diff mbox series

[net-next,v7,4/6] net/mlx5: Refactor tc miss handling to a single function

Message ID 20230131091027.8093-5-paulb@nvidia.com (mailing list archive)
State Superseded
Delegated to: Netdev Maintainers
Headers show
Series net/sched: cls_api: Support hardware miss to tc action | expand

Checks

Context Check Description
netdev/tree_selection success Clearly marked for net-next, async
netdev/fixes_present success Fixes tag not required for -next series
netdev/subject_prefix success Link
netdev/cover_letter success Series has a cover letter
netdev/patch_count success Link
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 0 this patch: 0
netdev/cc_maintainers warning 3 maintainers not CCed: leon@kernel.org linux-rdma@vger.kernel.org maord@nvidia.com
netdev/build_clang success Errors and warnings before: 0 this patch: 0
netdev/module_param success Was 0 now: 0
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 0 this patch: 0
netdev/checkpatch warning WARNING: line length of 100 exceeds 80 columns WARNING: line length of 81 exceeds 80 columns WARNING: line length of 82 exceeds 80 columns WARNING: line length of 84 exceeds 80 columns WARNING: line length of 85 exceeds 80 columns WARNING: line length of 86 exceeds 80 columns WARNING: line length of 87 exceeds 80 columns WARNING: line length of 88 exceeds 80 columns WARNING: line length of 89 exceeds 80 columns WARNING: line length of 92 exceeds 80 columns WARNING: line length of 97 exceeds 80 columns WARNING: line length of 98 exceeds 80 columns
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0

Commit Message

Paul Blakey Jan. 31, 2023, 9:10 a.m. UTC 
Move tc miss handling code to en_tc.c, and remove
duplicate code.

Signed-off-by: Paul Blakey <paulb@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
---
 .../ethernet/mellanox/mlx5/core/en/rep/tc.c   | 224 ++----------------
 .../net/ethernet/mellanox/mlx5/core/en_rx.c   |   4 +-
 .../net/ethernet/mellanox/mlx5/core/en_tc.c   | 221 +++++++++++++++--
 .../net/ethernet/mellanox/mlx5/core/en_tc.h   |  11 +-
 4 files changed, 231 insertions(+), 229 deletions(-)

Comments

Leon Romanovsky Feb. 2, 2023, 11:07 a.m. UTC | #1 
On Tue, Jan 31, 2023 at 11:10:25AM +0200, Paul Blakey wrote:
> Move tc miss handling code to en_tc.c, and remove
> duplicate code.
> 
> Signed-off-by: Paul Blakey <paulb@nvidia.com>
> Reviewed-by: Roi Dayan <roid@nvidia.com>
> ---
>  .../ethernet/mellanox/mlx5/core/en/rep/tc.c   | 224 ++----------------
>  .../net/ethernet/mellanox/mlx5/core/en_rx.c   |   4 +-
>  .../net/ethernet/mellanox/mlx5/core/en_tc.c   | 221 +++++++++++++++--
>  .../net/ethernet/mellanox/mlx5/core/en_tc.h   |  11 +-
>  4 files changed, 231 insertions(+), 229 deletions(-)

<...>

>  void mlx5e_rep_tc_receive(struct mlx5_cqe64 *cqe, struct mlx5e_rq *rq,
>  			  struct sk_buff *skb)
>  {
> -	u32 reg_c1 = be32_to_cpu(cqe->ft_metadata);
> +	u32 reg_c1 = be32_to_cpu(cqe->ft_metadata), reg_c0, zone_restore_id, tunnel_id;

I would recommend to put reg_c1 = be32_to_cpu(cqe->ft_metadata) above
reg_c0 = ... below and not as part of long list of variables.

