Introduce UCAP API and usage in mlx5

255 lines not on this page · raw message

index 85cfc790a7bb..973fe2c7ef53 100644
@@ -52,6 +52,7 @@
 #include <rdma/ib.h>
 #include <rdma/uverbs_std_types.h>
 #include <rdma/rdma_netlink.h>
+#include <rdma/ib_ucaps.h>
 
 #include "uverbs.h"
 #include "core_priv.h"

@@ -1345,6 +1346,7 @@ static void __exit ib_uverbs_cleanup(void)
 				 IB_UVERBS_NUM_FIXED_MINOR);
 	unregister_chrdev_region(dynamic_uverbs_dev,
 				 IB_UVERBS_NUM_DYNAMIC_MINOR);
+	ib_cleanup_ucaps();
 	mmu_notifier_synchronize();
 }
 

new file mode 100644
index 000000000000..d044d02f087f
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/*
+ * Copyright (c) 2025, NVIDIA CORPORATION & AFFILIATES. All rights reserved
+ */
+
+#ifndef _IB_UCAPS_H_
+#define _IB_UCAPS_H_
+
+#define UCAP_ENABLED(ucaps, type) (!!((ucaps) & (1U << type)))
+
+enum rdma_user_cap {
+	RDMA_UCAP_MLX5_CTRL_LOCAL,
+	RDMA_UCAP_MLX5_CTRL_OTHER_VHCA,
+	RDMA_UCAP_MAX
+};
+
+void ib_cleanup_ucaps(void);
+
+int ib_create_ucap(enum rdma_user_cap type);
+
+void ib_remove_ucap(enum rdma_user_cap type);
+
+int ib_get_ucaps(int *fds, int fd_count, uint64_t *idx_mask);
+
+#endif /* _IB_UCAPS_H_ */

index 5ad14c39d48c..96d639e1ffa0 100644
@@ -42,6 +42,7 @@
 
 #include <rdma/uverbs_types.h>
 #include <rdma/uverbs_std_types.h>
+#include <rdma/ib_ucaps.h>
 #include "rdma_core.h"
 
 #include "uverbs.h"

@@ -232,6 +233,8 @@ int ib_init_ucontext(struct uverbs_attr_bundle *attrs)
 {
 	struct ib_ucontext *ucontext = attrs->context;
 	struct ib_uverbs_file *file = attrs->ufile;
+	int *fd_array;
+	int fd_count;
 	int ret;
 
 	if (!down_read_trylock(&file->hw_destroy_rwsem))

@@ -247,6 +250,22 @@ int ib_init_ucontext(struct uverbs_attr_bundle *attrs)
 	if (ret)
 		goto err;
 
+	if (uverbs_attr_is_valid(attrs, UVERBS_ATTR_GET_CONTEXT_FD_ARR)) {
+		fd_count = uverbs_attr_ptr_get_array_size(attrs,
+							  UVERBS_ATTR_GET_CONTEXT_FD_ARR,
+							  sizeof(int));
+		if (fd_count < 0) {
+			ret = fd_count;
+			goto err_uncharge;
+		}
+
+		fd_array = uverbs_attr_get_alloced_ptr(attrs,
+						       UVERBS_ATTR_GET_CONTEXT_FD_ARR);
+		ret = ib_get_ucaps(fd_array, fd_count, &ucontext->enabled_caps);
+		if (ret)
+			goto err_uncharge;
+	}
+
 	ret = ucontext->device->ops.alloc_ucontext(ucontext,
 						   &attrs->driver_udata);
 	if (ret)

index fb0555647336..c0fd283d9d6c 100644
@@ -437,6 +437,10 @@ DECLARE_UVERBS_NAMED_METHOD(
 			    UVERBS_ATTR_TYPE(u32), UA_OPTIONAL),
 	UVERBS_ATTR_PTR_OUT(UVERBS_ATTR_GET_CONTEXT_CORE_SUPPORT,
 			    UVERBS_ATTR_TYPE(u64), UA_OPTIONAL),
+	UVERBS_ATTR_PTR_IN(UVERBS_ATTR_GET_CONTEXT_FD_ARR,
+			   UVERBS_ATTR_MIN_SIZE(sizeof(int)),
+			   UA_OPTIONAL,
+			   UA_ALLOC_AND_COPY),
 	UVERBS_ATTR_UHW());
 
