mlx5 IPsec packet offload support in eswitch mode

index dbe87bf89c0d..7976469108de 100644
@@ -814,11 +814,20 @@ static void setup_fte_upper_proto_match(struct mlx5_flow_spec *spec, struct upsp
 	}
 }
 
-static int setup_modify_header(struct mlx5_core_dev *mdev, u32 val, u8 dir,
+static enum mlx5_flow_namespace_type ipsec_fs_get_ns(struct mlx5e_ipsec *ipsec, u8 dir)
+{
+	if (dir == XFRM_DEV_OFFLOAD_IN)
+		return MLX5_FLOW_NAMESPACE_KERNEL;
+
+	return MLX5_FLOW_NAMESPACE_EGRESS;
+}
+
+static int setup_modify_header(struct mlx5e_ipsec *ipsec, u32 val, u8 dir,
 			       struct mlx5_flow_act *flow_act)
 {
+	enum mlx5_flow_namespace_type ns_type = ipsec_fs_get_ns(ipsec, dir);
 	u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {};
-	enum mlx5_flow_namespace_type ns_type;
+	struct mlx5_core_dev *mdev = ipsec->mdev;
 	struct mlx5_modify_hdr *modify_hdr;
 
 	MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET);

@@ -826,12 +835,10 @@ static int setup_modify_header(struct mlx5_core_dev *mdev, u32 val, u8 dir,
 	case XFRM_DEV_OFFLOAD_IN:
 		MLX5_SET(set_action_in, action, field,
 			 MLX5_ACTION_IN_FIELD_METADATA_REG_B);
-		ns_type = MLX5_FLOW_NAMESPACE_KERNEL;
 		break;
 	case XFRM_DEV_OFFLOAD_OUT:
 		MLX5_SET(set_action_in, action, field,
 			 MLX5_ACTION_IN_FIELD_METADATA_REG_C_0);
-		ns_type = MLX5_FLOW_NAMESPACE_EGRESS;
 		break;
 	default:
 		return -EINVAL;

@@ -991,26 +998,16 @@ setup_pkt_transport_reformat(struct mlx5_accel_esp_xfrm_attrs *attrs,
 	return 0;
 }
 
-static int setup_pkt_reformat(struct mlx5_core_dev *mdev,
+static int setup_pkt_reformat(struct mlx5e_ipsec *ipsec,
 			      struct mlx5_accel_esp_xfrm_attrs *attrs,
 			      struct mlx5_flow_act *flow_act)
 {
+	enum mlx5_flow_namespace_type ns_type = ipsec_fs_get_ns(ipsec, attrs->dir);
 	struct mlx5_pkt_reformat_params reformat_params = {};
+	struct mlx5_core_dev *mdev = ipsec->mdev;
 	struct mlx5_pkt_reformat *pkt_reformat;
-	enum mlx5_flow_namespace_type ns_type;
 	int ret;
 
-	switch (attrs->dir) {
-	case XFRM_DEV_OFFLOAD_IN:
-		ns_type = MLX5_FLOW_NAMESPACE_KERNEL;
-		break;
-	case XFRM_DEV_OFFLOAD_OUT:
-		ns_type = MLX5_FLOW_NAMESPACE_EGRESS;
-		break;
-	default:
-		return -EINVAL;
-	}
-
 	switch (attrs->mode) {
 	case XFRM_MODE_TRANSPORT:
 		ret = setup_pkt_transport_reformat(attrs, &reformat_params);

@@ -1068,14 +1065,14 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 	setup_fte_esp(spec);
 	setup_fte_no_frags(spec);
 
-	err = setup_modify_header(mdev, sa_entry->ipsec_obj_id | BIT(31),
+	err = setup_modify_header(ipsec, sa_entry->ipsec_obj_id | BIT(31),
 				  XFRM_DEV_OFFLOAD_IN, &flow_act);
 	if (err)
 		goto err_mod_header;
 
 	switch (attrs->type) {
 	case XFRM_DEV_OFFLOAD_PACKET:
-		err = setup_pkt_reformat(mdev, attrs, &flow_act);
+		err = setup_pkt_reformat(ipsec, attrs, &flow_act);
 		if (err)
 			goto err_pkt_reformat;
 		break;

@@ -1169,7 +1166,7 @@ static int tx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 	case XFRM_DEV_OFFLOAD_PACKET:
 		if (attrs->reqid)
 			setup_fte_reg_c0(spec, attrs->reqid);
-		err = setup_pkt_reformat(mdev, attrs, &flow_act);
+		err = setup_pkt_reformat(ipsec, attrs, &flow_act);
 		if (err)
 			goto err_pkt_reformat;
 		break;

@@ -1226,15 +1223,16 @@ static int tx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 {
 	struct mlx5_accel_pol_xfrm_attrs *attrs = &pol_entry->attrs;
 	struct mlx5_core_dev *mdev = mlx5e_ipsec_pol2dev(pol_entry);
-	struct mlx5e_ipsec_tx *tx = pol_entry->ipsec->tx;
+	struct mlx5e_ipsec *ipsec = pol_entry->ipsec;
 	struct mlx5_flow_destination dest[2] = {};
+	struct mlx5e_ipsec_tx *tx = ipsec->tx;
 	struct mlx5_flow_act flow_act = {};
 	struct mlx5_flow_handle *rule;
 	struct mlx5_flow_spec *spec;
 	struct mlx5_flow_table *ft;
 	int err, dstn = 0;
 
-	ft = tx_ft_get_policy(mdev, pol_entry->ipsec, attrs->prio);
+	ft = tx_ft_get_policy(mdev, ipsec, attrs->prio);
 	if (IS_ERR(ft))
 		return PTR_ERR(ft);
 

@@ -1258,7 +1256,7 @@ static int tx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 		if (!attrs->reqid)
 			break;
 
-		err = setup_modify_header(mdev, attrs->reqid,
+		err = setup_modify_header(ipsec, attrs->reqid,
 					  XFRM_DEV_OFFLOAD_OUT, &flow_act);
 		if (err)
 			goto err_mod_header;

