Merge branch 'mlx5-next' of https://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux

Leon Romanovsky says:

====================
mlx5-next changes

Following previous conversations [1] and our clear commitment to do
the TC work [2], please pull mlx5-next shared branch, which includes
low-level steering logic to allow RoCEv2 traffic to be encrypted/
decrypted through IPsec.

[1] https://lore.kernel.org/all/20230126230815.224239-1-saeed@kernel.org/
[2] https://lore.kernel.org/all/Y+Z7lVVWqnRBiPh2@nvidia.com/

* 'mlx5-next' of https://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux:
  net/mlx5: Configure IPsec steering for egress RoCEv2 traffic
  net/mlx5: Configure IPsec steering for ingress RoCEv2 traffic
  net/mlx5: Add IPSec priorities in RDMA namespaces
  net/mlx5: Implement new destination type TABLE_TYPE
  net/mlx5: Introduce new destination type TABLE_TYPE
====================

Link: https://lore.kernel.org/r/20230215095624.1365200-1-leon@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

12 files changed, 511 insertions, 15 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 06f511fcbd8e..8d4e25cc54ea 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -97,7 +97,7 @@ mlx5_core-$(CONFIG_MLX5_EN_MACSEC) += en_accel/macsec.o en_accel/macsec_fs.o \
 
 mlx5_core-$(CONFIG_MLX5_EN_IPSEC) += en_accel/ipsec.o en_accel/ipsec_rxtx.o \
 				     en_accel/ipsec_stats.o en_accel/ipsec_fs.o \
-				     en_accel/ipsec_offload.o
+				     en_accel/ipsec_offload.o lib/ipsec_fs_roce.o
 
 mlx5_core-$(CONFIG_MLX5_EN_TLS) += en_accel/ktls_stats.o \
 				   en_accel/fs_tcp.o en_accel/ktls.o en_accel/ktls_txrx.o \
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c
index 2732128e7a6e..6d73127b7217 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c
@@ -275,6 +275,10 @@ const char *parse_fs_dst(struct trace_seq *p,
 				 fs_dest_range_field_to_str(dst->range.field),
 				 dst->range.min, dst->range.max);
 		break;
+	case MLX5_FLOW_DESTINATION_TYPE_TABLE_TYPE:
+		trace_seq_printf(p, "flow_table_type=%u id:%u\n", dst->ft->type,
+				 dst->ft->id);
+		break;
 	case MLX5_FLOW_DESTINATION_TYPE_NONE:
 		trace_seq_printf(p, "none\n");
 		break;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
index 5233d4daca41..e5a44b0b9616 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
@@ -87,6 +87,7 @@ enum {
 	MLX5E_ACCEL_FS_POL_FT_LEVEL = MLX5E_INNER_TTC_FT_LEVEL + 1,
 	MLX5E_ACCEL_FS_ESP_FT_LEVEL,
 	MLX5E_ACCEL_FS_ESP_FT_ERR_LEVEL,
+	MLX5E_ACCEL_FS_ESP_FT_ROCE_LEVEL,
 #endif
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
index b387adca9c20..ddd7be05f18f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
@@ -93,6 +93,7 @@ enum mlx5_ipsec_cap {
 	MLX5_IPSEC_CAP_CRYPTO		= 1 << 0,
 	MLX5_IPSEC_CAP_ESN		= 1 << 1,
 	MLX5_IPSEC_CAP_PACKET_OFFLOAD	= 1 << 2,
+	MLX5_IPSEC_CAP_ROCE             = 1 << 3,
 };
 
 struct mlx5e_priv;
@@ -147,6 +148,7 @@ struct mlx5e_ipsec {
 	struct mlx5e_ipsec_tx *tx;
 	struct mlx5e_ipsec_aso *aso;
 	struct notifier_block nb;
+	struct mlx5_ipsec_fs *roce;
 };
 
 struct mlx5e_ipsec_esn_state {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index 5da6fe68eea6..9871ba1b25ff 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -6,6 +6,7 @@
 #include "en/fs.h"
 #include "ipsec.h"
 #include "fs_core.h"
+#include "lib/ipsec_fs_roce.h"
 
 #define NUM_IPSEC_FTE BIT(15)
 