 DECLARE_UVERBS_NAMED_METHOD(

index b59bf30de430..84b6d64c9e3a 100644
@@ -1530,6 +1530,7 @@ struct ib_ucontext {
 	struct ib_uverbs_file  *ufile;
 
 	struct ib_rdmacg_object	cg_obj;
+	u64 enabled_caps;
 	/*
 	 * Implementation details of the RDMA core, don't use in drivers:
 	 */

index ec719053aab9..ac7b162611ed 100644
@@ -88,6 +88,7 @@ enum uverbs_attrs_query_port_cmd_attr_ids {
 enum uverbs_attrs_get_context_attr_ids {
 	UVERBS_ATTR_GET_CONTEXT_NUM_COMP_VECTORS,
 	UVERBS_ATTR_GET_CONTEXT_CORE_SUPPORT,
+	UVERBS_ATTR_GET_CONTEXT_FD_ARR,
 };
 
 enum uverbs_attrs_query_context_attr_ids {

index 81849eb671a1..04b489a6a449 100644
@@ -47,6 +47,7 @@
 #include <rdma/uverbs_ioctl.h>
 #include <rdma/mlx5_user_ioctl_verbs.h>
 #include <rdma/mlx5_user_ioctl_cmds.h>
+#include <rdma/ib_ucaps.h>
 #include "macsec.h"
 #include "data_direct.h"
 

@@ -4201,8 +4202,47 @@ static int mlx5_ib_init_var_table(struct mlx5_ib_dev *dev)
 	return (var_table->bitmap) ? 0 : -ENOMEM;
 }
 
+static void mlx5_ib_cleanup_ucaps(struct mlx5_ib_dev *dev)
+{
+	if (MLX5_CAP_GEN(dev->mdev, uctx_cap) & MLX5_UCTX_CAP_RDMA_CTRL)
+		ib_remove_ucap(RDMA_UCAP_MLX5_CTRL_LOCAL);
+
+	if (MLX5_CAP_GEN(dev->mdev, uctx_cap) &
+	    MLX5_UCTX_CAP_RDMA_CTRL_OTHER_VHCA)
+		ib_remove_ucap(RDMA_UCAP_MLX5_CTRL_OTHER_VHCA);
+}
+
+static int mlx5_ib_init_ucaps(struct mlx5_ib_dev *dev)
+{
+	int ret;
+
+	if (MLX5_CAP_GEN(dev->mdev, uctx_cap) & MLX5_UCTX_CAP_RDMA_CTRL) {
+		ret = ib_create_ucap(RDMA_UCAP_MLX5_CTRL_LOCAL);
+		if (ret)
+			return ret;
+	}
+
+	if (MLX5_CAP_GEN(dev->mdev, uctx_cap) &
+	    MLX5_UCTX_CAP_RDMA_CTRL_OTHER_VHCA) {
+		ret = ib_create_ucap(RDMA_UCAP_MLX5_CTRL_OTHER_VHCA);
+		if (ret)
+			goto remove_local;
+	}
+
+	return 0;
+
+remove_local:
+	if (MLX5_CAP_GEN(dev->mdev, uctx_cap) & MLX5_UCTX_CAP_RDMA_CTRL)
+		ib_remove_ucap(RDMA_UCAP_MLX5_CTRL_LOCAL);
+	return ret;
+}
+
 static void mlx5_ib_stage_caps_cleanup(struct mlx5_ib_dev *dev)
 {
+	if (MLX5_CAP_GEN_2_64(dev->mdev, general_obj_types_127_64) &
+	    MLX5_HCA_CAP_2_GENERAL_OBJECT_TYPES_RDMA_CTRL)
+		mlx5_ib_cleanup_ucaps(dev);
+
 	bitmap_free(dev->var_table.bitmap);
 }
 

@@ -4253,6 +4293,13 @@ static int mlx5_ib_stage_caps_init(struct mlx5_ib_dev *dev)
 			return err;
 	}
 