@@ -1298,7 +1296,7 @@ static int tx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 err_mod_header:
 	kvfree(spec);
 err_alloc:
-	tx_ft_put_policy(pol_entry->ipsec, attrs->prio);
+	tx_ft_put_policy(ipsec, attrs->prio);
 	return err;
 }
 

index eab5bc718771..8d6379ac4574 100644
@@ -309,9 +309,8 @@ enum {
 
 void mlx5e_ipsec_offload_handle_rx_skb(struct net_device *netdev,
 				       struct sk_buff *skb,
-				       struct mlx5_cqe64 *cqe)
+				       u32 ipsec_meta_data)
 {
-	u32 ipsec_meta_data = be32_to_cpu(cqe->ft_metadata);
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5e_ipsec *ipsec = priv->ipsec;
 	struct mlx5e_ipsec_sa_entry *sa_entry;

index 1878a70b9031..436e9a8a32d3 100644
@@ -66,7 +66,7 @@ void mlx5e_ipsec_handle_tx_wqe(struct mlx5e_tx_wqe *wqe,
 			       struct mlx5_wqe_inline_seg *inlseg);
 void mlx5e_ipsec_offload_handle_rx_skb(struct net_device *netdev,
 				       struct sk_buff *skb,
-				       struct mlx5_cqe64 *cqe);
+				       u32 ipsec_meta_data);
 static inline unsigned int mlx5e_ipsec_tx_ids_len(struct mlx5e_accel_tx_ipsec_state *ipsec_st)
 {
 	return ipsec_st->tailen;

@@ -145,7 +145,7 @@ mlx5e_ipsec_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 static inline
 void mlx5e_ipsec_offload_handle_rx_skb(struct net_device *netdev,
 				       struct sk_buff *skb,
-				       struct mlx5_cqe64 *cqe)
+				       u32 ipsec_meta_data)
 {}
 
 static inline bool mlx5e_ipsec_eseg_meta(struct mlx5_wqe_eth_seg *eseg)

index 704b022cd1f0..b9e92456ec4d 100644
@@ -1535,7 +1535,8 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
 		mlx5e_ktls_handle_rx_skb(rq, skb, cqe, &cqe_bcnt);
 
 	if (unlikely(mlx5_ipsec_is_rx_flow(cqe)))
-		mlx5e_ipsec_offload_handle_rx_skb(netdev, skb, cqe);
+		mlx5e_ipsec_offload_handle_rx_skb(netdev, skb,
+						  be32_to_cpu(cqe->ft_metadata));
 
 	if (unlikely(mlx5e_macsec_is_rx_flow(cqe)))
 		mlx5e_macsec_offload_handle_rx_skb(netdev, skb, cqe);

index 891d39b4bfd4..ad62424249e1 100644
@@ -40,6 +40,7 @@
 #include "en.h"
 #include "ipsec.h"
 #include "ipsec_rxtx.h"
+#include "en_rep.h"
 
 #define MLX5_IPSEC_RESCHED msecs_to_jiffies(1000)
 #define MLX5E_IPSEC_TUNNEL_SA XA_MARK_1

@@ -835,6 +836,7 @@ void mlx5e_ipsec_init(struct mlx5e_priv *priv)
 			goto clear_aso;
 	}
 
+	ipsec->is_uplink_rep = mlx5e_is_uplink_rep(priv);
 	ret = mlx5e_accel_ipsec_fs_init(ipsec);
 	if (ret)
 		goto err_fs_init;

index 4e9887171508..ef64a042191d 100644
@@ -170,11 +170,14 @@ struct mlx5e_ipsec {
 	struct mlx5e_flow_steering *fs;
 	struct mlx5e_ipsec_rx *rx_ipv4;
 	struct mlx5e_ipsec_rx *rx_ipv6;
+	struct mlx5e_ipsec_rx *rx_esw;
 	struct mlx5e_ipsec_tx *tx;
+	struct mlx5e_ipsec_tx *tx_esw;
 	struct mlx5e_ipsec_aso *aso;
 	struct notifier_block nb;
 	struct notifier_block netevent_nb;
 	struct mlx5_ipsec_fs *roce;
+	u8 is_uplink_rep: 1;
 };
 
 struct mlx5e_ipsec_esn_state {

509 lines not on this page · raw message

index ef64a042191d..92c111c28a7a 100644
@@ -161,6 +161,17 @@ struct mlx5e_ipsec_aso {
 	spinlock_t lock;
 };
 
+struct mlx5e_ipsec_rx_create_attr {
+	struct mlx5_flow_namespace *ns;
+	struct mlx5_ttc_table *ttc;
+	u32 family;
+	int prio;
+	int pol_level;
+	int sa_level;
+	int status_level;
+	enum mlx5_flow_namespace_type chains_ns;
+};
+
 struct mlx5e_ipsec {
 	struct mlx5_core_dev *mdev;
 	struct xarray sadb;

158 lines not on this page · raw message

59 lines not on this page · raw message

180 lines not on this page · raw message

index a3554bde3e07..beed57e24088 100644
@@ -46,7 +46,8 @@ u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev)
 			caps |= MLX5_IPSEC_CAP_PACKET_OFFLOAD;
 
 		if (MLX5_CAP_FLOWTABLE_NIC_TX(mdev, ignore_flow_level) &&
-		    MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ignore_flow_level))
+		    MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ignore_flow_level) &&
+		    MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, ignore_flow_level))
 			caps |= MLX5_IPSEC_CAP_PRIO;
 
 		if (MLX5_CAP_FLOWTABLE_NIC_TX(mdev,

184 lines not on this page · raw message

new file mode 100644
index 000000000000..1d6104648d32
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#ifndef __MLX5_ESW_IPSEC_FS_H__
+#define __MLX5_ESW_IPSEC_FS_H__
+
+struct mlx5e_ipsec;
+
+#ifdef CONFIG_MLX5_ESWITCH
+void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,
+				      struct mlx5e_ipsec_rx *rx);
+int mlx5_esw_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec,
+				    struct mlx5e_ipsec_rx *rx,
+				    struct mlx5_flow_destination *dest);
+void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec,
+				       struct mlx5e_ipsec_rx_create_attr *attr);
+int mlx5_esw_ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ipsec,
+					   struct mlx5_flow_destination *dest);
+#else
+static inline void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,
+						    struct mlx5e_ipsec_rx *rx) {}
+
+static inline int mlx5_esw_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec,
+						  struct mlx5e_ipsec_rx *rx,
+						  struct mlx5_flow_destination *dest)
+{
+	return  -EINVAL;
+}
+
+static inline void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec,
+						     struct mlx5e_ipsec_rx_create_attr *attr) {}
+
+static inline int mlx5_esw_ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ipsec,
+							 struct mlx5_flow_destination *dest)
+{
+	return -EINVAL;
+}
+#endif /* CONFIG_MLX5_ESWITCH */
+#endif /* __MLX5_ESW_IPSEC_FS_H__ */

index 4ef04aa28771..8ae1854d6b73 100644
@@ -2987,6 +2987,12 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering)
 	if (err)
 		goto out_err;
 
