net/mlx5e: Handle IPsec offload for RX datapath in switchdev mode

Reuse tun opts bits in reg c1, to pass IPsec obj id to datapath.
As this is only for RX SA and there are only 11 bits, xarray is used
to map IPsec obj id to an index, which is between 1 and 0x7ff, and
replace obj id to write to reg c1.

Signed-off-by: Jianbo Liu <[e-mail]>
Signed-off-by: Leon Romanovsky <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Jakub Kicinski <[e-mail]>

drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c

···
 	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:

drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h

···
 	struct mlx5e_ipsec_fc *fc;
 	struct mlx5_fs_chains *chains;
 	u8 allow_tunnel_mode : 1;
+	struct xarray ipsec_obj_id_map;
 };
 
 struct mlx5e_ipsec {
···
 	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 {

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

···
 		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;
 
···
 	}
 
 	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);
 }
 
···
 	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);
···
 		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);
 	}

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

···
 #include "ipsec.h"
 #include "ipsec_rxtx.h"
 #include "en.h"
+#include "esw/ipsec_fs.h"
 
 enum {
 	MLX5E_IPSEC_TX_SYNDROME_OFFLOAD = 0x8,
···
 	default:
 		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;
 }

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

···
 #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;
···
 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;

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

···
 
 	return 0;
 }
+
+int mlx5_esw_ipsec_rx_setup_modify_header(struct mlx5e_ipsec_sa_entry *sa_entry,
+					  struct mlx5_flow_act *flow_act)
+{
+	u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {};
+	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
+	struct mlx5_core_dev *mdev = ipsec->mdev;
+	struct mlx5_modify_hdr *modify_hdr;
+	u32 mapped_id;
+	int err;
+
+	err = xa_alloc_bh(&ipsec->rx_esw->ipsec_obj_id_map, &mapped_id,
+			  xa_mk_value(sa_entry->ipsec_obj_id),
+			  XA_LIMIT(1, ESW_IPSEC_RX_MAPPED_ID_MASK), 0);
+	if (err)
+		return err;
+
+	/* reuse tunnel bits for ipsec,
+	 * tun_id is always 0 and tun_opts is mapped to ipsec_obj_id.
+	 */
+	MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET);
+	MLX5_SET(set_action_in, action, field,
+		 MLX5_ACTION_IN_FIELD_METADATA_REG_C_1);
+	MLX5_SET(set_action_in, action, offset, ESW_ZONE_ID_BITS);
+	MLX5_SET(set_action_in, action, length,
+		 ESW_TUN_ID_BITS + ESW_TUN_OPTS_BITS);
+	MLX5_SET(set_action_in, action, data, mapped_id);
+
+	modify_hdr = mlx5_modify_header_alloc(mdev, MLX5_FLOW_NAMESPACE_FDB,
+					      1, action);
+	if (IS_ERR(modify_hdr)) {
+		err = PTR_ERR(modify_hdr);
+		goto err_header_alloc;
+	}
+
+	sa_entry->rx_mapped_id = mapped_id;
+	flow_act->modify_hdr = modify_hdr;
+	flow_act->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
+
+	return 0;
+
+err_header_alloc:
+	xa_erase_bh(&ipsec->rx_esw->ipsec_obj_id_map, mapped_id);
+	return err;
+}
+
+void mlx5_esw_ipsec_rx_id_mapping_remove(struct mlx5e_ipsec_sa_entry *sa_entry)
+{
+	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
+
+	if (sa_entry->rx_mapped_id)
+		xa_erase_bh(&ipsec->rx_esw->ipsec_obj_id_map,
+			    sa_entry->rx_mapped_id);
+}
+
+int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv, u32 id,
+					  u32 *ipsec_obj_id)
+{
+	struct mlx5e_ipsec *ipsec = priv->ipsec;
+	void *val;
+
+	val = xa_load(&ipsec->rx_esw->ipsec_obj_id_map, id);
+	if (!val)
+		return -ENOENT;
+
+	*ipsec_obj_id = xa_to_value(val);
+
+	return 0;
+}

drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h

···
 #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,
···
 				       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) {}
···
 
 static inline int mlx5_esw_ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ipsec,
 							 struct mlx5_flow_destination *dest)
+{
+	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;
 }

include/linux/mlx5/eswitch.h

···
 	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);