt_counters(struct mlx5_ib_dev *dev,
-					  struct mlx5_ib_port *port,
-					  struct rdma_hw_stats *stats)
+					    const struct mlx5_ib_counters *cnts,
+					    struct rdma_hw_stats *stats)
 {
-	int offset = port->cnts.num_q_counters + port->cnts.num_cong_counters;
+	int offset = cnts->num_q_counters + cnts->num_cong_counters;
 	int sz = MLX5_ST_SZ_BYTES(ppcnt_reg);
 	int ret, i;
 	void *out;
@@ -5528,12 +5571,10 @@ static int mlx5_ib_query_ext_ppcnt_counters(struct mlx5_ib_dev *dev,
 	if (ret)
 		goto free;
 
-	for (i = 0; i < port->cnts.num_ext_ppcnt_counters; i++) {
+	for (i = 0; i < cnts->num_ext_ppcnt_counters; i++)
 		stats->value[i + offset] =
 			be64_to_cpup((__be64 *)(out +
-				    port->cnts.offsets[i + offset]));
-	}
-
+				    cnts->offsets[i + offset]));
 free:
 	kvfree(out);
 	return ret;
@@ -5544,7 +5585,7 @@ static int mlx5_ib_get_hw_stats(struct ib_device *ibdev,
 				u8 port_num, int index)
 {
 	struct mlx5_ib_dev *dev = to_mdev(ibdev);
-	struct mlx5_ib_port *port = &dev->port[port_num - 1];
+	const struct mlx5_ib_counters *cnts = get_counters(dev, port_num - 1);
 	struct mlx5_core_dev *mdev;
 	int ret, num_counters;
 	u8 mdev_port_num;
@@ -5552,18 +5593,17 @@ static int mlx5_ib_get_hw_stats(struct ib_device *ibdev,
 	if (!stats)
 		return -EINVAL;
 
-	num_counters = port->cnts.num_q_counters +
-		       port->cnts.num_cong_counters +
-		       port->cnts.num_ext_ppcnt_counters;
+	num_counters = cnts->num_q_counters +
+		       cnts->num_cong_counters +
+		       cnts->num_ext_ppcnt_counters;
 
 	/* q_counters are per IB device, query the master mdev */
-	ret = mlx5_ib_query_q_counters(dev->mdev, port, stats,
-				       port->cnts.set_id);
+	ret = mlx5_ib_query_q_counters(dev->mdev, cnts, stats, cnts->set_id);
 	if (ret)
 		return ret;
 
 	if (MLX5_CAP_PCAM_FEATURE(dev->mdev, rx_icrc_encapsulated_counter)) {
-		ret =  mlx5_ib_query_ext_ppcnt_counters(dev, port, stats);
+		ret =  mlx5_ib_query_ext_ppcnt_counters(dev, cnts, stats);
 		if (ret)
 			return ret;
 	}
@@ -5580,10 +5620,10 @@ static int mlx5_ib_get_hw_stats(struct ib_device *ibdev,
 		}
 		ret = mlx5_lag_query_cong_counters(dev->mdev,
 						   stats->value +
-						   port->cnts.num_q_counters,
-						   port->cnts.num_cong_counters,
-						   port->cnts.offsets +
-						   port->cnts.num_q_counters);
+						   cnts->num_q_counters,
+						   cnts->num_cong_counters,
+						   cnts->offsets +
+						   cnts->num_q_counters);
 
 		mlx5_ib_put_native_port_mdev(dev, port_num);
 		if (ret)
@@ -5598,20 +5638,22 @@ static struct rdma_hw_stats *
 mlx5_ib_counter_alloc_stats(struct rdma_counter *counter)
 {
 	struct mlx5_ib_dev *dev = to_mdev(counter->device);
-	struct mlx5_ib_port *port = &dev->port[counter->port - 1];
+	const struct mlx5_ib_counters *cnts =
+		get_counters(dev, counter->port - 1);
 