+	maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, FDB_CRYPTO_INGRESS, 3);
+	if (IS_ERR(maj_prio)) {
+		err = PTR_ERR(maj_prio);
+		goto out_err;
+	}
+
 	err = create_fdb_fast_path(steering);
 	if (err)
 		goto out_err;

index 2cb404c7ea13..6b1fa94f69c8 100644
@@ -109,6 +109,7 @@ enum mlx5_flow_namespace_type {
 
 enum {
 	FDB_BYPASS_PATH,
+	FDB_CRYPTO_INGRESS,
 	FDB_TC_OFFLOAD,
 	FDB_FT_OFFLOAD,
 	FDB_TC_MISS,

index b5c773ffc763..b12fe3c5a258 100644
@@ -715,9 +715,20 @@ void mlx5e_rep_tc_receive(struct mlx5_cqe64 *cqe, struct mlx5e_rq *rq,
 	uplink_priv = &uplink_rpriv->uplink_priv;
 	ct_priv = uplink_priv->ct_priv;
 
-	if (!mlx5_ipsec_is_rx_flow(cqe) &&
-	    !mlx5e_tc_update_skb(cqe, skb, mapping_ctx, reg_c0, ct_priv, zone_restore_id, tunnel_id,
-				 &tc_priv))
+#ifdef CONFIG_MLX5_EN_IPSEC
+	if (!(tunnel_id >> ESW_TUN_OPTS_BITS)) {
+		u32 mapped_id;
+		u32 metadata;
+
+		mapped_id = tunnel_id & ESW_IPSEC_RX_MAPPED_ID_MASK;
+		if (mapped_id &&
+		    !mlx5_esw_ipsec_rx_make_metadata(priv, mapped_id, &metadata))
+			mlx5e_ipsec_offload_handle_rx_skb(priv->netdev, skb, metadata);
+	}
+#endif
+
+	if (!mlx5e_tc_update_skb(cqe, skb, mapping_ctx, reg_c0, ct_priv,
+				 zone_restore_id, tunnel_id, &tc_priv))
 		goto free_skb;
 
 forward:

index 5ab8c9e714c4..bc8e200f4059 100644
@@ -202,6 +202,7 @@ struct mlx5e_ipsec_rx {
 	struct mlx5e_ipsec_fc *fc;
 	struct mlx5_fs_chains *chains;
 	u8 allow_tunnel_mode : 1;
+	struct xarray ipsec_obj_id_map;
 };
 
 struct mlx5e_ipsec {

@@ -248,6 +249,7 @@ struct mlx5e_ipsec_sa_entry {
 	struct mlx5e_ipsec_work *work;
 	struct mlx5e_ipsec_dwork *dwork;
 	struct mlx5e_ipsec_limits limits;
+	u32 rx_mapped_id;
 };
 
 struct mlx5_accel_pol_xfrm_attrs {

index 0e7095c60b64..0d386fbfb18c 100644
@@ -1120,6 +1120,9 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 		err = setup_modify_header(ipsec, attrs->type,
 					  sa_entry->ipsec_obj_id | BIT(31),
 					  XFRM_DEV_OFFLOAD_IN, &flow_act);
+	else
+		err = mlx5_esw_ipsec_rx_setup_modify_header(sa_entry, &flow_act);
+
 	if (err)
 		goto err_mod_header;
 

@@ -1608,6 +1611,7 @@ void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 	}
 
 	mlx5_modify_header_dealloc(mdev, ipsec_rule->modify_hdr);
+	mlx5_esw_ipsec_rx_id_mapping_remove(sa_entry);
 	rx_ft_put(sa_entry->ipsec, sa_entry->attrs.family, sa_entry->attrs.type);
 }
 

@@ -1660,6 +1664,8 @@ void mlx5e_accel_ipsec_fs_cleanup(struct mlx5e_ipsec *ipsec)
 	kfree(ipsec->rx_ipv6);
 
 	if (ipsec->is_uplink_rep) {
+		xa_destroy(&ipsec->rx_esw->ipsec_obj_id_map);
+
 		mutex_destroy(&ipsec->tx_esw->ft.mutex);
 		WARN_ON(ipsec->tx_esw->ft.refcnt);
 		kfree(ipsec->tx_esw);

@@ -1720,6 +1726,7 @@ int mlx5e_accel_ipsec_fs_init(struct mlx5e_ipsec *ipsec)
 		mutex_init(&ipsec->tx_esw->ft.mutex);
 		mutex_init(&ipsec->rx_esw->ft.mutex);
 		ipsec->tx_esw->ns = ns_esw;
+		xa_init_flags(&ipsec->rx_esw->ipsec_obj_id_map, XA_FLAGS_ALLOC1);
 	} else if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_ROCE) {
 		ipsec->roce = mlx5_ipsec_fs_roce_init(mdev);
 	}

index 8d6379ac4574..c00fe0d5ea11 100644
@@ -37,6 +37,7 @@
 #include "ipsec.h"
 #include "ipsec_rxtx.h"
 #include "en.h"
+#include "esw/ipsec_fs.h"
 
 enum {
 	MLX5E_IPSEC_TX_SYNDROME_OFFLOAD = 0x8,

@@ -355,3 +356,24 @@ void mlx5e_ipsec_offload_handle_rx_skb(struct net_device *netdev,
 		atomic64_inc(&ipsec->sw_stats.ipsec_rx_drop_syndrome);
 	}
 }
+
+int mlx5_esw_ipsec_rx_make_metadata(struct mlx5e_priv *priv, u32 id, u32 *metadata)
+{
+	struct mlx5e_ipsec *ipsec = priv->ipsec;
+	u32 ipsec_obj_id;
+	int err;
+
+	if (!ipsec || !ipsec->is_uplink_rep)
+		return -EINVAL;
+
+	err = mlx5_esw_ipsec_rx_ipsec_obj_id_search(priv, id, &ipsec_obj_id);
+	if (err) {
+		atomic64_inc(&ipsec->sw_stats.ipsec_rx_drop_sadb_miss);
+		return err;
+	}
+
+	*metadata = MLX5_IPSEC_METADATA_CREATE(ipsec_obj_id,
+					       MLX5E_IPSEC_OFFLOAD_RX_SYNDROME_DECRYPTED);
+
+	return 0;
+}