+	if (MLX5_CAP_GEN_2_64(dev->mdev, general_obj_types_127_64) &
+	    MLX5_HCA_CAP_2_GENERAL_OBJECT_TYPES_RDMA_CTRL) {
+		err = mlx5_ib_init_ucaps(dev);
+		if (err)
+			return err;
+	}
+
 	dev->ib_dev.use_cq_dim = true;
 
 	return 0;

index 162814ae8cb4..6ae2801fa13f 100644
@@ -12,6 +12,7 @@
 #include <rdma/mlx5_user_ioctl_verbs.h>
 #include <rdma/ib_hdrs.h>
 #include <rdma/ib_umem.h>
+#include <rdma/ib_ucaps.h>
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/fs.h>
 #include <linux/mlx5/fs_helpers.h>

@@ -690,7 +691,7 @@ static struct mlx5_ib_flow_prio *_get_prio(struct mlx5_ib_dev *dev,
 					   struct mlx5_ib_flow_prio *prio,
 					   int priority,
 					   int num_entries, int num_groups,
-					   u32 flags)
+					   u32 flags, u16 vport)
 {
 	struct mlx5_flow_table_attr ft_attr = {};
 	struct mlx5_flow_table *ft;

@@ -698,6 +699,7 @@ static struct mlx5_ib_flow_prio *_get_prio(struct mlx5_ib_dev *dev,
 	ft_attr.prio = priority;
 	ft_attr.max_fte = num_entries;
 	ft_attr.flags = flags;
+	ft_attr.vport = vport;
 	ft_attr.autogroup.max_num_groups = num_groups;
 	ft = mlx5_create_auto_grouped_flow_table(ns, &ft_attr);
 	if (IS_ERR(ft))

@@ -792,7 +794,7 @@ static struct mlx5_ib_flow_prio *get_flow_table(struct mlx5_ib_dev *dev,
 	ft = prio->flow_table;
 	if (!ft)
 		return _get_prio(dev, ns, prio, priority, max_table_size,
-				 num_groups, flags);
+				 num_groups, flags, 0);
 
 	return prio;
 }

@@ -935,7 +937,7 @@ int mlx5_ib_fs_add_op_fc(struct mlx5_ib_dev *dev, u32 port_num,
 	prio = &dev->flow_db->opfcs[type];
 	if (!prio->flow_table) {
 		prio = _get_prio(dev, ns, prio, priority,
-				 dev->num_ports * MAX_OPFC_RULES, 1, 0);
+				 dev->num_ports * MAX_OPFC_RULES, 1, 0, 0);
 		if (IS_ERR(prio)) {
 			err = PTR_ERR(prio);
 			goto free;

@@ -1413,17 +1415,51 @@ static struct ib_flow *mlx5_ib_create_flow(struct ib_qp *qp,
 	return ERR_PTR(err);
 }
 
+static int mlx5_ib_fill_transport_ns_info(struct mlx5_ib_dev *dev,
+					  enum mlx5_flow_namespace_type type,
+					  u32 *flags, u16 *vport_idx,
+					  u16 *vport,
+					  struct mlx5_core_dev **ft_mdev,
+					  u32 ib_port)
+{
+	struct mlx5_core_dev *esw_mdev;
+
+	if (!is_mdev_switchdev_mode(dev->mdev))
+		return 0;
+
+	if (!MLX5_CAP_ADV_RDMA(dev->mdev, rdma_transport_manager))
+		return -EOPNOTSUPP;
+
+	if (!dev->port[ib_port - 1].rep)
+		return -EINVAL;
+
+	esw_mdev = mlx5_eswitch_get_core_dev(dev->port[ib_port - 1].rep->esw);
+	if (esw_mdev != dev->mdev)
+		return -EOPNOTSUPP;
+
+	*flags |= MLX5_FLOW_TABLE_OTHER_VPORT;
+	*ft_mdev = esw_mdev;
+	*vport = dev->port[ib_port - 1].rep->vport;
+	*vport_idx = dev->port[ib_port - 1].rep->vport_index;
+
+	return 0;
+}
+
 static struct mlx5_ib_flow_prio *
 _get_flow_table(struct mlx5_ib_dev *dev, u16 user_priority,
 		enum mlx5_flow_namespace_type ns_type,
-		bool mcast)
+		bool mcast, u32 ib_port)
 {
+	struct mlx5_core_dev *ft_mdev = dev->mdev;
 	struct mlx5_flow_namespace *ns = NULL;
 	struct mlx5_ib_flow_prio *prio = NULL;
 	int max_table_size = 0;
+	u16 vport_idx = 0;
 	bool esw_encap;
 	u32 flags = 0;
+	u16 vport = 0;
 	int priority;
+	int ret;
 
 	if (mcast)
 		priority = MLX5_IB_FLOW_MCAST_PRIO;