 	/* Q counters are in the beginning of all counters */
-	return rdma_alloc_hw_stats_struct(port->cnts.names,
-					  port->cnts.num_q_counters,
+	return rdma_alloc_hw_stats_struct(cnts->names,
+					  cnts->num_q_counters,
 					  RDMA_HW_STATS_DEFAULT_LIFESPAN);
 }
 
 static int mlx5_ib_counter_update_stats(struct rdma_counter *counter)
 {
 	struct mlx5_ib_dev *dev = to_mdev(counter->device);
-	struct mlx5_ib_port *port = &dev->port[counter->port - 1];
+	const struct mlx5_ib_counters *cnts =
+		get_counters(dev, counter->port - 1);
 
-	return mlx5_ib_query_q_counters(dev->mdev, port,
+	return mlx5_ib_query_q_counters(dev->mdev, cnts,
 					counter->stats, counter->id);
 }
 
@@ -5788,7 +5830,6 @@ static void init_delay_drop(struct mlx5_ib_dev *dev)
 		mlx5_ib_warn(dev, "Failed to init delay drop debugfs\n");
 }
 
-/* The mlx5_ib_multiport_mutex should be held when calling this function */
 static void mlx5_ib_unbind_slave_port(struct mlx5_ib_dev *ibdev,
 				      struct mlx5_ib_multiport_info *mpi)
 {
@@ -5798,6 +5839,8 @@ static void mlx5_ib_unbind_slave_port(struct mlx5_ib_dev *ibdev,
 	int err;
 	int i;
 
+	lockdep_assert_held(&mlx5_ib_multiport_mutex);
+
 	mlx5_ib_cleanup_cong_debugfs(ibdev, port_num);
 
 	spin_lock(&port->mp.mpi_lock);
@@ -5847,13 +5890,14 @@ static void mlx5_ib_unbind_slave_port(struct mlx5_ib_dev *ibdev,
 	ibdev->port[port_num].roce.last_port_state = IB_PORT_DOWN;
 }
 
-/* The mlx5_ib_multiport_mutex should be held when calling this function */
 static bool mlx5_ib_bind_slave_port(struct mlx5_ib_dev *ibdev,
 				    struct mlx5_ib_multiport_info *mpi)
 {
 	u8 port_num = mlx5_core_native_port_num(mpi->mdev) - 1;
 	int err;
 
+	lockdep_assert_held(&mlx5_ib_multiport_mutex);
+
 	spin_lock(&ibdev->port[port_num].mp.mpi_lock);
 	if (ibdev->port[port_num].mp.mpi) {
 		mlx5_ib_dbg(ibdev, "port %d already affiliated.\n",
@@ -6882,7 +6926,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 	dev->port = kcalloc(num_ports, sizeof(*dev->port),
 			     GFP_KERNEL);
 	if (!dev->port) {
-		ib_dealloc_device((struct ib_device *)dev);
+		ib_dealloc_device(&dev->ib_dev);
 		return NULL;
 	}
 
@@ -6909,6 +6953,7 @@ static void mlx5_ib_remove(struct mlx5_core_dev *mdev, void *context)
 			mlx5_ib_unbind_slave_port(mpi->ibdev, mpi);
 		list_del(&mpi->list);
 		mutex_unlock(&mlx5_ib_multiport_mutex);
+		kfree(mpi);
 		return;
 	}
 
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 125a507c10ed..2ceaef3ea3fb 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -200,6 +200,7 @@ struct mlx5_ib_flow_db {
 	struct mlx5_ib_flow_prio	sniffer[MLX5_IB_NUM_SNIFFER_FTS];
 	struct mlx5_ib_flow_prio	egress[MLX5_IB_NUM_EGRESS_FTS];
 	struct mlx5_ib_flow_prio	fdb;
+	struct mlx5_ib_flow_prio	rdma_rx[MLX5_IB_NUM_FLOW_FT];
 	struct mlx5_flow_table		*lag_demux_ft;
 	/* Protect flow steering bypass flow tables
 	 * when add/del flow rules.
@@ -1476,6 +1477,7 @@ int bfregn_to_uar_index(struct mlx5_ib_dev *dev,
 			bool dyn_bfreg);
 
 int mlx5_ib_qp_set_counter(struct ib_qp *qp, struct rdma_counter *counter);
+u16 mlx5_ib_get_counters_id(struct mlx5_ib_dev *dev, u8 port_num);
 
 static inline bool mlx5_ib_can_use_umr(struct mlx5_ib_dev *dev,
 				       bool do_modify_atomic)
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index dd26e7acb37e..2e9b43061797 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -982,17 +982,6 @@ static int pagefault_data_segments(struct mlx5_ib_dev *dev,
 	return ret < 0 ? ret : npages;
 }
 