>  	struct mlx5e_tc_update_priv tc_priv = {};
> -	struct mlx5_mapped_obj mapped_obj;
> +	struct mlx5_rep_uplink_priv *uplink_priv;
> +	struct mlx5e_rep_priv *uplink_rpriv;
> +	struct mlx5_tc_ct_priv *ct_priv;
> +	struct mapping_ctx *mapping_ctx;
>  	struct mlx5_eswitch *esw;
> -	bool forward_tx = false;
>  	struct mlx5e_priv *priv;
> -	u32 reg_c0;
> -	int err;
>  
>  	reg_c0 = (be32_to_cpu(cqe->sop_drop_qpn) & MLX5E_TC_FLOW_ID_MASK);
>  	if (!reg_c0 || reg_c0 == MLX5_FS_DEFAULT_FLOW_TAG)
>  		goto forward;

<...>

> +static bool mlx5e_tc_restore_tunnel(struct mlx5e_priv *priv, struct sk_buff *skb,
> +				    struct mlx5e_tc_update_priv *tc_priv,
> +				    u32 tunnel_id)
>  {
> -#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
> -	u32 chain = 0, chain_tag, reg_b, zone_restore_id;
> -	struct mlx5e_priv *priv = netdev_priv(skb->dev);
> -	struct mlx5_mapped_obj mapped_obj;
> -	struct tc_skb_ext *tc_skb_ext;
> -	struct mlx5e_tc_table *tc;
> +	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
> +	struct tunnel_match_enc_opts enc_opts = {};
> +	struct mlx5_rep_uplink_priv *uplink_priv;
> +	struct mlx5e_rep_priv *uplink_rpriv;
> +	struct metadata_dst *tun_dst;
> +	struct tunnel_match_key key;
> +	u32 tun_id, enc_opts_id;
> +	struct net_device *dev;
>  	int err;
>  
> -	reg_b = be32_to_cpu(cqe->ft_metadata);
> -	tc = mlx5e_fs_get_tc(priv->fs);
> -	chain_tag = reg_b & MLX5E_TC_TABLE_CHAIN_TAG_MASK;
> +	enc_opts_id = tunnel_id & ENC_OPTS_BITS_MASK;
> +	tun_id = tunnel_id >> ENC_OPTS_BITS;
>  
> -	err = mapping_find(tc->mapping, chain_tag, &mapped_obj);
> +	if (!tun_id)
> +		return true;
> +
> +	uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
> +	uplink_priv = &uplink_rpriv->uplink_priv;
> +
> +	err = mapping_find(uplink_priv->tunnel_mapping, tun_id, &key);
>  	if (err) {
>  		netdev_dbg(priv->netdev,
> -			   "Couldn't find chain for chain tag: %d, err: %d\n",
> -			   chain_tag, err);
> +			   "Couldn't find tunnel for tun_id: %d, err: %d\n",
> +			   tun_id, err);
> +		return false;
> +	}
> +
> +	if (enc_opts_id) {
> +		err = mapping_find(uplink_priv->tunnel_enc_opts_mapping,
> +				   enc_opts_id, &enc_opts);
> +		if (err) {
> +			netdev_dbg(priv->netdev,
> +				   "Couldn't find tunnel (opts) for tun_id: %d, err: %d\n",
> +				   enc_opts_id, err);
> +			return false;
> +		}
> +	}
> +
> +	if (key.enc_control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
> +		tun_dst = __ip_tun_set_dst(key.enc_ipv4.src, key.enc_ipv4.dst,
> +					   key.enc_ip.tos, key.enc_ip.ttl,
> +					   key.enc_tp.dst, TUNNEL_KEY,
> +					   key32_to_tunnel_id(key.enc_key_id.keyid),
> +					   enc_opts.key.len);
> +	} else if (key.enc_control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
> +		tun_dst = __ipv6_tun_set_dst(&key.enc_ipv6.src, &key.enc_ipv6.dst,
> +					     key.enc_ip.tos, key.enc_ip.ttl,
> +					     key.enc_tp.dst, 0, TUNNEL_KEY,
> +					     key32_to_tunnel_id(key.enc_key_id.keyid),
> +					     enc_opts.key.len);
> +	} else {
> +		netdev_dbg(priv->netdev,
> +			   "Couldn't restore tunnel, unsupported addr_type: %d\n",
> +			   key.enc_control.addr_type);
>  		return false;
>  	}

I know that you moved this code from some other place, but it is not
mlx5 style, we use switch<->case for code like this.