@@ -1471,13 +1507,38 @@ _get_flow_table(struct mlx5_ib_dev *dev, u16 user_priority,
 			MLX5_CAP_FLOWTABLE_RDMA_TX(dev->mdev, log_max_ft_size));
 		priority = user_priority;
 		break;
+	case MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_RX:
+	case MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_TX:
+		if (ib_port == 0 || user_priority > MLX5_RDMA_TRANSPORT_BYPASS_PRIO)
+			return ERR_PTR(-EINVAL);
+		ret = mlx5_ib_fill_transport_ns_info(dev, ns_type, &flags,
+						     &vport_idx, &vport,
+						     &ft_mdev, ib_port);
+		if (ret)
+			return ERR_PTR(ret);
+
+		if (ns_type == MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_RX)
+			max_table_size =
+				BIT(MLX5_CAP_FLOWTABLE_RDMA_TRANSPORT_RX(
+					ft_mdev, log_max_ft_size));
+		else
+			max_table_size =
+				BIT(MLX5_CAP_FLOWTABLE_RDMA_TRANSPORT_TX(
+					ft_mdev, log_max_ft_size));
+		priority = user_priority;
+		break;
 	default:
 		break;
 	}
 
 	max_table_size = min_t(int, max_table_size, MLX5_FS_MAX_ENTRIES);
 
-	ns = mlx5_get_flow_namespace(dev->mdev, ns_type);
+	if (ns_type == MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_RX ||
+	    ns_type == MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_TX)
+		ns = mlx5_get_flow_vport_namespace(ft_mdev, ns_type, vport_idx);
+	else
+		ns = mlx5_get_flow_namespace(ft_mdev, ns_type);
+
 	if (!ns)
 		return ERR_PTR(-EOPNOTSUPP);
 

@@ -1497,6 +1558,12 @@ _get_flow_table(struct mlx5_ib_dev *dev, u16 user_priority,
 	case MLX5_FLOW_NAMESPACE_RDMA_TX:
 		prio = &dev->flow_db->rdma_tx[priority];
 		break;
+	case MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_RX:
+		prio = &dev->flow_db->rdma_transport_rx[ib_port - 1];
+		break;
+	case MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_TX:
+		prio = &dev->flow_db->rdma_transport_tx[ib_port - 1];
+		break;
 	default: return ERR_PTR(-EINVAL);
 	}
 

@@ -1507,7 +1574,7 @@ _get_flow_table(struct mlx5_ib_dev *dev, u16 user_priority,
 		return prio;
 
 	return _get_prio(dev, ns, prio, priority, max_table_size,
-			 MLX5_FS_MAX_TYPES, flags);
+			 MLX5_FS_MAX_TYPES, flags, vport);
 }
 
 static struct mlx5_ib_flow_handler *

@@ -1626,7 +1693,8 @@ static struct mlx5_ib_flow_handler *raw_fs_rule_add(
 	mutex_lock(&dev->flow_db->lock);
 
 	ft_prio = _get_flow_table(dev, fs_matcher->priority,
-				  fs_matcher->ns_type, mcast);
+				  fs_matcher->ns_type, mcast,
+				  fs_matcher->ib_port);
 	if (IS_ERR(ft_prio)) {
 		err = PTR_ERR(ft_prio);
 		goto unlock;

@@ -1742,6 +1810,12 @@ mlx5_ib_ft_type_to_namespace(enum mlx5_ib_uapi_flow_table_type table_type,
 	case MLX5_IB_UAPI_FLOW_TABLE_TYPE_RDMA_TX:
 		*namespace = MLX5_FLOW_NAMESPACE_RDMA_TX;
 		break;
+	case MLX5_IB_UAPI_FLOW_TABLE_TYPE_RDMA_TRANSPORT_RX:
+		*namespace = MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_RX;
+		break;
+	case MLX5_IB_UAPI_FLOW_TABLE_TYPE_RDMA_TRANSPORT_TX:
+		*namespace = MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_TX;
+		break;
 	default:
 		return -EINVAL;
 	}

@@ -1831,7 +1905,8 @@ static int get_dests(struct uverbs_attr_bundle *attrs,
 		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) &&
+	if ((fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_RDMA_RX ||
+	     fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_RX) &&
 	    ((!dest_devx && !dest_qp) || (dest_devx && dest_qp)))
 		return -EINVAL;
 