index 436e9a8a32d3..9ee014a8ad24 100644
@@ -43,6 +43,7 @@
 #define MLX5_IPSEC_METADATA_MARKER(metadata)  (((metadata) >> 31) & 0x1)
 #define MLX5_IPSEC_METADATA_SYNDROM(metadata) (((metadata) >> 24) & GENMASK(5, 0))
 #define MLX5_IPSEC_METADATA_HANDLE(metadata)  ((metadata) & GENMASK(23, 0))
+#define MLX5_IPSEC_METADATA_CREATE(id, syndrome) ((id) | ((syndrome) << 24))
 
 struct mlx5e_accel_tx_ipsec_state {
 	struct xfrm_offload *xo;

@@ -67,6 +68,7 @@ void mlx5e_ipsec_handle_tx_wqe(struct mlx5e_tx_wqe *wqe,
 void mlx5e_ipsec_offload_handle_rx_skb(struct net_device *netdev,
 				       struct sk_buff *skb,
 				       u32 ipsec_meta_data);
+int mlx5_esw_ipsec_rx_make_metadata(struct mlx5e_priv *priv, u32 id, u32 *metadata);
 static inline unsigned int mlx5e_ipsec_tx_ids_len(struct mlx5e_accel_tx_ipsec_state *ipsec_st)
 {
 	return ipsec_st->tailen;

72 lines not on this page · raw message

index 1d6104648d32..44df34032d1e 100644
@@ -5,6 +5,7 @@
 #define __MLX5_ESW_IPSEC_FS_H__
 
 struct mlx5e_ipsec;
+struct mlx5e_ipsec_sa_entry;
 
 #ifdef CONFIG_MLX5_ESWITCH
 void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,

@@ -16,6 +17,11 @@ void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec,
 				       struct mlx5e_ipsec_rx_create_attr *attr);
 int mlx5_esw_ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ipsec,
 					   struct mlx5_flow_destination *dest);
+int mlx5_esw_ipsec_rx_setup_modify_header(struct mlx5e_ipsec_sa_entry *sa_entry,
+					  struct mlx5_flow_act *flow_act);
+void mlx5_esw_ipsec_rx_id_mapping_remove(struct mlx5e_ipsec_sa_entry *sa_entry);
+int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv, u32 id,
+					  u32 *ipsec_obj_id);
 #else
 static inline void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,
 						    struct mlx5e_ipsec_rx *rx) {}

@@ -35,5 +41,19 @@ static inline int mlx5_esw_ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ips
 {
 	return -EINVAL;
 }
+
+static inline int mlx5_esw_ipsec_rx_setup_modify_header(struct mlx5e_ipsec_sa_entry *sa_entry,
+							struct mlx5_flow_act *flow_act)
+{
+	return -EINVAL;
+}
+
+static inline void mlx5_esw_ipsec_rx_id_mapping_remove(struct mlx5e_ipsec_sa_entry *sa_entry) {}
+
+static inline int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv, u32 id,
+							u32 *ipsec_obj_id)
+{
+	return -EINVAL;
+}
 #endif /* CONFIG_MLX5_ESWITCH */
 #endif /* __MLX5_ESW_IPSEC_FS_H__ */

index e2701ed0200e..950d2431a53c 100644
@@ -144,6 +144,9 @@ u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw,
 	GENMASK(31 - ESW_TUN_ID_BITS - ESW_RESERVED_BITS, \
 		ESW_TUN_OPTS_OFFSET + 1)
 
+/* reuse tun_opts for the mapped ipsec obj id when tun_id is 0 (invalid) */
+#define ESW_IPSEC_RX_MAPPED_ID_MASK GENMASK(ESW_TUN_OPTS_BITS - 1, 0)
+
 u8 mlx5_eswitch_mode(const struct mlx5_core_dev *dev);
 u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev);
 struct mlx5_core_dev *mlx5_eswitch_get_core_dev(struct mlx5_eswitch *esw);

index bc8e200f4059..a3cd3986b2cc 100644
@@ -205,6 +205,14 @@ struct mlx5e_ipsec_rx {
 	struct xarray ipsec_obj_id_map;
 };
 
+struct mlx5e_ipsec_tx_create_attr {
+	int prio;
+	int pol_level;
+	int sa_level;
+	int cnt_level;
+	enum mlx5_flow_namespace_type chains_ns;
+};
+
 struct mlx5e_ipsec {
 	struct mlx5_core_dev *mdev;
 	struct xarray sadb;

index 0d386fbfb18c..f89174dbed92 100644
@@ -569,15 +569,29 @@ static void tx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec_tx *tx,
 	mlx5_destroy_flow_table(tx->ft.status);
 }
 
-static int tx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec_tx *tx,
+static void ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec,
+				     struct mlx5e_ipsec_tx *tx,
+				     struct mlx5e_ipsec_tx_create_attr *attr)
+{
+	attr->prio = 0;
+	attr->pol_level = 0;
+	attr->sa_level = 1;
+	attr->cnt_level = 2;
+	attr->chains_ns = MLX5_FLOW_NAMESPACE_EGRESS_IPSEC;
+}
+
+static int tx_create(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx,
 		     struct mlx5_ipsec_fs *roce)
 {
+	struct mlx5_core_dev *mdev = ipsec->mdev;
+	struct mlx5e_ipsec_tx_create_attr attr;
 	struct mlx5_flow_destination dest = {};
 	struct mlx5_flow_table *ft;
 	u32 flags = 0;
 	int err;
 
-	ft = ipsec_ft_create(tx->ns, 2, 0, 1, 0);
+	ipsec_tx_create_attr_set(ipsec, tx, &attr);
+	ft = ipsec_ft_create(tx->ns, attr.cnt_level, attr.prio, 1, 0);
 	if (IS_ERR(ft))
 		return PTR_ERR(ft);
 	tx->ft.status = ft;