@@ -166,7 +167,8 @@ out:
 	return err;
 }
 
-static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec_rx *rx)
+static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
+		       struct mlx5e_ipsec_rx *rx, u32 family)
 {
 	mlx5_del_flow_rules(rx->pol.rule);
 	mlx5_destroy_flow_group(rx->pol.group);
@@ -179,6 +181,8 @@ static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec_rx *rx)
 	mlx5_del_flow_rules(rx->status.rule);
 	mlx5_modify_header_dealloc(mdev, rx->status.modify_hdr);
 	mlx5_destroy_flow_table(rx->ft.status);
+
+	mlx5_ipsec_fs_roce_rx_destroy(ipsec->roce, family);
 }
 
 static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
@@ -186,18 +190,35 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 {
 	struct mlx5_flow_namespace *ns = mlx5e_fs_get_ns(ipsec->fs, false);
 	struct mlx5_ttc_table *ttc = mlx5e_fs_get_ttc(ipsec->fs, false);
+	struct mlx5_flow_destination default_dest;
 	struct mlx5_flow_destination dest[2];
 	struct mlx5_flow_table *ft;
 	int err;
 
+	default_dest = mlx5_ttc_get_default_dest(ttc, family2tt(family));
+	err = mlx5_ipsec_fs_roce_rx_create(mdev, ipsec->roce, ns, &default_dest,
+					   family, MLX5E_ACCEL_FS_ESP_FT_ROCE_LEVEL,
+					   MLX5E_NIC_PRIO);
+	if (err)
+		return err;
+
 	ft = ipsec_ft_create(ns, MLX5E_ACCEL_FS_ESP_FT_ERR_LEVEL,
 			     MLX5E_NIC_PRIO, 1);
-	if (IS_ERR(ft))
-		return PTR_ERR(ft);
+	if (IS_ERR(ft)) {
+		err = PTR_ERR(ft);
+		goto err_fs_ft_status;
+	}
 
 	rx->ft.status = ft;
 
-	dest[0] = mlx5_ttc_get_default_dest(ttc, family2tt(family));
+	ft = mlx5_ipsec_fs_roce_ft_get(ipsec->roce, family);
+	if (ft) {
+		dest[0].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+		dest[0].ft = ft;
+	} else {
+		dest[0] = default_dest;
+	}
+
 	dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
 	dest[1].counter_id = mlx5_fc_id(rx->fc->cnt);
 	err = ipsec_status_rule(mdev, rx, dest);
@@ -245,6 +266,8 @@ err_fs_ft:
 	mlx5_modify_header_dealloc(mdev, rx->status.modify_hdr);
 err_add:
 	mlx5_destroy_flow_table(rx->ft.status);
+err_fs_ft_status:
+	mlx5_ipsec_fs_roce_rx_destroy(ipsec->roce, family);
 	return err;
 }
 
@@ -304,14 +327,15 @@ static void rx_ft_put(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	mlx5_ttc_fwd_default_dest(ttc, family2tt(family));
 
 	/* remove FT */
-	rx_destroy(mdev, rx);
+	rx_destroy(mdev, ipsec, rx, family);
 
 out:
 	mutex_unlock(&rx->ft.mutex);
 }
 
 /* IPsec TX flow steering */
-static int tx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec_tx *tx)
+static int tx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec_tx *tx,
+		     struct mlx5_ipsec_fs *roce)
 {
 	struct mlx5_flow_destination dest = {};
 	struct mlx5_flow_table *ft;
@@ -334,8 +358,15 @@ static int tx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec_tx *tx)
 	err = ipsec_miss_create(mdev, tx->ft.pol, &tx->pol, &dest);
 	if (err)
 		goto err_pol_miss;
+
+	err = mlx5_ipsec_fs_roce_tx_create(mdev, roce, tx->ft.pol);
+	if (err)
+		goto err_roce;
 	return 0;
 
+err_roce:
+	mlx5_del_flow_rules(tx->pol.rule);
+	mlx5_destroy_flow_group(tx->pol.group);
 err_pol_miss:
 	mlx5_destroy_flow_table(tx->ft.pol);
 err_pol_ft:
@@ -353,9 +384,10 @@ static struct mlx5e_ipsec_tx *tx_ft_get(struct mlx5_core_dev *mdev,
 	if (tx->ft.refcnt)
 		goto skip;
 
-	err = tx_create(mdev, tx);
+	err = tx_create(mdev, tx, ipsec->roce);
 	if (err)
 		goto out;
+
 skip:
 	tx->ft.refcnt++;
 out:
@@ -374,6 +406,7 @@ static void tx_ft_put(struct mlx5e_ipsec *ipsec)
 	if (tx->ft.refcnt)
 		goto out;
 
+	mlx5_ipsec_fs_roce_tx_destroy(ipsec->roce);
 	mlx5_del_flow_rules(tx->pol.rule);
 	mlx5_destroy_flow_group(tx->pol.group);
 	mlx5_destroy_flow_table(tx->ft.pol);
@@ -1031,6 +1064,9 @@ void mlx5e_accel_ipsec_fs_cleanup(struct mlx5e_ipsec *ipsec)
 	if (!ipsec->tx)
 		return;
 