-static const u32 mlx5_ib_odp_opcode_cap[] = {
-	[MLX5_OPCODE_SEND]	       = IB_ODP_SUPPORT_SEND,
-	[MLX5_OPCODE_SEND_IMM]	       = IB_ODP_SUPPORT_SEND,
-	[MLX5_OPCODE_SEND_INVAL]       = IB_ODP_SUPPORT_SEND,
-	[MLX5_OPCODE_RDMA_WRITE]       = IB_ODP_SUPPORT_WRITE,
-	[MLX5_OPCODE_RDMA_WRITE_IMM]   = IB_ODP_SUPPORT_WRITE,
-	[MLX5_OPCODE_RDMA_READ]	       = IB_ODP_SUPPORT_READ,
-	[MLX5_OPCODE_ATOMIC_CS]	       = IB_ODP_SUPPORT_ATOMIC,
-	[MLX5_OPCODE_ATOMIC_FA]	       = IB_ODP_SUPPORT_ATOMIC,
-};
-
 /*
  * Parse initiator WQE. Advances the wqe pointer to point at the
  * scatter-gather list, and set wqe_end to the end of the WQE.
@@ -1003,12 +992,8 @@ static int mlx5_ib_mr_initiator_pfault_handler(
 {
 	struct mlx5_wqe_ctrl_seg *ctrl = *wqe;
 	u16 wqe_index = pfault->wqe.wqe_index;
-	u32 transport_caps;
 	struct mlx5_base_av *av;
 	unsigned ds, opcode;
-#if defined(DEBUG)
-	u32 ctrl_wqe_index, ctrl_qpn;
-#endif
 	u32 qpn = qp->trans_qp.base.mqp.qpn;
 
 	ds = be32_to_cpu(ctrl->qpn_ds) & MLX5_WQE_CTRL_DS_MASK;
@@ -1024,58 +1009,17 @@ static int mlx5_ib_mr_initiator_pfault_handler(
 		return -EFAULT;
 	}
 
-#if defined(DEBUG)
-	ctrl_wqe_index = (be32_to_cpu(ctrl->opmod_idx_opcode) &
-			MLX5_WQE_CTRL_WQE_INDEX_MASK) >>
-			MLX5_WQE_CTRL_WQE_INDEX_SHIFT;
-	if (wqe_index != ctrl_wqe_index) {
-		mlx5_ib_err(dev, "Got WQE with invalid wqe_index. wqe_index=0x%x, qpn=0x%x ctrl->wqe_index=0x%x\n",
-			    wqe_index, qpn,
-			    ctrl_wqe_index);
-		return -EFAULT;
-	}
-
-	ctrl_qpn = (be32_to_cpu(ctrl->qpn_ds) & MLX5_WQE_CTRL_QPN_MASK) >>
-		MLX5_WQE_CTRL_QPN_SHIFT;
-	if (qpn != ctrl_qpn) {
-		mlx5_ib_err(dev, "Got WQE with incorrect QP number. wqe_index=0x%x, qpn=0x%x ctrl->qpn=0x%x\n",
-			    wqe_index, qpn,
-			    ctrl_qpn);
-		return -EFAULT;
-	}
-#endif /* DEBUG */
-
 	*wqe_end = *wqe + ds * MLX5_WQE_DS_UNITS;
 	*wqe += sizeof(*ctrl);
 
 	opcode = be32_to_cpu(ctrl->opmod_idx_opcode) &
 		 MLX5_WQE_CTRL_OPCODE_MASK;
 