>  
> -	if (mapped_obj.type == MLX5_MAPPED_OBJ_CHAIN) {
> -		chain = mapped_obj.chain;
> +	if (!tun_dst) {
> +		netdev_dbg(priv->netdev, "Couldn't restore tunnel, no tun_dst\n");
> +		return false;
> +	}
> +

<...>

> +static bool mlx5e_tc_restore_skb_chain(struct sk_buff *skb, struct mlx5_tc_ct_priv *ct_priv,
> +				       u32 chain, u32 zone_restore_id,
> +				       u32 tunnel_id,  struct mlx5e_tc_update_priv *tc_priv)
> +{
> +	struct mlx5e_priv *priv = netdev_priv(skb->dev);
> +	struct tc_skb_ext *tc_skb_ext;
> +
> +#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)

Is it possible to rewrite all these "#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)"
to something more close to recommended kernel style?

if (IS_ENABLED(CONFIG_NET_TC_SKB_EXT) && chain) {
 ...

Spaghetti code like this is not very friendly to ctags.

> +	if (chain) {
> +		if (!mlx5e_tc_ct_restore_flow(ct_priv, skb, zone_restore_id))
> +			return false;
> +
>  		tc_skb_ext = tc_skb_ext_alloc(skb);
> -		if (WARN_ON(!tc_skb_ext))
> +		if (!tc_skb_ext) {
> +			WARN_ON(1);
>  			return false;
> +		}
>  
>  		tc_skb_ext->chain = chain;
> +	}
> +#endif /* CONFIG_NET_TC_SKB_EXT */

<...>

> +bool mlx5e_tc_update_skb_nic(struct mlx5_cqe64 *cqe, struct sk_buff *skb)

This function is declared in .h file and has empty implementation for not
enabled CONFIG_NET_TC_SKB_EXT. Why do you need this IS_ENABLED?