+	if (mlx5_ipsec_device_caps(ipsec->mdev) & MLX5_IPSEC_CAP_ROCE)
+		mlx5_ipsec_fs_roce_cleanup(ipsec->roce);
+
 	ipsec_fs_destroy_counters(ipsec);
 	mutex_destroy(&ipsec->tx->ft.mutex);
 	WARN_ON(ipsec->tx->ft.refcnt);
@@ -1047,6 +1083,7 @@ void mlx5e_accel_ipsec_fs_cleanup(struct mlx5e_ipsec *ipsec)
 
 int mlx5e_accel_ipsec_fs_init(struct mlx5e_ipsec *ipsec)
 {
+	struct mlx5_core_dev *mdev = ipsec->mdev;
 	struct mlx5_flow_namespace *ns;
 	int err = -ENOMEM;
 
@@ -1076,6 +1113,9 @@ int mlx5e_accel_ipsec_fs_init(struct mlx5e_ipsec *ipsec)
 	mutex_init(&ipsec->rx_ipv6->ft.mutex);
 	ipsec->tx->ns = ns;
 
+	if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_ROCE)
+		ipsec->roce = mlx5_ipsec_fs_roce_init(mdev);
+
 	return 0;
 
 err_counters:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
index 7fb3835befbd..5fa7a4c40429 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
@@ -42,6 +42,11 @@ u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev)
 	    MLX5_CAP_FLOWTABLE_NIC_RX(mdev, decap))
 		caps |= MLX5_IPSEC_CAP_PACKET_OFFLOAD;
 
+	if (mlx5_get_roce_state(mdev) &&
+	    MLX5_CAP_GEN_2(mdev, flow_table_type_2_type) & MLX5_FT_NIC_RX_2_NIC_RX_RDMA &&
+	    MLX5_CAP_GEN_2(mdev, flow_table_type_2_type) & MLX5_FT_NIC_TX_RDMA_2_NIC_TX)
+		caps |= MLX5_IPSEC_CAP_ROCE;
+
 	if (!caps)
 		return 0;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index 374c17445e54..144e59480686 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -646,6 +646,12 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 				id = dst->dest_attr.sampler_id;
 				ifc_type = MLX5_IFC_FLOW_DESTINATION_TYPE_FLOW_SAMPLER;
 				break;
+			case MLX5_FLOW_DESTINATION_TYPE_TABLE_TYPE:
+				MLX5_SET(dest_format_struct, in_dests,
+					 destination_table_type, dst->dest_attr.ft->type);
+				id = dst->dest_attr.ft->id;
+				ifc_type = MLX5_IFC_FLOW_DESTINATION_TYPE_TABLE_TYPE;
+				break;
 			default:
 				id = dst->dest_attr.tir_num;
 				ifc_type = MLX5_IFC_FLOW_DESTINATION_TYPE_TIR;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index fad479df12e4..731acbe22dc7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -113,8 +113,10 @@
 #define ETHTOOL_PRIO_NUM_LEVELS 1
 #define ETHTOOL_NUM_PRIOS 11
 #define ETHTOOL_MIN_LEVEL (KERNEL_MIN_LEVEL + ETHTOOL_NUM_PRIOS)
-/* Promiscuous, Vlan, mac, ttc, inner ttc, {UDP/ANY/aRFS/accel/{esp, esp_err}}, IPsec policy */
-#define KERNEL_NIC_PRIO_NUM_LEVELS 8
+/* Promiscuous, Vlan, mac, ttc, inner ttc, {UDP/ANY/aRFS/accel/{esp, esp_err}}, IPsec policy,
+ * IPsec RoCE policy
+ */
+#define KERNEL_NIC_PRIO_NUM_LEVELS 9
 #define KERNEL_NIC_NUM_PRIOS 1
 /* One more level for tc */
 #define KERNEL_MIN_LEVEL (KERNEL_NIC_PRIO_NUM_LEVELS + 1)
@@ -221,19 +223,30 @@ static struct init_tree_node egress_root_fs = {
 };
 
 enum {
+	RDMA_RX_IPSEC_PRIO,
 	RDMA_RX_COUNTERS_PRIO,
 	RDMA_RX_BYPASS_PRIO,
 	RDMA_RX_KERNEL_PRIO,
 };
 