@@ -1848,7 +1923,8 @@ static int get_dests(struct uverbs_attr_bundle *attrs,
 			return -EINVAL;
 		/* Allow only flow table as dest when inserting to FDB or RDMA_RX */
 		if ((fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_FDB_BYPASS ||
-		     fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_RDMA_RX) &&
+		     fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_RDMA_RX ||
+		     fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_RX) &&
 		    *dest_type != MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE)
 			return -EINVAL;
 	} else if (dest_qp) {

@@ -1869,14 +1945,16 @@ static int get_dests(struct uverbs_attr_bundle *attrs,
 			*dest_id = mqp->raw_packet_qp.rq.tirn;
 		*dest_type = MLX5_FLOW_DESTINATION_TYPE_TIR;
 	} else if ((fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_EGRESS ||
-		    fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_RDMA_TX) &&
+		    fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_RDMA_TX ||
+		    fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_TX) &&
 		   !(*flags & MLX5_IB_ATTR_CREATE_FLOW_FLAGS_DROP)) {
 		*dest_type = MLX5_FLOW_DESTINATION_TYPE_PORT;
 	}
 
 	if (*dest_type == MLX5_FLOW_DESTINATION_TYPE_TIR &&
 	    (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_EGRESS ||
-	     fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_RDMA_TX))
+	     fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_RDMA_TX ||
+	     fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_TX))
 		return -EINVAL;
 
 	return 0;

@@ -2353,6 +2431,15 @@ static int mlx5_ib_matcher_ns(struct uverbs_attr_bundle *attrs,
 	return 0;
 }
 
+static bool verify_context_caps(struct mlx5_ib_dev *dev, u64 enabled_caps)
+{
+	if (is_mdev_switchdev_mode(dev->mdev))
+		return UCAP_ENABLED(enabled_caps,
+				    RDMA_UCAP_MLX5_CTRL_OTHER_VHCA);
+
+	return UCAP_ENABLED(enabled_caps, RDMA_UCAP_MLX5_CTRL_LOCAL);
+}
+
 static int UVERBS_HANDLER(MLX5_IB_METHOD_FLOW_MATCHER_CREATE)(
 	struct uverbs_attr_bundle *attrs)
 {

@@ -2401,6 +2488,26 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_FLOW_MATCHER_CREATE)(
 		goto end;
 	}
 
+	if (uverbs_attr_is_valid(attrs, MLX5_IB_ATTR_FLOW_MATCHER_IB_PORT)) {
+		err = uverbs_copy_from(&obj->ib_port, attrs,
+				       MLX5_IB_ATTR_FLOW_MATCHER_IB_PORT);
+		if (err)
+			goto end;
+		if (!rdma_is_port_valid(&dev->ib_dev, obj->ib_port)) {
+			err = -EINVAL;
+			goto end;
+		}
+		if (obj->ns_type != MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_RX &&
+		    obj->ns_type != MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_TX) {
+			err = -EINVAL;
+			goto end;
+		}
+		if (!verify_context_caps(dev, uobj->context->enabled_caps)) {
+			err = -EOPNOTSUPP;
+			goto end;
+		}
+	}
+
 	uobj->object = obj;
 	obj->mdev = dev->mdev;
 	atomic_set(&obj->usecnt, 0);

@@ -2448,7 +2555,7 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_STEERING_ANCHOR_CREATE)(
 
 	mutex_lock(&dev->flow_db->lock);
 
-	ft_prio = _get_flow_table(dev, priority, ns_type, 0);
+	ft_prio = _get_flow_table(dev, priority, ns_type, 0, 0);
 	if (IS_ERR(ft_prio)) {
 		err = PTR_ERR(ft_prio);
 		goto free_obj;

@@ -2834,7 +2941,10 @@ DECLARE_UVERBS_NAMED_METHOD(
 			     UA_OPTIONAL),
 	UVERBS_ATTR_CONST_IN(MLX5_IB_ATTR_FLOW_MATCHER_FT_TYPE,
 			     enum mlx5_ib_uapi_flow_table_type,
-			     UA_OPTIONAL));
+			     UA_OPTIONAL),
+	UVERBS_ATTR_PTR_IN(MLX5_IB_ATTR_FLOW_MATCHER_IB_PORT,
+			   UVERBS_ATTR_TYPE(u32),
+			   UA_OPTIONAL));
 