-	switch (qp->ibqp.qp_type) {
-	case IB_QPT_XRC_INI:
+	if (qp->ibqp.qp_type == IB_QPT_XRC_INI)
 		*wqe += sizeof(struct mlx5_wqe_xrc_seg);
-		transport_caps = dev->odp_caps.per_transport_caps.xrc_odp_caps;
-		break;
-	case IB_QPT_RC:
-		transport_caps = dev->odp_caps.per_transport_caps.rc_odp_caps;
-		break;
-	case IB_QPT_UD:
-		transport_caps = dev->odp_caps.per_transport_caps.ud_odp_caps;
-		break;
-	default:
-		mlx5_ib_err(dev, "ODP fault on QP of an unsupported transport 0x%x\n",
-			    qp->ibqp.qp_type);
-		return -EFAULT;
-	}
-
-	if (unlikely(opcode >= ARRAY_SIZE(mlx5_ib_odp_opcode_cap) ||
-		     !(transport_caps & mlx5_ib_odp_opcode_cap[opcode]))) {
-		mlx5_ib_err(dev, "ODP fault on QP of an unsupported opcode 0x%x\n",
-			    opcode);
-		return -EFAULT;
-	}
 
-	if (qp->ibqp.qp_type == IB_QPT_UD) {
+	if (qp->ibqp.qp_type == IB_QPT_UD ||
+	    qp->qp_sub_type == MLX5_IB_QPT_DCI) {
 		av = *wqe;
 		if (av->dqp_dct & cpu_to_be32(MLX5_EXTENDED_UD_AV))
 			*wqe += sizeof(struct mlx5_av);
@@ -1138,19 +1082,6 @@ static int mlx5_ib_mr_responder_pfault_handler_rq(struct mlx5_ib_dev *dev,
 		return -EFAULT;
 	}
 
-	switch (qp->ibqp.qp_type) {
-	case IB_QPT_RC:
-		if (!(dev->odp_caps.per_transport_caps.rc_odp_caps &
-		      IB_ODP_SUPPORT_RECV))
-			goto invalid_transport_or_opcode;
-		break;
-	default:
-invalid_transport_or_opcode:
-		mlx5_ib_err(dev, "ODP fault on QP of an unsupported transport. transport: 0x%x\n",
-			    qp->ibqp.qp_type);
-		return -EFAULT;
-	}
-
 	*wqe_end = wqe + wqe_size;
 
 	return 0;
@@ -1200,7 +1131,7 @@ static void mlx5_ib_mr_wqe_pfault_handler(struct mlx5_ib_dev *dev,
 {
 	bool sq = pfault->type & MLX5_PFAULT_REQUESTOR;
 	u16 wqe_index = pfault->wqe.wqe_index;
-	void *wqe = NULL, *wqe_end = NULL;
+	void *wqe, *wqe_start = NULL, *wqe_end = NULL;
 	u32 bytes_mapped, total_wqe_bytes;
 	struct mlx5_core_rsc_common *res;
 	int resume_with_error = 1;
@@ -1221,12 +1152,13 @@ static void mlx5_ib_mr_wqe_pfault_handler(struct mlx5_ib_dev *dev,
 		goto resolve_page_fault;
 	}
 
-	wqe = (void *)__get_free_page(GFP_KERNEL);
-	if (!wqe) {
+	wqe_start = (void *)__get_free_page(GFP_KERNEL);
+	if (!wqe_start) {
 		mlx5_ib_err(dev, "Error allocating memory for IO page fault handling.\n");
 		goto resolve_page_fault;
 	}
 