+#define RDMA_RX_IPSEC_NUM_PRIOS 1
+#define RDMA_RX_IPSEC_NUM_LEVELS 2
+#define RDMA_RX_IPSEC_MIN_LEVEL  (RDMA_RX_IPSEC_NUM_LEVELS)
+
 #define RDMA_RX_BYPASS_MIN_LEVEL MLX5_BY_PASS_NUM_REGULAR_PRIOS
 #define RDMA_RX_KERNEL_MIN_LEVEL (RDMA_RX_BYPASS_MIN_LEVEL + 1)
 #define RDMA_RX_COUNTERS_MIN_LEVEL (RDMA_RX_KERNEL_MIN_LEVEL + 2)
 
 static struct init_tree_node rdma_rx_root_fs = {
 	.type = FS_TYPE_NAMESPACE,
-	.ar_size = 3,
+	.ar_size = 4,
 	.children = (struct init_tree_node[]) {
+		[RDMA_RX_IPSEC_PRIO] =
+		ADD_PRIO(0, RDMA_RX_IPSEC_MIN_LEVEL, 0,
+			 FS_CHAINING_CAPS,
+			 ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF,
+				ADD_MULTIPLE_PRIO(RDMA_RX_IPSEC_NUM_PRIOS,
+						  RDMA_RX_IPSEC_NUM_LEVELS))),
 		[RDMA_RX_COUNTERS_PRIO] =
 		ADD_PRIO(0, RDMA_RX_COUNTERS_MIN_LEVEL, 0,
 			 FS_CHAINING_CAPS,
@@ -256,15 +269,20 @@ static struct init_tree_node rdma_rx_root_fs = {
 
 enum {
 	RDMA_TX_COUNTERS_PRIO,
+	RDMA_TX_IPSEC_PRIO,
 	RDMA_TX_BYPASS_PRIO,
 };
 
 #define RDMA_TX_BYPASS_MIN_LEVEL MLX5_BY_PASS_NUM_PRIOS
 #define RDMA_TX_COUNTERS_MIN_LEVEL (RDMA_TX_BYPASS_MIN_LEVEL + 1)
 
+#define RDMA_TX_IPSEC_NUM_PRIOS 1
+#define RDMA_TX_IPSEC_PRIO_NUM_LEVELS 1
+#define RDMA_TX_IPSEC_MIN_LEVEL  (RDMA_TX_COUNTERS_MIN_LEVEL + RDMA_TX_IPSEC_NUM_PRIOS)
+
 static struct init_tree_node rdma_tx_root_fs = {
 	.type = FS_TYPE_NAMESPACE,
-	.ar_size = 2,
+	.ar_size = 3,
 	.children = (struct init_tree_node[]) {
 		[RDMA_TX_COUNTERS_PRIO] =
 		ADD_PRIO(0, RDMA_TX_COUNTERS_MIN_LEVEL, 0,
@@ -272,6 +290,13 @@ static struct init_tree_node rdma_tx_root_fs = {
 			 ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF,
 				ADD_MULTIPLE_PRIO(MLX5_RDMA_TX_NUM_COUNTERS_PRIOS,
 						  RDMA_TX_COUNTERS_PRIO_NUM_LEVELS))),
+		[RDMA_TX_IPSEC_PRIO] =
+		ADD_PRIO(0, RDMA_TX_IPSEC_MIN_LEVEL, 0,
+			 FS_CHAINING_CAPS,
+			 ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF,
+				ADD_MULTIPLE_PRIO(RDMA_TX_IPSEC_NUM_PRIOS,
+						  RDMA_TX_IPSEC_PRIO_NUM_LEVELS))),
+
 		[RDMA_TX_BYPASS_PRIO] =
 		ADD_PRIO(0, RDMA_TX_BYPASS_MIN_LEVEL, 0,
 			 FS_CHAINING_CAPS_RDMA_TX,
@@ -451,7 +476,8 @@ static bool is_fwd_dest_type(enum mlx5_flow_destination_type type)
 		type == MLX5_FLOW_DESTINATION_TYPE_VPORT ||
 		type == MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER ||
 		type == MLX5_FLOW_DESTINATION_TYPE_TIR ||
-		type == MLX5_FLOW_DESTINATION_TYPE_RANGE;
+		type == MLX5_FLOW_DESTINATION_TYPE_RANGE ||
+		type == MLX5_FLOW_DESTINATION_TYPE_TABLE_TYPE;
 }
 