 DECLARE_UVERBS_NAMED_METHOD_DESTROY(
 	MLX5_IB_METHOD_FLOW_MATCHER_DESTROY,

@@ -2904,8 +3014,26 @@ int mlx5_ib_fs_init(struct mlx5_ib_dev *dev)
 	if (!dev->flow_db)
 		return -ENOMEM;
 
+	dev->flow_db->rdma_transport_rx = kcalloc(dev->num_ports,
+					sizeof(struct mlx5_ib_flow_prio),
+					GFP_KERNEL);
+	if (!dev->flow_db->rdma_transport_rx)
+		goto free_flow_db;
+
+	dev->flow_db->rdma_transport_tx = kcalloc(dev->num_ports,
+					sizeof(struct mlx5_ib_flow_prio),
+					GFP_KERNEL);
+	if (!dev->flow_db->rdma_transport_tx)
+		goto free_rdma_transport_rx;
+
 	mutex_init(&dev->flow_db->lock);
 
 	ib_set_device_ops(&dev->ib_dev, &flow_ops);
 	return 0;
+
+free_rdma_transport_rx:
+	kfree(dev->flow_db->rdma_transport_rx);
+free_flow_db:
+	kfree(dev->flow_db);
+	return -ENOMEM;
 }

index b9734904f5f0..0516555eb1c1 100644
@@ -40,6 +40,8 @@ static inline void mlx5_ib_fs_cleanup(struct mlx5_ib_dev *dev)
 	 * is a safe assumption that all references are gone.
 	 */
 	mlx5_ib_fs_cleanup_anchor(dev);
+	kfree(dev->flow_db->rdma_transport_tx);
+	kfree(dev->flow_db->rdma_transport_rx);
 	kfree(dev->flow_db);
 }
 #endif /* _MLX5_IB_FS_H */

index 974a45c92fbb..ccaaef20f50d 100644
@@ -276,6 +276,7 @@ struct mlx5_ib_flow_matcher {
 	struct mlx5_core_dev	*mdev;
 	atomic_t		usecnt;
 	u8			match_criteria_enable;
+	u32			ib_port;
 };
 
 struct mlx5_ib_steering_anchor {

@@ -307,6 +308,8 @@ struct mlx5_ib_flow_db {
 	struct mlx5_ib_flow_prio	rdma_tx[MLX5_IB_NUM_FLOW_FT];
 	struct mlx5_ib_flow_prio	opfcs[MLX5_IB_OPCOUNTER_MAX];
 	struct mlx5_flow_table		*lag_demux_ft;
+	struct mlx5_ib_flow_prio        *rdma_transport_rx;
+	struct mlx5_ib_flow_prio        *rdma_transport_tx;
 	/* Protect flow steering bypass flow tables
 	 * when add/del flow rules.
 	 * only single add/removal of flow steering rule could be done

index fd2e4a3a56b3..18f9fe070213 100644
@@ -239,6 +239,7 @@ enum mlx5_ib_flow_matcher_create_attrs {
 	MLX5_IB_ATTR_FLOW_MATCHER_MATCH_CRITERIA,
 	MLX5_IB_ATTR_FLOW_MATCHER_FLOW_FLAGS,
 	MLX5_IB_ATTR_FLOW_MATCHER_FT_TYPE,
+	MLX5_IB_ATTR_FLOW_MATCHER_IB_PORT,
 };
 
 enum mlx5_ib_flow_matcher_destroy_attrs {

index 7c233df475e7..8f86e79d78a5 100644
@@ -45,6 +45,8 @@ enum mlx5_ib_uapi_flow_table_type {
 	MLX5_IB_UAPI_FLOW_TABLE_TYPE_FDB	= 0x2,
 	MLX5_IB_UAPI_FLOW_TABLE_TYPE_RDMA_RX	= 0x3,
 	MLX5_IB_UAPI_FLOW_TABLE_TYPE_RDMA_TX	= 0x4,
+	MLX5_IB_UAPI_FLOW_TABLE_TYPE_RDMA_TRANSPORT_RX	= 0x5,
+	MLX5_IB_UAPI_FLOW_TABLE_TYPE_RDMA_TRANSPORT_TX	= 0x6,
 };
 
 enum mlx5_ib_uapi_flow_action_packet_reformat_type {

index 4186884c66e1..5d42087c7777 100644
@@ -13,6 +13,7 @@
 #include <rdma/uverbs_std_types.h>
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/fs.h>
+#include <rdma/ib_ucaps.h>
 #include "mlx5_ib.h"
 #include "devx.h"
 #include "qp.h"