@@ -590,7 +604,7 @@ static int tx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec_tx *tx,
 		tx->allow_tunnel_mode = mlx5_eswitch_block_encap(mdev);
 	if (tx->allow_tunnel_mode)
 		flags = MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT;
-	ft = ipsec_ft_create(tx->ns, 1, 0, 4, flags);
+	ft = ipsec_ft_create(tx->ns, attr.sa_level, attr.prio, 4, flags);
 	if (IS_ERR(ft)) {
 		err = PTR_ERR(ft);
 		goto err_sa_ft;

@@ -599,7 +613,7 @@ static int tx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec_tx *tx,
 
 	if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_PRIO) {
 		tx->chains = ipsec_chains_create(
-			mdev, tx->ft.sa, MLX5_FLOW_NAMESPACE_EGRESS_IPSEC, 0, 0,
+			mdev, tx->ft.sa, attr.chains_ns, attr.prio, attr.pol_level,
 			&tx->ft.pol);
 		if (IS_ERR(tx->chains)) {
 			err = PTR_ERR(tx->chains);

@@ -609,7 +623,7 @@ static int tx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec_tx *tx,
 		goto connect_roce;
 	}
 
-	ft = ipsec_ft_create(tx->ns, 0, 0, 2, 0);
+	ft = ipsec_ft_create(tx->ns, attr.pol_level, attr.prio, 2, 0);
 	if (IS_ERR(ft)) {
 		err = PTR_ERR(ft);
 		goto err_pol_ft;

@@ -656,7 +670,7 @@ static int tx_get(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	if (tx->ft.refcnt)
 		goto skip;
 
-	err = tx_create(mdev, tx, ipsec->roce);
+	err = tx_create(ipsec, tx, ipsec->roce);
 	if (err)
 		return err;
 

index f89174dbed92..a2f3ba811af8 100644
@@ -10,6 +10,7 @@
 #include "lib/ipsec_fs_roce.h"
 #include "lib/fs_chains.h"
 #include "esw/ipsec_fs.h"
+#include "en_rep.h"
 
 #define NUM_IPSEC_FTE BIT(15)
 #define MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_SIZE 16

@@ -23,6 +24,7 @@ struct mlx5e_ipsec_fc {
 struct mlx5e_ipsec_tx {
 	struct mlx5e_ipsec_ft ft;
 	struct mlx5e_ipsec_miss pol;
+	struct mlx5e_ipsec_miss sa;
 	struct mlx5e_ipsec_rule status;
 	struct mlx5_flow_namespace *ns;
 	struct mlx5e_ipsec_fc *fc;

@@ -550,7 +552,7 @@ static int ipsec_counter_rule_tx(struct mlx5_core_dev *mdev, struct mlx5e_ipsec_
 }
 
 /* IPsec TX flow steering */
-static void tx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec_tx *tx,
+static void tx_destroy(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx,
 		       struct mlx5_ipsec_fs *roce)
 {
 	mlx5_ipsec_fs_roce_tx_destroy(roce);

@@ -562,9 +564,13 @@ static void tx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec_tx *tx,
 		mlx5_destroy_flow_table(tx->ft.pol);
 	}
 
+	if (tx == ipsec->tx_esw) {
+		mlx5_del_flow_rules(tx->sa.rule);
+		mlx5_destroy_flow_group(tx->sa.group);
+	}
 	mlx5_destroy_flow_table(tx->ft.sa);
 	if (tx->allow_tunnel_mode)
-		mlx5_eswitch_unblock_encap(mdev);
+		mlx5_eswitch_unblock_encap(ipsec->mdev);
 	mlx5_del_flow_rules(tx->status.rule);
 	mlx5_destroy_flow_table(tx->ft.status);
 }

@@ -573,6 +579,11 @@ static void ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec,
 				     struct mlx5e_ipsec_tx *tx,
 				     struct mlx5e_ipsec_tx_create_attr *attr)
 {
+	if (tx == ipsec->tx_esw) {
+		mlx5_esw_ipsec_tx_create_attr_set(ipsec, attr);
+		return;
+	}
+
 	attr->prio = 0;
 	attr->pol_level = 0;
 	attr->sa_level = 1;

@@ -611,6 +622,15 @@ static int tx_create(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx,
 	}
 	tx->ft.sa = ft;
 
+	if (tx == ipsec->tx_esw) {
+		dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
+		dest.vport.num = MLX5_VPORT_UPLINK;
+		err = ipsec_miss_create(mdev, tx->ft.sa, &tx->sa, &dest);
+		if (err)
+			goto err_sa_miss;
+		memset(&dest, 0, sizeof(dest));
+	}
+
 	if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_PRIO) {
 		tx->chains = ipsec_chains_create(
 			mdev, tx->ft.sa, attr.chains_ns, attr.prio, attr.pol_level,

@@ -652,6 +672,11 @@ static int tx_create(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx,
 		mlx5_destroy_flow_table(tx->ft.pol);
 	}
 err_pol_ft:
+	if (tx == ipsec->tx_esw) {
+		mlx5_del_flow_rules(tx->sa.rule);
+		mlx5_destroy_flow_group(tx->sa.group);
+	}
+err_sa_miss:
 	mlx5_destroy_flow_table(tx->ft.sa);
 err_sa_ft:
 	if (tx->allow_tunnel_mode)

@@ -662,6 +687,25 @@ static int tx_create(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx,
 	return err;
 }
 
+static void ipsec_esw_tx_ft_policy_set(struct mlx5_core_dev *mdev,
+				       struct mlx5_flow_table *ft)
+{
+#ifdef CONFIG_MLX5_ESWITCH
+	struct mlx5_eswitch *esw = mdev->priv.eswitch;
+	struct mlx5e_rep_priv *uplink_rpriv;
+	struct mlx5e_priv *priv;
+
+	esw->offloads.ft_ipsec_tx_pol = ft;
+	uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
+	priv = netdev_priv(uplink_rpriv->netdev);
+	if (!priv->channels.num)
+		return;
+
+	mlx5e_rep_deactivate_channels(priv);
+	mlx5e_rep_activate_channels(priv);
+#endif
+}
+
 static int tx_get(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 		  struct mlx5e_ipsec_tx *tx)
 {