> +{
> +#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
> +	struct mlx5e_priv *priv = netdev_priv(skb->dev);
> +	u32 mapped_obj_id, reg_b, zone_restore_id;
> +	struct mlx5_tc_ct_priv *ct_priv;
> +	struct mapping_ctx *mapping_ctx;
> +	struct mlx5e_tc_table *tc;
> +
> +	reg_b = be32_to_cpu(cqe->ft_metadata);
> +	tc = mlx5e_fs_get_tc(priv->fs);
> +	mapped_obj_id = reg_b & MLX5E_TC_TABLE_CHAIN_TAG_MASK;
> +	zone_restore_id = (reg_b >> MLX5_REG_MAPPING_MOFFSET(NIC_ZONE_RESTORE_TO_REG)) &
> +			  ESW_ZONE_ID_MASK;
> +	ct_priv = tc->ct;
> +	mapping_ctx = tc->mapping;
> +
> +	return mlx5e_tc_update_skb(cqe, skb, mapping_ctx, mapped_obj_id, ct_priv, zone_restore_id,
> +				   0, NULL);
>  #endif /* CONFIG_NET_TC_SKB_EXT */
>  
>  	return true;
> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
> index ce516dc7f3fd..4fa5d4e024cd 100644
> --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
> +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
> @@ -59,6 +59,8 @@ int mlx5e_tc_num_filters(struct mlx5e_priv *priv, unsigned long flags);
>  
>  struct mlx5e_tc_update_priv {
>  	struct net_device *fwd_dev;
> +	bool skb_done;
> +	bool forward_tx;
>  };
>  
>  struct mlx5_nic_flow_attr {
> @@ -386,14 +388,19 @@ static inline bool mlx5e_cqe_regb_chain(struct mlx5_cqe64 *cqe)
>  	return false;
>  }
>  
> -bool mlx5e_tc_update_skb(struct mlx5_cqe64 *cqe, struct sk_buff *skb);
> +bool mlx5e_tc_update_skb_nic(struct mlx5_cqe64 *cqe, struct sk_buff *skb);
> +bool mlx5e_tc_update_skb(struct mlx5_cqe64 *cqe, struct sk_buff *skb,
> +			 struct mapping_ctx *mapping_ctx, u32 mapped_obj_id,
> +			 struct mlx5_tc_ct_priv *ct_priv,
> +			 u32 zone_restore_id, u32 tunnel_id,
> +			 struct mlx5e_tc_update_priv *tc_priv);
>  #else /* CONFIG_MLX5_CLS_ACT */
>  static inline struct mlx5e_tc_table *mlx5e_tc_table_alloc(void) { return NULL; }
>  static inline void mlx5e_tc_table_free(struct mlx5e_tc_table *tc) {}
>  static inline bool mlx5e_cqe_regb_chain(struct mlx5_cqe64 *cqe)
>  { return false; }
>  static inline bool
> -mlx5e_tc_update_skb(struct mlx5_cqe64 *cqe, struct sk_buff *skb)
> +mlx5e_tc_update_skb_nic(struct mlx5_cqe64 *cqe, struct sk_buff *skb)
>  { return true; }
>  #endif
>  
> -- 
> 2.30.1
> 
>
diff mbox series

Patch

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
index b08339d986d5..4438c2a8d4ad 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
@@ -1,7 +1,6 @@ 
 // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
 /* Copyright (c) 2020 Mellanox Technologies. */
 
-#include <net/dst_metadata.h>
 #include <linux/netdevice.h>
 #include <linux/if_macvlan.h>
 #include <linux/list.h>
@@ -665,232 +664,53 @@  void mlx5e_rep_tc_netdevice_event_unregister(struct mlx5e_rep_priv *rpriv)
 				 mlx5e_rep_indr_block_unbind);
 }
 