@@ -122,7 +123,27 @@ devx_ufile2uctx(const struct uverbs_attr_bundle *attrs)
 	return to_mucontext(ib_uverbs_get_ucontext(attrs));
 }
 
-int mlx5_ib_devx_create(struct mlx5_ib_dev *dev, bool is_user)
+static int set_uctx_ucaps(struct mlx5_ib_dev *dev, u64 req_ucaps, u32 *cap)
+{
+	if (UCAP_ENABLED(req_ucaps, RDMA_UCAP_MLX5_CTRL_LOCAL)) {
+		if (MLX5_CAP_GEN(dev->mdev, uctx_cap) & MLX5_UCTX_CAP_RDMA_CTRL)
+			*cap |= MLX5_UCTX_CAP_RDMA_CTRL;
+		else
+			return -EOPNOTSUPP;
+	}
+
+	if (UCAP_ENABLED(req_ucaps, RDMA_UCAP_MLX5_CTRL_OTHER_VHCA)) {
+		if (MLX5_CAP_GEN(dev->mdev, uctx_cap) &
+		    MLX5_UCTX_CAP_RDMA_CTRL_OTHER_VHCA)
+			*cap |= MLX5_UCTX_CAP_RDMA_CTRL_OTHER_VHCA;
+		else
+			return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+int mlx5_ib_devx_create(struct mlx5_ib_dev *dev, bool is_user, u64 req_ucaps)
 {
 	u32 in[MLX5_ST_SZ_DW(create_uctx_in)] = {};
 	u32 out[MLX5_ST_SZ_DW(create_uctx_out)] = {};

@@ -144,6 +165,12 @@ int mlx5_ib_devx_create(struct mlx5_ib_dev *dev, bool is_user)
 	     MLX5_UCTX_CAP_INTERNAL_DEV_RES))
 		cap |= MLX5_UCTX_CAP_INTERNAL_DEV_RES;
 
+	if (req_ucaps) {
+		err = set_uctx_ucaps(dev, req_ucaps, &cap);
+		if (err)
+			return err;
+	}
+
 	MLX5_SET(create_uctx_in, in, opcode, MLX5_CMD_OP_CREATE_UCTX);
 	MLX5_SET(uctx, uctx, cap, cap);
 

@@ -2573,7 +2600,7 @@ int mlx5_ib_devx_init(struct mlx5_ib_dev *dev)
 	struct mlx5_devx_event_table *table = &dev->devx_event_table;
 	int uid;
 
-	uid = mlx5_ib_devx_create(dev, false);
+	uid = mlx5_ib_devx_create(dev, false, 0);
 	if (uid > 0) {
 		dev->devx_whitelist_uid = uid;
 		xa_init(&table->event_xa);

index 1344bf4c9d21..ee9e7d3af93f 100644
@@ -24,13 +24,14 @@ struct devx_obj {
 	struct list_head event_sub; /* holds devx_event_subscription entries */
 };
 #if IS_ENABLED(CONFIG_INFINIBAND_USER_ACCESS)
-int mlx5_ib_devx_create(struct mlx5_ib_dev *dev, bool is_user);
+int mlx5_ib_devx_create(struct mlx5_ib_dev *dev, bool is_user, u64 req_ucaps);
 void mlx5_ib_devx_destroy(struct mlx5_ib_dev *dev, u16 uid);
 int mlx5_ib_devx_init(struct mlx5_ib_dev *dev);
 void mlx5_ib_devx_cleanup(struct mlx5_ib_dev *dev);
 void mlx5_ib_ufile_hw_cleanup(struct ib_uverbs_file *ufile);
 #else
-static inline int mlx5_ib_devx_create(struct mlx5_ib_dev *dev, bool is_user)
+static inline int mlx5_ib_devx_create(struct mlx5_ib_dev *dev, bool is_user,
+				      u64 req_ucaps)
 {
 	return -EOPNOTSUPP;
 }

index 04b489a6a449..d07cacaa0abd 100644
@@ -1935,6 +1935,12 @@ static int set_ucontext_resp(struct ib_ucontext *uctx,
 	return 0;
 }
 