 static bool check_valid_spec(const struct mlx5_flow_spec *spec)
@@ -2368,6 +2394,14 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev,
 		root_ns = steering->rdma_tx_root_ns;
 		prio = RDMA_TX_COUNTERS_PRIO;
 		break;
+	case MLX5_FLOW_NAMESPACE_RDMA_RX_IPSEC:
+		root_ns = steering->rdma_rx_root_ns;
+		prio = RDMA_RX_IPSEC_PRIO;
+		break;
+	case MLX5_FLOW_NAMESPACE_RDMA_TX_IPSEC:
+		root_ns = steering->rdma_tx_root_ns;
+		prio = RDMA_TX_IPSEC_PRIO;
+		break;
 	default: /* Must be NIC RX */
 		WARN_ON(!is_nic_rx_ns(type));
 		root_ns = steering->root_ns;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c
new file mode 100644
index 000000000000..2c53589b765d
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c
@@ -0,0 +1,368 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#include "fs_core.h"
+#include "lib/ipsec_fs_roce.h"
+#include "mlx5_core.h"
+
+struct mlx5_ipsec_miss {
+	struct mlx5_flow_group *group;
+	struct mlx5_flow_handle *rule;
+};
+
+struct mlx5_ipsec_rx_roce {
+	struct mlx5_flow_group *g;
+	struct mlx5_flow_table *ft;
+	struct mlx5_flow_handle *rule;
+	struct mlx5_ipsec_miss roce_miss;
+
+	struct mlx5_flow_table *ft_rdma;
+	struct mlx5_flow_namespace *ns_rdma;
+};
+
+struct mlx5_ipsec_tx_roce {
+	struct mlx5_flow_group *g;
+	struct mlx5_flow_table *ft;
+	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_namespace *ns;
+};
+
+struct mlx5_ipsec_fs {
+	struct mlx5_ipsec_rx_roce ipv4_rx;
+	struct mlx5_ipsec_rx_roce ipv6_rx;
+	struct mlx5_ipsec_tx_roce tx;
+};
+
+static void ipsec_fs_roce_setup_udp_dport(struct mlx5_flow_spec *spec,
+					  u16 dport)
+{
+	spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS;
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ip_protocol);
+	MLX5_SET(fte_match_param, spec->match_value, outer_headers.ip_protocol, IPPROTO_UDP);
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.udp_dport);
+	MLX5_SET(fte_match_param, spec->match_value, outer_headers.udp_dport, dport);
+}
+
+static int
+ipsec_fs_roce_rx_rule_setup(struct mlx5_core_dev *mdev,
+			    struct mlx5_flow_destination *default_dst,
+			    struct mlx5_ipsec_rx_roce *roce)
+{
+	struct mlx5_flow_destination dst = {};
+	MLX5_DECLARE_FLOW_ACT(flow_act);
+	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_spec *spec;
+	int err = 0;
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec)
+		return -ENOMEM;
+
+	ipsec_fs_roce_setup_udp_dport(spec, ROCE_V2_UDP_DPORT);
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	dst.type = MLX5_FLOW_DESTINATION_TYPE_TABLE_TYPE;
+	dst.ft = roce->ft_rdma;
+	rule = mlx5_add_flow_rules(roce->ft, spec, &flow_act, &dst, 1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_err(mdev, "Fail to add RX RoCE IPsec rule err=%d\n",
+			      err);
+		goto fail_add_rule;
+	}
+
+	roce->rule = rule;
+
+	memset(spec, 0, sizeof(*spec));
+	rule = mlx5_add_flow_rules(roce->ft, spec, &flow_act, default_dst, 1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_err(mdev, "Fail to add RX RoCE IPsec miss rule err=%d\n",
+			      err);
+		goto fail_add_default_rule;
+	}
+
+	roce->roce_miss.rule = rule;
+
+	kvfree(spec);
+	return 0;
+
+fail_add_default_rule:
+	mlx5_del_flow_rules(roce->rule);
+fail_add_rule:
+	kvfree(spec);
+	return err;
+}
+
+static int ipsec_fs_roce_tx_rule_setup(struct mlx5_core_dev *mdev,
+				       struct mlx5_ipsec_tx_roce *roce,
+				       struct mlx5_flow_table *pol_ft)
+{
+	struct mlx5_flow_destination dst = {};
+	MLX5_DECLARE_FLOW_ACT(flow_act);
+	struct mlx5_flow_handle *rule;
+	int err = 0;
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	dst.type = MLX5_FLOW_DESTINATION_TYPE_TABLE_TYPE;
+	dst.ft = pol_ft;
+	rule = mlx5_add_flow_rules(roce->ft, NULL, &flow_act, &dst,
+				   1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_err(mdev, "Fail to add TX RoCE IPsec rule err=%d\n",
+			      err);