-static bool mlx5e_restore_tunnel(struct mlx5e_priv *priv, struct sk_buff *skb,
-				 struct mlx5e_tc_update_priv *tc_priv,
-				 u32 tunnel_id)
-{
-	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-	struct tunnel_match_enc_opts enc_opts = {};
-	struct mlx5_rep_uplink_priv *uplink_priv;
-	struct mlx5e_rep_priv *uplink_rpriv;
-	struct metadata_dst *tun_dst;
-	struct tunnel_match_key key;
-	u32 tun_id, enc_opts_id;
-	struct net_device *dev;
-	int err;
-
-	enc_opts_id = tunnel_id & ENC_OPTS_BITS_MASK;
-	tun_id = tunnel_id >> ENC_OPTS_BITS;
-
-	if (!tun_id)
-		return true;
-
-	uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
-	uplink_priv = &uplink_rpriv->uplink_priv;
-
-	err = mapping_find(uplink_priv->tunnel_mapping, tun_id, &key);
-	if (err) {
-		netdev_dbg(priv->netdev,
-			   "Couldn't find tunnel for tun_id: %d, err: %d\n",
-			   tun_id, err);
-		return false;
-	}
-
-	if (enc_opts_id) {
-		err = mapping_find(uplink_priv->tunnel_enc_opts_mapping,
-				   enc_opts_id, &enc_opts);
-		if (err) {
-			netdev_dbg(priv->netdev,
-				   "Couldn't find tunnel (opts) for tun_id: %d, err: %d\n",
-				   enc_opts_id, err);
-			return false;
-		}
-	}
-
-	if (key.enc_control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
-		tun_dst = __ip_tun_set_dst(key.enc_ipv4.src, key.enc_ipv4.dst,
-					   key.enc_ip.tos, key.enc_ip.ttl,
-					   key.enc_tp.dst, TUNNEL_KEY,
-					   key32_to_tunnel_id(key.enc_key_id.keyid),
-					   enc_opts.key.len);
-	} else if (key.enc_control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
-		tun_dst = __ipv6_tun_set_dst(&key.enc_ipv6.src, &key.enc_ipv6.dst,
-					     key.enc_ip.tos, key.enc_ip.ttl,
-					     key.enc_tp.dst, 0, TUNNEL_KEY,
-					     key32_to_tunnel_id(key.enc_key_id.keyid),
-					     enc_opts.key.len);
-	} else {
-		netdev_dbg(priv->netdev,
-			   "Couldn't restore tunnel, unsupported addr_type: %d\n",
-			   key.enc_control.addr_type);
-		return false;
-	}
-
-	if (!tun_dst) {
-		netdev_dbg(priv->netdev, "Couldn't restore tunnel, no tun_dst\n");
-		return false;
-	}
-
-	tun_dst->u.tun_info.key.tp_src = key.enc_tp.src;
-
-	if (enc_opts.key.len)
-		ip_tunnel_info_opts_set(&tun_dst->u.tun_info,
-					enc_opts.key.data,
-					enc_opts.key.len,
-					enc_opts.key.dst_opt_type);
-
-	skb_dst_set(skb, (struct dst_entry *)tun_dst);
-	dev = dev_get_by_index(&init_net, key.filter_ifindex);
-	if (!dev) {
-		netdev_dbg(priv->netdev,
-			   "Couldn't find tunnel device with ifindex: %d\n",
-			   key.filter_ifindex);
-		return false;
-	}
-
-	/* Set fwd_dev so we do dev_put() after datapath */
-	tc_priv->fwd_dev = dev;
-
-	skb->dev = dev;
-
-	return true;
-}
-
-static bool mlx5e_restore_skb_chain(struct sk_buff *skb, u32 chain, u32 reg_c1,
-				    struct mlx5e_tc_update_priv *tc_priv)
-{
-	struct mlx5e_priv *priv = netdev_priv(skb->dev);
-	u32 tunnel_id = (reg_c1 >> ESW_TUN_OFFSET) & TUNNEL_ID_MASK;