+	wqe = wqe_start;
 	qp = (res->res == MLX5_RES_QP) ? res_to_qp(res) : NULL;
 	if (qp && sq) {
 		ret = mlx5_ib_read_user_wqe_sq(qp, wqe_index, wqe, PAGE_SIZE,
@@ -1281,7 +1213,7 @@ resolve_page_fault:
 		    pfault->wqe.wq_num, resume_with_error,
 		    pfault->type);
 	mlx5_core_res_put(res);
-	free_page((unsigned long)wqe);
+	free_page((unsigned long)wqe_start);
 }
 
 static int pages_in_range(u64 address, u32 length)
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 72869ff4a334..8937d72ddcf6 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -3386,19 +3386,16 @@ static int __mlx5_ib_qp_set_counter(struct ib_qp *qp,
 	struct mlx5_ib_dev *dev = to_mdev(qp->device);
 	struct mlx5_ib_qp *mqp = to_mqp(qp);
 	struct mlx5_qp_context context = {};
-	struct mlx5_ib_port *mibport = NULL;
 	struct mlx5_ib_qp_base *base;
 	u32 set_id;
 
 	if (!MLX5_CAP_GEN(dev->mdev, rts2rts_qp_counters_set_id))
 		return 0;
 
-	if (counter) {
+	if (counter)
 		set_id = counter->id;
-	} else {
-		mibport = &dev->port[mqp->port - 1];
-		set_id = mibport->cnts.set_id;
-	}
+	else
+		set_id = mlx5_ib_get_counters_id(dev, mqp->port - 1);
 
 	base = &mqp->trans_qp.base;
 	context.qp_counter_set_usr_page &= cpu_to_be32(0xffffff);
@@ -3459,7 +3456,6 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 	struct mlx5_ib_cq *send_cq, *recv_cq;
 	struct mlx5_qp_context *context;
 	struct mlx5_ib_pd *pd;
-	struct mlx5_ib_port *mibport = NULL;
 	enum mlx5_qp_state mlx5_cur, mlx5_new;
 	enum mlx5_qp_optpar optpar;
 	u32 set_id = 0;
@@ -3624,11 +3620,10 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 		if (qp->flags & MLX5_IB_QP_UNDERLAY)
 			port_num = 0;
 
-		mibport = &dev->port[port_num];
 		if (ibqp->counter)
 			set_id = ibqp->counter->id;
 		else
-			set_id = mibport->cnts.set_id;
+			set_id = mlx5_ib_get_counters_id(dev, port_num);
 		context->qp_counter_set_usr_page |=
 			cpu_to_be32(set_id << 24);
 	}
@@ -3817,6 +3812,8 @@ static int mlx5_ib_modify_dct(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 
 	dctc = MLX5_ADDR_OF(create_dct_in, qp->dct.in, dct_context_entry);
 	if (cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT) {
+		u16 set_id;
+
 		required |= IB_QP_ACCESS_FLAGS | IB_QP_PKEY_INDEX | IB_QP_PORT;
 		if (!is_valid_mask(attr_mask, required, 0))
 			return -EINVAL;
@@ -3843,7 +3840,9 @@ static int mlx5_ib_modify_dct(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 		}
 		MLX5_SET(dctc, dctc, pkey_index, attr->pkey_index);
 		MLX5_SET(dctc, dctc, port, attr->port_num);
-		MLX5_SET(dctc, dctc, counter_set_id, dev->port[attr->port_num - 1].cnts.set_id);
+
+		set_id = mlx5_ib_get_counters_id(dev, attr->port_num - 1);
+		MLX5_SET(dctc, dctc, counter_set_id, set_id);
 
 	} else if (cur_state == IB_QPS_INIT && new_state == IB_QPS_RTR) {
 		struct mlx5_ib_modify_qp_resp resp = {};
@@ -6345,11 +6344,13 @@ int mlx5_ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *wq_attr,
 	}
 
 	if (curr_wq_state == IB_WQS_RESET && wq_state == IB_WQS_RDY) {
+		u16 set_id;
+
+		set_id = mlx5_ib_get_counters_id(dev, 0);
 		if (MLX5_CAP_GEN(dev->mdev, modify_rq_counter_set_id)) {
 			MLX5_SET64(modify_rq_in, in, modify_bitmask,
 				   MLX5_MODIFY_RQ_IN_MODIFY_BITMASK_RQ_COUNTER_SET_ID);
-			MLX5_SET(rqc, rqc, counter_set_id,
-				 dev->port->cnts.set_id);
+			MLX5_SET(rqc, rqc, counter_set_id, set_id);
 		} else
 			dev_info_once(
 				&dev->ib_dev.dev,