+		goto out;
+	}
+	roce->rule = rule;
+
+out:
+	return err;
+}
+
+void mlx5_ipsec_fs_roce_tx_destroy(struct mlx5_ipsec_fs *ipsec_roce)
+{
+	struct mlx5_ipsec_tx_roce *tx_roce;
+
+	if (!ipsec_roce)
+		return;
+
+	tx_roce = &ipsec_roce->tx;
+
+	mlx5_del_flow_rules(tx_roce->rule);
+	mlx5_destroy_flow_group(tx_roce->g);
+	mlx5_destroy_flow_table(tx_roce->ft);
+}
+
+#define MLX5_TX_ROCE_GROUP_SIZE BIT(0)
+
+int mlx5_ipsec_fs_roce_tx_create(struct mlx5_core_dev *mdev,
+				 struct mlx5_ipsec_fs *ipsec_roce,
+				 struct mlx5_flow_table *pol_ft)
+{
+	struct mlx5_flow_table_attr ft_attr = {};
+	struct mlx5_ipsec_tx_roce *roce;
+	struct mlx5_flow_table *ft;
+	struct mlx5_flow_group *g;
+	int ix = 0;
+	int err;
+	u32 *in;
+
+	if (!ipsec_roce)
+		return 0;
+
+	roce = &ipsec_roce->tx;
+
+	in = kvzalloc(MLX5_ST_SZ_BYTES(create_flow_group_in), GFP_KERNEL);
+	if (!in)
+		return -ENOMEM;
+
+	ft_attr.max_fte = 1;
+	ft = mlx5_create_flow_table(roce->ns, &ft_attr);
+	if (IS_ERR(ft)) {
+		err = PTR_ERR(ft);
+		mlx5_core_err(mdev, "Fail to create RoCE IPsec tx ft err=%d\n", err);
+		return err;
+	}
+
+	roce->ft = ft;
+
+	MLX5_SET_CFG(in, start_flow_index, ix);
+	ix += MLX5_TX_ROCE_GROUP_SIZE;
+	MLX5_SET_CFG(in, end_flow_index, ix - 1);
+	g = mlx5_create_flow_group(ft, in);
+	if (IS_ERR(g)) {
+		err = PTR_ERR(g);
+		mlx5_core_err(mdev, "Fail to create RoCE IPsec tx group err=%d\n", err);
+		goto fail;
+	}
+	roce->g = g;
+
+	err = ipsec_fs_roce_tx_rule_setup(mdev, roce, pol_ft);
+	if (err) {
+		mlx5_core_err(mdev, "Fail to create RoCE IPsec tx rules err=%d\n", err);
+		goto rule_fail;
+	}
+
+	return 0;
+
+rule_fail:
+	mlx5_destroy_flow_group(roce->g);
+fail:
+	mlx5_destroy_flow_table(ft);
+	return err;
+}
+
+struct mlx5_flow_table *mlx5_ipsec_fs_roce_ft_get(struct mlx5_ipsec_fs *ipsec_roce, u32 family)
+{
+	struct mlx5_ipsec_rx_roce *rx_roce;
+
+	if (!ipsec_roce)
+		return NULL;
+
+	rx_roce = (family == AF_INET) ? &ipsec_roce->ipv4_rx :
+					&ipsec_roce->ipv6_rx;
+
+	return rx_roce->ft;
+}
+
+void mlx5_ipsec_fs_roce_rx_destroy(struct mlx5_ipsec_fs *ipsec_roce, u32 family)
+{
+	struct mlx5_ipsec_rx_roce *rx_roce;
+
+	if (!ipsec_roce)
+		return;
+
+	rx_roce = (family == AF_INET) ? &ipsec_roce->ipv4_rx :
+					&ipsec_roce->ipv6_rx;
+
+	mlx5_del_flow_rules(rx_roce->roce_miss.rule);
+	mlx5_del_flow_rules(rx_roce->rule);
+	mlx5_destroy_flow_table(rx_roce->ft_rdma);
+	mlx5_destroy_flow_group(rx_roce->roce_miss.group);
+	mlx5_destroy_flow_group(rx_roce->g);
+	mlx5_destroy_flow_table(rx_roce->ft);
+}
+
+#define MLX5_RX_ROCE_GROUP_SIZE BIT(0)
+
+int mlx5_ipsec_fs_roce_rx_create(struct mlx5_core_dev *mdev,
+				 struct mlx5_ipsec_fs *ipsec_roce,
+				 struct mlx5_flow_namespace *ns,
+				 struct mlx5_flow_destination *default_dst,
+				 u32 family, u32 level, u32 prio)
+{
+	struct mlx5_flow_table_attr ft_attr = {};
+	struct mlx5_ipsec_rx_roce *roce;
+	struct mlx5_flow_table *ft;
+	struct mlx5_flow_group *g;
+	void *outer_headers_c;
+	int ix = 0;
+	u32 *in;
+	int err;
+	u8 *mc;
+
+	if (!ipsec_roce)
+		return 0;
+
+	roce = (family == AF_INET) ? &ipsec_roce->ipv4_rx :
+				     &ipsec_roce->ipv6_rx;
+
+	ft_attr.max_fte = 2;
+	ft_attr.level = level;
+	ft_attr.prio = prio;
+	ft = mlx5_create_flow_table(ns, &ft_attr);
+	if (IS_ERR(ft)) {
+		err = PTR_ERR(ft);
+		mlx5_core_err(mdev, "Fail to create RoCE IPsec rx ft at nic err=%d\n", err);
+		return err;
+	}
+
+	roce->ft = ft;
+
+	in = kvzalloc(MLX5_ST_SZ_BYTES(create_flow_group_in), GFP_KERNEL);
+	if (!in) {
+		err = -ENOMEM;
+		goto fail_nomem;
+	}
+
+	mc = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria);
+	outer_headers_c = MLX5_ADDR_OF(fte_match_param, mc, outer_headers);
+	MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, outer_headers_c, ip_protocol);
+	MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, outer_headers_c, udp_dport);
+