-
-#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
-	if (chain) {
-		struct mlx5_rep_uplink_priv *uplink_priv;
-		struct mlx5e_rep_priv *uplink_rpriv;
-		struct tc_skb_ext *tc_skb_ext;
-		struct mlx5_eswitch *esw;
-		u32 zone_restore_id;
-
-		tc_skb_ext = tc_skb_ext_alloc(skb);
-		if (!tc_skb_ext) {
-			WARN_ON(1);
-			return false;
-		}
-		tc_skb_ext->chain = chain;
-		zone_restore_id = reg_c1 & ESW_ZONE_ID_MASK;
-		esw = priv->mdev->priv.eswitch;
-		uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
-		uplink_priv = &uplink_rpriv->uplink_priv;
-		if (!mlx5e_tc_ct_restore_flow(uplink_priv->ct_priv, skb,
-					      zone_restore_id))
-			return false;
-	}
-#endif /* CONFIG_NET_TC_SKB_EXT */
-
-	return mlx5e_restore_tunnel(priv, skb, tc_priv, tunnel_id);
-}
-
-static void mlx5_rep_tc_post_napi_receive(struct mlx5e_tc_update_priv *tc_priv)
-{
-	if (tc_priv->fwd_dev)
-		dev_put(tc_priv->fwd_dev);
-}
-
-static void mlx5e_restore_skb_sample(struct mlx5e_priv *priv, struct sk_buff *skb,
-				     struct mlx5_mapped_obj *mapped_obj,
-				     struct mlx5e_tc_update_priv *tc_priv)
-{
-	if (!mlx5e_restore_tunnel(priv, skb, tc_priv, mapped_obj->sample.tunnel_id)) {
-		netdev_dbg(priv->netdev,
-			   "Failed to restore tunnel info for sampled packet\n");
-		return;
-	}
-	mlx5e_tc_sample_skb(skb, mapped_obj);
-	mlx5_rep_tc_post_napi_receive(tc_priv);
-}
-
-static bool mlx5e_restore_skb_int_port(struct mlx5e_priv *priv, struct sk_buff *skb,
-				       struct mlx5_mapped_obj *mapped_obj,
-				       struct mlx5e_tc_update_priv *tc_priv,
-				       bool *forward_tx,
-				       u32 reg_c1)
-{
-	u32 tunnel_id = (reg_c1 >> ESW_TUN_OFFSET) & TUNNEL_ID_MASK;
-	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-	struct mlx5_rep_uplink_priv *uplink_priv;
-	struct mlx5e_rep_priv *uplink_rpriv;
-
-	/* Tunnel restore takes precedence over int port restore */
-	if (tunnel_id)
-		return mlx5e_restore_tunnel(priv, skb, tc_priv, tunnel_id);
-
-	uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
-	uplink_priv = &uplink_rpriv->uplink_priv;
-
-	if (mlx5e_tc_int_port_dev_fwd(uplink_priv->int_port_priv, skb,
-				      mapped_obj->int_port_metadata, forward_tx)) {
-		/* Set fwd_dev for future dev_put */
-		tc_priv->fwd_dev = skb->dev;
-
-		return true;
-	}
-
-	return false;
-}
-
 void mlx5e_rep_tc_receive(struct mlx5_cqe64 *cqe, struct mlx5e_rq *rq,
 			  struct sk_buff *skb)
 {
-	u32 reg_c1 = be32_to_cpu(cqe->ft_metadata);
+	u32 reg_c1 = be32_to_cpu(cqe->ft_metadata), reg_c0, zone_restore_id, tunnel_id;
 	struct mlx5e_tc_update_priv tc_priv = {};
-	struct mlx5_mapped_obj mapped_obj;
+	struct mlx5_rep_uplink_priv *uplink_priv;
+	struct mlx5e_rep_priv *uplink_rpriv;
+	struct mlx5_tc_ct_priv *ct_priv;
+	struct mapping_ctx *mapping_ctx;
 	struct mlx5_eswitch *esw;
-	bool forward_tx = false;
 	struct mlx5e_priv *priv;
-	u32 reg_c0;
-	int err;
 