@@ -674,6 +718,9 @@ static int tx_get(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	if (err)
 		return err;
 
+	if (tx == ipsec->tx_esw)
+		ipsec_esw_tx_ft_policy_set(mdev, tx->ft.pol);
+
 skip:
 	tx->ft.refcnt++;
 	return 0;

@@ -684,7 +731,10 @@ static void tx_put(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx)
 	if (--tx->ft.refcnt)
 		return;
 
-	tx_destroy(ipsec->mdev, tx, ipsec->roce);
+	if (tx == ipsec->tx_esw)
+		ipsec_esw_tx_ft_policy_set(ipsec->mdev, NULL);
+
+	tx_destroy(ipsec, tx, ipsec->roce);
 }
 
 static struct mlx5_flow_table *tx_ft_get_policy(struct mlx5_core_dev *mdev,

@@ -842,15 +892,15 @@ static void setup_fte_reg_a(struct mlx5_flow_spec *spec)
 		 misc_parameters_2.metadata_reg_a, MLX5_ETH_WQE_FT_META_IPSEC);
 }
 
-static void setup_fte_reg_c0(struct mlx5_flow_spec *spec, u32 reqid)
+static void setup_fte_reg_c4(struct mlx5_flow_spec *spec, u32 reqid)
 {
 	/* Pass policy check before choosing this SA */
 	spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2;
 
-	MLX5_SET(fte_match_param, spec->match_criteria,
-		 misc_parameters_2.metadata_reg_c_0, reqid);
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+			 misc_parameters_2.metadata_reg_c_4);
 	MLX5_SET(fte_match_param, spec->match_value,
-		 misc_parameters_2.metadata_reg_c_0, reqid);
+		 misc_parameters_2.metadata_reg_c_4, reqid);
 }
 
 static void setup_fte_upper_proto_match(struct mlx5_flow_spec *spec, struct upspec *upspec)

@@ -902,7 +952,7 @@ static int setup_modify_header(struct mlx5e_ipsec *ipsec, int type, u32 val, u8
 		break;
 	case XFRM_DEV_OFFLOAD_OUT:
 		MLX5_SET(set_action_in, action, field,
-			 MLX5_ACTION_IN_FIELD_METADATA_REG_C_0);
+			 MLX5_ACTION_IN_FIELD_METADATA_REG_C_4);
 		break;
 	default:
 		return -EINVAL;

@@ -1235,7 +1285,7 @@ static int tx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 		break;
 	case XFRM_DEV_OFFLOAD_PACKET:
 		if (attrs->reqid)
-			setup_fte_reg_c0(spec, attrs->reqid);
+			setup_fte_reg_c4(spec, attrs->reqid);
 		err = setup_pkt_reformat(ipsec, attrs, &flow_act);
 		if (err)
 			goto err_pkt_reformat;

@@ -1346,6 +1396,8 @@ static int tx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 	}
 
 	flow_act.flags |= FLOW_ACT_NO_APPEND;
+	if (tx == ipsec->tx_esw && tx->chains)
+		flow_act.flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
 	dest[dstn].ft = tx->ft.sa;
 	dest[dstn].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
 	dstn++;

index 0675587c1a79..e60cd3dc1b13 100644
@@ -12,6 +12,12 @@ enum {
 	MLX5_ESW_IPSEC_RX_ESP_FT_CHK_LEVEL,
 };
 
+enum {
+	MLX5_ESW_IPSEC_TX_POL_FT_LEVEL,
+	MLX5_ESW_IPSEC_TX_ESP_FT_LEVEL,
+	MLX5_ESW_IPSEC_TX_ESP_FT_CNT_LEVEL,
+};
+
 static void esw_ipsec_rx_status_drop_destroy(struct mlx5e_ipsec *ipsec,
 					     struct mlx5e_ipsec_rx *rx)
 {

@@ -251,3 +257,13 @@ int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv, u32 id,
 
 	return 0;
 }
+
+void mlx5_esw_ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec,
+				       struct mlx5e_ipsec_tx_create_attr *attr)
+{
+	attr->prio = FDB_CRYPTO_EGRESS;
+	attr->pol_level = MLX5_ESW_IPSEC_TX_POL_FT_LEVEL;
+	attr->sa_level = MLX5_ESW_IPSEC_TX_ESP_FT_LEVEL;
+	attr->cnt_level = MLX5_ESW_IPSEC_TX_ESP_FT_CNT_LEVEL;
+	attr->chains_ns = MLX5_FLOW_NAMESPACE_FDB;
+}

index 44df34032d1e..275684f99ed3 100644
@@ -22,6 +22,8 @@ int mlx5_esw_ipsec_rx_setup_modify_header(struct mlx5e_ipsec_sa_entry *sa_entry,
 void mlx5_esw_ipsec_rx_id_mapping_remove(struct mlx5e_ipsec_sa_entry *sa_entry);
 int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv, u32 id,
 					  u32 *ipsec_obj_id);
+void mlx5_esw_ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec,
+				       struct mlx5e_ipsec_tx_create_attr *attr);
 #else
 static inline void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,
 						    struct mlx5e_ipsec_rx *rx) {}

@@ -55,5 +57,8 @@ static inline int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv,
 {
 	return -EINVAL;
 }
+
+static inline void mlx5_esw_ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec,
+						     struct mlx5e_ipsec_tx_create_attr *attr) {}
 #endif /* CONFIG_MLX5_ESWITCH */
 #endif /* __MLX5_ESW_IPSEC_FS_H__ */

index ae0dc8a3060d..1070cfa72678 100644
@@ -254,6 +254,7 @@ struct mlx5_esw_offload {
 	struct mlx5_flow_group *vport_rx_group;
 	struct mlx5_flow_group *vport_rx_drop_group;
 	struct mlx5_flow_handle *vport_rx_drop_rule;
+	struct mlx5_flow_table *ft_ipsec_tx_pol;
 	struct xarray vport_reps;
 	struct list_head peer_flows[MLX5_MAX_PORTS];
 	struct mutex peer_mutex;

index bdfe609cc9ec..e8bf18098203 100644
@@ -884,6 +884,17 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *on_esw,
 	dest.vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 
+	if (rep->vport == MLX5_VPORT_UPLINK && on_esw->offloads.ft_ipsec_tx_pol) {
+		dest.ft = on_esw->offloads.ft_ipsec_tx_pol;
+		flow_act.flags = FLOW_ACT_IGNORE_FLOW_LEVEL;
+		dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+	} else {
+		dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
+		dest.vport.num = rep->vport;
+		dest.vport.vhca_id = MLX5_CAP_GEN(rep->esw->dev, vhca_id);
+		dest.vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
+	}
+
 	if (MLX5_CAP_ESW_FLOWTABLE(on_esw->dev, flow_source) &&
 	    rep->vport == MLX5_VPORT_UPLINK)
 		spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_LOCAL_VPORT;

index 8ae1854d6b73..830ff8480fe1 100644
@@ -3015,6 +3015,12 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering)
 		goto out_err;
 	}
 