+	MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS);
+	MLX5_SET_CFG(in, start_flow_index, ix);
+	ix += MLX5_RX_ROCE_GROUP_SIZE;
+	MLX5_SET_CFG(in, end_flow_index, ix - 1);
+	g = mlx5_create_flow_group(ft, in);
+	if (IS_ERR(g)) {
+		err = PTR_ERR(g);
+		mlx5_core_err(mdev, "Fail to create RoCE IPsec rx group at nic err=%d\n", err);
+		goto fail_group;
+	}
+	roce->g = g;
+
+	memset(in, 0, MLX5_ST_SZ_BYTES(create_flow_group_in));
+	MLX5_SET_CFG(in, start_flow_index, ix);
+	ix += MLX5_RX_ROCE_GROUP_SIZE;
+	MLX5_SET_CFG(in, end_flow_index, ix - 1);
+	g = mlx5_create_flow_group(ft, in);
+	if (IS_ERR(g)) {
+		err = PTR_ERR(g);
+		mlx5_core_err(mdev, "Fail to create RoCE IPsec rx miss group at nic err=%d\n", err);
+		goto fail_mgroup;
+	}
+	roce->roce_miss.group = g;
+
+	memset(&ft_attr, 0, sizeof(ft_attr));
+	if (family == AF_INET)
+		ft_attr.level = 1;
+	ft = mlx5_create_flow_table(roce->ns_rdma, &ft_attr);
+	if (IS_ERR(ft)) {
+		err = PTR_ERR(ft);
+		mlx5_core_err(mdev, "Fail to create RoCE IPsec rx ft at rdma err=%d\n", err);
+		goto fail_rdma_table;
+	}
+
+	roce->ft_rdma = ft;
+
+	err = ipsec_fs_roce_rx_rule_setup(mdev, default_dst, roce);
+	if (err) {
+		mlx5_core_err(mdev, "Fail to create RoCE IPsec rx rules err=%d\n", err);
+		goto fail_setup_rule;
+	}
+
+	kvfree(in);
+	return 0;
+
+fail_setup_rule:
+	mlx5_destroy_flow_table(roce->ft_rdma);
+fail_rdma_table:
+	mlx5_destroy_flow_group(roce->roce_miss.group);
+fail_mgroup:
+	mlx5_destroy_flow_group(roce->g);
+fail_group:
+	kvfree(in);
+fail_nomem:
+	mlx5_destroy_flow_table(roce->ft);
+	return err;
+}
+
+void mlx5_ipsec_fs_roce_cleanup(struct mlx5_ipsec_fs *ipsec_roce)
+{
+	kfree(ipsec_roce);
+}
+
+struct mlx5_ipsec_fs *mlx5_ipsec_fs_roce_init(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_ipsec_fs *roce_ipsec;
+	struct mlx5_flow_namespace *ns;
+
+	ns = mlx5_get_flow_namespace(mdev, MLX5_FLOW_NAMESPACE_RDMA_RX_IPSEC);
+	if (!ns) {
+		mlx5_core_err(mdev, "Failed to get RoCE rx ns\n");
+		return NULL;
+	}
+
+	roce_ipsec = kzalloc(sizeof(*roce_ipsec), GFP_KERNEL);
+	if (!roce_ipsec)
+		return NULL;
+
+	roce_ipsec->ipv4_rx.ns_rdma = ns;
+	roce_ipsec->ipv6_rx.ns_rdma = ns;
+
+	ns = mlx5_get_flow_namespace(mdev, MLX5_FLOW_NAMESPACE_RDMA_TX_IPSEC);
+	if (!ns) {
+		mlx5_core_err(mdev, "Failed to get RoCE tx ns\n");
+		goto err_tx;
+	}
+
+	roce_ipsec->tx.ns = ns;
+
+	return roce_ipsec;
+
+err_tx:
+	kfree(roce_ipsec);
+	return NULL;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.h
new file mode 100644
index 000000000000..9712d705fe48
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#ifndef __MLX5_LIB_IPSEC_H__
+#define __MLX5_LIB_IPSEC_H__
+
+struct mlx5_ipsec_fs;
+
+struct mlx5_flow_table *
+mlx5_ipsec_fs_roce_ft_get(struct mlx5_ipsec_fs *ipsec_roce, u32 family);
+void mlx5_ipsec_fs_roce_rx_destroy(struct mlx5_ipsec_fs *ipsec_roce,
+				   u32 family);
+int mlx5_ipsec_fs_roce_rx_create(struct mlx5_core_dev *mdev,
+				 struct mlx5_ipsec_fs *ipsec_roce,
+				 struct mlx5_flow_namespace *ns,
+				 struct mlx5_flow_destination *default_dst,
+				 u32 family, u32 level, u32 prio);
+void mlx5_ipsec_fs_roce_tx_destroy(struct mlx5_ipsec_fs *ipsec_roce);
+int mlx5_ipsec_fs_roce_tx_create(struct mlx5_core_dev *mdev,
+				 struct mlx5_ipsec_fs *ipsec_roce,
+				 struct mlx5_flow_table *pol_ft);
+void mlx5_ipsec_fs_roce_cleanup(struct mlx5_ipsec_fs *ipsec_roce);
+struct mlx5_ipsec_fs *mlx5_ipsec_fs_roce_init(struct mlx5_core_dev *mdev);
+
+#endif /* __MLX5_LIB_IPSEC_H__ */
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 90a2fe5839fa..2cb404c7ea13 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -51,6 +51,7 @@ enum mlx5_flow_destination_type {
 	MLX5_FLOW_DESTINATION_TYPE_COUNTER,
 	MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM,
 	MLX5_FLOW_DESTINATION_TYPE_RANGE,
+	MLX5_FLOW_DESTINATION_TYPE_TABLE_TYPE,
 };
 