 	reg_c0 = (be32_to_cpu(cqe->sop_drop_qpn) & MLX5E_TC_FLOW_ID_MASK);
 	if (!reg_c0 || reg_c0 == MLX5_FS_DEFAULT_FLOW_TAG)
 		goto forward;
 
-	/* If reg_c0 is not equal to the default flow tag then skb->mark
+	/* If mapped_obj_id is not equal to the default flow tag then skb->mark
 	 * is not supported and must be reset back to 0.
 	 */
 	skb->mark = 0;
 
 	priv = netdev_priv(skb->dev);
 	esw = priv->mdev->priv.eswitch;
-	err = mapping_find(esw->offloads.reg_c0_obj_pool, reg_c0, &mapped_obj);
-	if (err) {
-		netdev_dbg(priv->netdev,
-			   "Couldn't find mapped object for reg_c0: %d, err: %d\n",
-			   reg_c0, err);
-		goto free_skb;
-	}
+	mapping_ctx = esw->offloads.reg_c0_obj_pool;
+	zone_restore_id = reg_c1 & ESW_ZONE_ID_MASK;
+	tunnel_id = (reg_c1 >> ESW_TUN_OFFSET) & TUNNEL_ID_MASK;
 
-	if (mapped_obj.type == MLX5_MAPPED_OBJ_CHAIN) {
-		if (!mlx5e_restore_skb_chain(skb, mapped_obj.chain, reg_c1, &tc_priv) &&
-		    !mlx5_ipsec_is_rx_flow(cqe))
-			goto free_skb;
-	} else if (mapped_obj.type == MLX5_MAPPED_OBJ_SAMPLE) {
-		mlx5e_restore_skb_sample(priv, skb, &mapped_obj, &tc_priv);
-		goto free_skb;
-	} else if (mapped_obj.type == MLX5_MAPPED_OBJ_INT_PORT_METADATA) {
-		if (!mlx5e_restore_skb_int_port(priv, skb, &mapped_obj, &tc_priv,
-						&forward_tx, reg_c1))
-			goto free_skb;
-	} else {
-		netdev_dbg(priv->netdev, "Invalid mapped object type: %d\n", mapped_obj.type);
+	uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
+	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))
 		goto free_skb;
-	}
 
 forward:
-	if (forward_tx)
+	if (tc_priv.skb_done)
+		goto free_skb;
+
+	if (tc_priv.forward_tx)
 		dev_queue_xmit(skb);
 	else
 		napi_gro_receive(rq->cq.napi, skb);
 
-	mlx5_rep_tc_post_napi_receive(&tc_priv);
+	if (tc_priv.fwd_dev)
+		dev_put(tc_priv.fwd_dev);
 
 	return;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index a9473a51edc1..fea0c2aa95e2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1792,7 +1792,7 @@  static void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
 
 	if (mlx5e_cqe_regb_chain(cqe))
-		if (!mlx5e_tc_update_skb(cqe, skb)) {
+		if (!mlx5e_tc_update_skb_nic(cqe, skb)) {
 			dev_kfree_skb_any(skb);
 			goto free_wqe;
 		}
@@ -2259,7 +2259,7 @@  static void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cq
 	mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
 
 	if (mlx5e_cqe_regb_chain(cqe))
-		if (!mlx5e_tc_update_skb(cqe, skb)) {
+		if (!mlx5e_tc_update_skb_nic(cqe, skb)) {
 			dev_kfree_skb_any(skb);
 			goto mpwrq_cqe_out;
 		}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 4e6f5caf8ab6..6275c451e32a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -43,6 +43,7 @@ 
 #include <net/ipv6_stubs.h>
 #include <net/bareudp.h>
 #include <net/bonding.h>
+#include <net/dst_metadata.h>
 #include "en.h"
 #include "en/tc/post_act.h"
 #include "en_rep.h"
@@ -5562,47 +5563,221 @@  int mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 	}
 }
 
-bool mlx5e_tc_update_skb(struct mlx5_cqe64 *cqe,
-			 struct sk_buff *skb)
+static bool mlx5e_tc_restore_tunnel(struct mlx5e_priv *priv, struct sk_buff *skb,
+				    struct mlx5e_tc_update_priv *tc_priv,
+				    u32 tunnel_id)
 {
-#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
-	u32 chain = 0, chain_tag, reg_b, zone_restore_id;
-	struct mlx5e_priv *priv = netdev_priv(skb->dev);
-	struct mlx5_mapped_obj mapped_obj;
-	struct tc_skb_ext *tc_skb_ext;
-	struct mlx5e_tc_table *tc;
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	struct tunnel_match_enc_opts enc_opts = {};
+	struct mlx5_rep_uplink_priv *uplink_priv;
+	struct mlx5e_rep_priv *uplink_rpriv;
+	struct metadata_dst *tun_dst;
+	struct tunnel_match_key key;
+	u32 tun_id, enc_opts_id;
+	struct net_device *dev;
 	int err;
 
-	reg_b = be32_to_cpu(cqe->ft_metadata);
-	tc = mlx5e_fs_get_tc(priv->fs);
-	chain_tag = reg_b & MLX5E_TC_TABLE_CHAIN_TAG_MASK;
+	enc_opts_id = tunnel_id & ENC_OPTS_BITS_MASK;
+	tun_id = tunnel_id >> ENC_OPTS_BITS;
 