+	maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, FDB_CRYPTO_EGRESS, 3);
+	if (IS_ERR(maj_prio)) {
+		err = PTR_ERR(maj_prio);
+		goto out_err;
+	}
+
 	/* We put this priority last, knowing that nothing will get here
 	 * unless explicitly forwarded to. This is possible because the
 	 * slow path tables have catch all rules and nothing gets passed

index 6b1fa94f69c8..c302ec34255b 100644
@@ -115,6 +115,7 @@ enum {
 	FDB_TC_MISS,
 	FDB_BR_OFFLOAD,
 	FDB_SLOW_PATH,
+	FDB_CRYPTO_EGRESS,
 	FDB_PER_VPORT,
 };
 

index 830ff8480fe1..59df6156246e 100644
@@ -1066,7 +1066,7 @@ int mlx5_modify_rule_destination(struct mlx5_flow_handle *handle,
 	}
 
 	for (i = 0; i < handle->num_rules; i++) {
-		if (mlx5_flow_dests_cmp(new_dest, &handle->rule[i]->dest_attr))
+		if (mlx5_flow_dests_cmp(old_dest, &handle->rule[i]->dest_attr))
 			return _mlx5_modify_rule_destination(handle->rule[i],
 							     new_dest);
 	}

index a2f3ba811af8..2e5eb427f824 100644
@@ -254,8 +254,6 @@ static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	mlx5_del_flow_rules(rx->sa.rule);
 	mlx5_destroy_flow_group(rx->sa.group);
 	mlx5_destroy_flow_table(rx->ft.sa);
-	if (rx->allow_tunnel_mode)
-		mlx5_eswitch_unblock_encap(mdev);
 	if (rx == ipsec->rx_esw) {
 		mlx5_esw_ipsec_rx_status_destroy(ipsec, rx);
 	} else {

@@ -359,8 +357,6 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 		goto err_add;
 
 	/* Create FT */
-	if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_TUNNEL)
-		rx->allow_tunnel_mode = mlx5_eswitch_block_encap(mdev);
 	if (rx->allow_tunnel_mode)
 		flags = MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT;
 	ft = ipsec_ft_create(attr.ns, attr.sa_level, attr.prio, 2, flags);

@@ -415,8 +411,6 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 err_fs:
 	mlx5_destroy_flow_table(rx->ft.sa);
 err_fs_ft:
-	if (rx->allow_tunnel_mode)
-		mlx5_eswitch_unblock_encap(mdev);
 	mlx5_del_flow_rules(rx->status.rule);
 	mlx5_modify_header_dealloc(mdev, rx->status.modify_hdr);
 err_add:

@@ -434,13 +428,26 @@ static int rx_get(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	if (rx->ft.refcnt)
 		goto skip;
 
+	if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_TUNNEL)
+		rx->allow_tunnel_mode = mlx5_eswitch_block_encap(mdev);
+
+	err = mlx5_eswitch_block_mode_trylock(mdev);
+	if (err)
+		goto err_out;
+
 	err = rx_create(mdev, ipsec, rx, family);
+	mlx5_eswitch_block_mode_unlock(mdev, err);
 	if (err)
-		return err;
+		goto err_out;
 
 skip:
 	rx->ft.refcnt++;
 	return 0;
+
+err_out:
+	if (rx->allow_tunnel_mode)
+		mlx5_eswitch_unblock_encap(mdev);
+	return err;
 }
 
 static void rx_put(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_rx *rx,

@@ -449,7 +456,12 @@ static void rx_put(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_rx *rx,
 	if (--rx->ft.refcnt)
 		return;
 
+	mlx5_eswitch_unblock_mode_lock(ipsec->mdev);
 	rx_destroy(ipsec->mdev, ipsec, rx, family);
+	mlx5_eswitch_unblock_mode_unlock(ipsec->mdev);
+
+	if (rx->allow_tunnel_mode)
+		mlx5_eswitch_unblock_encap(ipsec->mdev);
 }
 
 static struct mlx5e_ipsec_rx *rx_ft_get(struct mlx5_core_dev *mdev,

@@ -569,8 +581,6 @@ static void tx_destroy(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx,
 		mlx5_destroy_flow_group(tx->sa.group);
 	}
 	mlx5_destroy_flow_table(tx->ft.sa);
-	if (tx->allow_tunnel_mode)
-		mlx5_eswitch_unblock_encap(ipsec->mdev);
 	mlx5_del_flow_rules(tx->status.rule);
 	mlx5_destroy_flow_table(tx->ft.status);
 }

@@ -611,8 +621,6 @@ static int tx_create(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx,
 	if (err)
 		goto err_status_rule;
 
-	if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_TUNNEL)
-		tx->allow_tunnel_mode = mlx5_eswitch_block_encap(mdev);
 	if (tx->allow_tunnel_mode)
 		flags = MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT;
 	ft = ipsec_ft_create(tx->ns, attr.sa_level, attr.prio, 4, flags);

@@ -679,8 +687,6 @@ static int tx_create(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx,
 err_sa_miss:
 	mlx5_destroy_flow_table(tx->ft.sa);
 err_sa_ft:
-	if (tx->allow_tunnel_mode)
-		mlx5_eswitch_unblock_encap(mdev);
 	mlx5_del_flow_rules(tx->status.rule);
 err_status_rule:
 	mlx5_destroy_flow_table(tx->ft.status);

@@ -714,16 +720,32 @@ static int tx_get(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	if (tx->ft.refcnt)
 		goto skip;
 