+static bool uctx_rdma_ctrl_is_enabled(u64 enabled_caps)
+{
+	return UCAP_ENABLED(enabled_caps, RDMA_UCAP_MLX5_CTRL_LOCAL) ||
+	       UCAP_ENABLED(enabled_caps, RDMA_UCAP_MLX5_CTRL_OTHER_VHCA);
+}
+
 static int mlx5_ib_alloc_ucontext(struct ib_ucontext *uctx,
 				  struct ib_udata *udata)
 {

@@ -1977,10 +1983,17 @@ static int mlx5_ib_alloc_ucontext(struct ib_ucontext *uctx,
 		return -EINVAL;
 
 	if (req.flags & MLX5_IB_ALLOC_UCTX_DEVX) {
-		err = mlx5_ib_devx_create(dev, true);
+		err = mlx5_ib_devx_create(dev, true, uctx->enabled_caps);
 		if (err < 0)
 			goto out_ctx;
 		context->devx_uid = err;
+
+		if (uctx_rdma_ctrl_is_enabled(uctx->enabled_caps)) {
+			err = mlx5_cmd_add_privileged_uid(dev->mdev,
+							  context->devx_uid);
+			if (err)
+				goto out_devx;
+		}
 	}
 
 	lib_uar_4k = req.lib_caps & MLX5_LIB_CAP_4K_UAR;

@@ -1995,7 +2008,7 @@ static int mlx5_ib_alloc_ucontext(struct ib_ucontext *uctx,
 	/* updates req->total_num_bfregs */
 	err = calc_total_bfregs(dev, lib_uar_4k, &req, bfregi);
 	if (err)
-		goto out_devx;
+		goto out_ucap;
 
 	mutex_init(&bfregi->lock);
 	bfregi->lib_uar_4k = lib_uar_4k;

@@ -2003,7 +2016,7 @@ static int mlx5_ib_alloc_ucontext(struct ib_ucontext *uctx,
 				GFP_KERNEL);
 	if (!bfregi->count) {
 		err = -ENOMEM;
-		goto out_devx;
+		goto out_ucap;
 	}
 
 	bfregi->sys_pages = kcalloc(bfregi->num_sys_pages,

@@ -2067,6 +2080,11 @@ static int mlx5_ib_alloc_ucontext(struct ib_ucontext *uctx,
 out_count:
 	kfree(bfregi->count);
 
+out_ucap:
+	if (req.flags & MLX5_IB_ALLOC_UCTX_DEVX &&
+	    uctx_rdma_ctrl_is_enabled(uctx->enabled_caps))
+		mlx5_cmd_remove_privileged_uid(dev->mdev, context->devx_uid);
+
 out_devx:
 	if (req.flags & MLX5_IB_ALLOC_UCTX_DEVX)
 		mlx5_ib_devx_destroy(dev, context->devx_uid);

@@ -2111,8 +2129,12 @@ static void mlx5_ib_dealloc_ucontext(struct ib_ucontext *ibcontext)
 	kfree(bfregi->sys_pages);
 	kfree(bfregi->count);
 
-	if (context->devx_uid)
+	if (context->devx_uid) {
+		if (uctx_rdma_ctrl_is_enabled(ibcontext->enabled_caps))
+			mlx5_cmd_remove_privileged_uid(dev->mdev,
+						       context->devx_uid);
 		mlx5_ib_devx_destroy(dev, context->devx_uid);
+	}
 }
 
 static phys_addr_t uar_index2pfn(struct mlx5_ib_dev *dev,

index 82b1184891ed..e958bd6e34d7 100644
@@ -169,7 +169,9 @@ int ib_create_ucap(enum rdma_user_cap type)
        ucap->dev.class = &ucaps_class;
        ucap->dev.devt = MKDEV(MAJOR(ucaps_base_dev), type);
        ucap->dev.release = ucap_dev_release;
-       dev_set_name(&ucap->dev, ucap_names[type]);
+       ret = dev_set_name(&ucap->dev, ucap_names[type]);
+       if (ret)
+               goto err_device;
 
        cdev_init(&ucap->cdev, &ucaps_cdev_fops);
        ucap->cdev.owner = THIS_MODULE;