 enum {
@@ -102,6 +103,8 @@ enum mlx5_flow_namespace_type {
 	MLX5_FLOW_NAMESPACE_PORT_SEL,
 	MLX5_FLOW_NAMESPACE_RDMA_RX_COUNTERS,
 	MLX5_FLOW_NAMESPACE_RDMA_TX_COUNTERS,
+	MLX5_FLOW_NAMESPACE_RDMA_RX_IPSEC,
+	MLX5_FLOW_NAMESPACE_RDMA_TX_IPSEC,
 };
 
 enum {
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 1e530a8a2cf5..5ad5126615a1 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -316,6 +316,11 @@ enum {
 	MLX5_CMD_OP_GENERAL_END = 0xd00,
 };
 
+enum {
+	MLX5_FT_NIC_RX_2_NIC_RX_RDMA = BIT(0),
+	MLX5_FT_NIC_TX_RDMA_2_NIC_TX = BIT(1),
+};
+
 struct mlx5_ifc_flow_table_fields_supported_bits {
 	u8         outer_dmac[0x1];
 	u8         outer_smac[0x1];
@@ -1929,7 +1934,8 @@ struct mlx5_ifc_cmd_hca_cap_2_bits {
 
 	u8	   reserved_at_e0[0xc0];
 
-	u8	   reserved_at_1a0[0xb];
+	u8	   flow_table_type_2_type[0x8];
+	u8	   reserved_at_1a8[0x3];
 	u8	   log_min_mkey_entity_size[0x5];
 	u8	   reserved_at_1b0[0x10];
 
@@ -1953,6 +1959,7 @@ enum mlx5_ifc_flow_destination_type {
 	MLX5_IFC_FLOW_DESTINATION_TYPE_TIR          = 0x2,
 	MLX5_IFC_FLOW_DESTINATION_TYPE_FLOW_SAMPLER = 0x6,
 	MLX5_IFC_FLOW_DESTINATION_TYPE_UPLINK       = 0x8,
+	MLX5_IFC_FLOW_DESTINATION_TYPE_TABLE_TYPE   = 0xA,
 };
 
 enum mlx5_flow_table_miss_action {
@@ -1967,7 +1974,8 @@ struct mlx5_ifc_dest_format_struct_bits {
 
 	u8         destination_eswitch_owner_vhca_id_valid[0x1];
 	u8         packet_reformat[0x1];
-	u8         reserved_at_22[0xe];
+	u8         reserved_at_22[0x6];
+	u8         destination_table_type[0x8];
 	u8         destination_eswitch_owner_vhca_id[0x10];
 };