-	err = tx_create(ipsec, tx, ipsec->roce);
+	if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_TUNNEL)
+		tx->allow_tunnel_mode = mlx5_eswitch_block_encap(mdev);
+
+	err = mlx5_eswitch_block_mode_trylock(mdev);
 	if (err)
-		return err;
+		goto err_out;
+
+	err = tx_create(ipsec, tx, ipsec->roce);
+	if (err) {
+		mlx5_eswitch_block_mode_unlock(mdev, err);
+		goto err_out;
+	}
 
 	if (tx == ipsec->tx_esw)
 		ipsec_esw_tx_ft_policy_set(mdev, tx->ft.pol);
 
+	mlx5_eswitch_block_mode_unlock(mdev, err);
+
 skip:
 	tx->ft.refcnt++;
 	return 0;
+
+err_out:
+	if (tx->allow_tunnel_mode)
+		mlx5_eswitch_unblock_encap(mdev);
+	return err;
 }
 
 static void tx_put(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx)

@@ -731,10 +753,17 @@ static void tx_put(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx)
 	if (--tx->ft.refcnt)
 		return;
 
+	mlx5_eswitch_unblock_mode_lock(ipsec->mdev);
+
 	if (tx == ipsec->tx_esw)
 		ipsec_esw_tx_ft_policy_set(ipsec->mdev, NULL);
 
 	tx_destroy(ipsec, tx, ipsec->roce);
+
+	mlx5_eswitch_unblock_mode_unlock(ipsec->mdev);
+
+	if (tx->allow_tunnel_mode)
+		mlx5_eswitch_unblock_encap(ipsec->mdev);
 }
 
 static struct mlx5_flow_table *tx_ft_get_policy(struct mlx5_core_dev *mdev,

index 1070cfa72678..ddd16fd4a3a1 100644
@@ -270,6 +270,7 @@ struct mlx5_esw_offload {
 	u8 inline_mode;
 	atomic64_t num_flows;
 	u64 num_block_encap;
+	u64 num_block_mode;
 	enum devlink_eswitch_encap_mode encap;
 	struct ida vport_metadata_ida;
 	unsigned int host_number; /* ECPF supports one external host */

@@ -789,6 +790,11 @@ int mlx5_eswitch_reload_reps(struct mlx5_eswitch *esw);
 bool mlx5_eswitch_block_encap(struct mlx5_core_dev *dev);
 void mlx5_eswitch_unblock_encap(struct mlx5_core_dev *dev);
 
+int mlx5_eswitch_block_mode_trylock(struct mlx5_core_dev *dev);
+void mlx5_eswitch_block_mode_unlock(struct mlx5_core_dev *dev, int err);
+void mlx5_eswitch_unblock_mode_lock(struct mlx5_core_dev *dev);
+void mlx5_eswitch_unblock_mode_unlock(struct mlx5_core_dev *dev);
+
 static inline int mlx5_eswitch_num_vfs(struct mlx5_eswitch *esw)
 {
 	if (mlx5_esw_allowed(esw))

@@ -867,6 +873,14 @@ static inline bool mlx5_eswitch_block_encap(struct mlx5_core_dev *dev)
 static inline void mlx5_eswitch_unblock_encap(struct mlx5_core_dev *dev)
 {
 }
+
+static inline int mlx5_eswitch_block_mode_trylock(struct mlx5_core_dev *dev) { return 0; }
+
+static inline void mlx5_eswitch_block_mode_unlock(struct mlx5_core_dev *dev, int err) {}
+
+static inline void mlx5_eswitch_unblock_mode_lock(struct mlx5_core_dev *dev) {}
+
+static inline void mlx5_eswitch_unblock_mode_unlock(struct mlx5_core_dev *dev) {}
 #endif /* CONFIG_MLX5_ESWITCH */
 
 #endif /* __MLX5_ESWITCH_H__ */

82 lines not on this page · raw message

index 2e5eb427f824..c71230c3957e 100644
@@ -755,8 +755,10 @@ static void tx_put(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx)
 
 	mlx5_eswitch_unblock_mode_lock(ipsec->mdev);
 
-	if (tx == ipsec->tx_esw)
+	if (tx == ipsec->tx_esw) {
+		mlx5_esw_ipsec_restore_dest_uplink(ipsec->mdev);
 		ipsec_esw_tx_ft_policy_set(ipsec->mdev, NULL);
+	}
 
 	tx_destroy(ipsec, tx, ipsec->roce);
 

65 lines not on this page · raw message

index 275684f99ed3..0c90f7a8b0d3 100644
@@ -24,6 +24,7 @@ int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv, u32 id,
 					  u32 *ipsec_obj_id);
 void mlx5_esw_ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec,
 				       struct mlx5e_ipsec_tx_create_attr *attr);
+void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev);
 #else
 static inline void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,
 						    struct mlx5e_ipsec_rx *rx) {}

@@ -60,5 +61,7 @@ static inline int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv,
 
 static inline void mlx5_esw_ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec,
 						     struct mlx5e_ipsec_tx_create_attr *attr) {}
+
+static inline void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev) {}
 #endif /* CONFIG_MLX5_ESWITCH */
 #endif /* __MLX5_ESW_IPSEC_FS_H__ */

index ddd16fd4a3a1..def16c23aed7 100644
@@ -816,6 +816,8 @@ mlx5_eswitch_get_slow_fdb(struct mlx5_eswitch *esw)
 	return esw->fdb_table.offloads.slow_fdb;
 }
 
+int mlx5_eswitch_restore_ipsec_rule(struct mlx5_eswitch *esw, struct mlx5_flow_handle *rule,
+				    struct mlx5_esw_flow_attr *esw_attr, int attr_idx);
 #else  /* CONFIG_MLX5_ESWITCH */
 /* eswitch API stubs */
 static inline int  mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; }

115 lines not on this page · raw message

index 152b62138450..373f37584619 100644
@@ -1341,6 +1341,7 @@ static mlx5e_stats_grp_t mlx5e_ul_rep_stats_grps[] = {
 	&MLX5E_STATS_GRP(channels),
 	&MLX5E_STATS_GRP(per_port_buff_congest),
 #ifdef CONFIG_MLX5_EN_IPSEC
+	&MLX5E_STATS_GRP(ipsec_hw),
 	&MLX5E_STATS_GRP(ipsec_sw),
 #endif
 	&MLX5E_STATS_GRP(ptp),