-	err = mapping_find(tc->mapping, chain_tag, &mapped_obj);
+	if (!tun_id)
+		return true;
+
+	uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
+	uplink_priv = &uplink_rpriv->uplink_priv;
+
+	err = mapping_find(uplink_priv->tunnel_mapping, tun_id, &key);
 	if (err) {
 		netdev_dbg(priv->netdev,
-			   "Couldn't find chain for chain tag: %d, err: %d\n",
-			   chain_tag, err);
+			   "Couldn't find tunnel for tun_id: %d, err: %d\n",
+			   tun_id, err);
+		return false;
+	}
+
+	if (enc_opts_id) {
+		err = mapping_find(uplink_priv->tunnel_enc_opts_mapping,
+				   enc_opts_id, &enc_opts);
+		if (err) {
+			netdev_dbg(priv->netdev,
+				   "Couldn't find tunnel (opts) for tun_id: %d, err: %d\n",
+				   enc_opts_id, err);
+			return false;
+		}
+	}
+
+	if (key.enc_control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
+		tun_dst = __ip_tun_set_dst(key.enc_ipv4.src, key.enc_ipv4.dst,
+					   key.enc_ip.tos, key.enc_ip.ttl,
+					   key.enc_tp.dst, TUNNEL_KEY,
+					   key32_to_tunnel_id(key.enc_key_id.keyid),
+					   enc_opts.key.len);
+	} else if (key.enc_control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
+		tun_dst = __ipv6_tun_set_dst(&key.enc_ipv6.src, &key.enc_ipv6.dst,
+					     key.enc_ip.tos, key.enc_ip.ttl,
+					     key.enc_tp.dst, 0, TUNNEL_KEY,
+					     key32_to_tunnel_id(key.enc_key_id.keyid),
+					     enc_opts.key.len);
+	} else {
+		netdev_dbg(priv->netdev,
+			   "Couldn't restore tunnel, unsupported addr_type: %d\n",
+			   key.enc_control.addr_type);
 		return false;
 	}
 
-	if (mapped_obj.type == MLX5_MAPPED_OBJ_CHAIN) {
-		chain = mapped_obj.chain;
+	if (!tun_dst) {
+		netdev_dbg(priv->netdev, "Couldn't restore tunnel, no tun_dst\n");
+		return false;
+	}
+
+	tun_dst->u.tun_info.key.tp_src = key.enc_tp.src;
+
+	if (enc_opts.key.len)
+		ip_tunnel_info_opts_set(&tun_dst->u.tun_info,
+					enc_opts.key.data,
+					enc_opts.key.len,
+					enc_opts.key.dst_opt_type);
+
+	skb_dst_set(skb, (struct dst_entry *)tun_dst);
+	dev = dev_get_by_index(&init_net, key.filter_ifindex);
+	if (!dev) {
+		netdev_dbg(priv->netdev,
+			   "Couldn't find tunnel device with ifindex: %d\n",
+			   key.filter_ifindex);
+		return false;
+	}
+
+	/* Set fwd_dev so we do dev_put() after datapath */
+	tc_priv->fwd_dev = dev;
+
+	skb->dev = dev;
+
+	return true;
+}
+
+static bool mlx5e_tc_restore_skb_chain(struct sk_buff *skb, struct mlx5_tc_ct_priv *ct_priv,
+				       u32 chain, u32 zone_restore_id,
+				       u32 tunnel_id,  struct mlx5e_tc_update_priv *tc_priv)
+{
+	struct mlx5e_priv *priv = netdev_priv(skb->dev);
+	struct tc_skb_ext *tc_skb_ext;
+
+#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
+	if (chain) {
+		if (!mlx5e_tc_ct_restore_flow(ct_priv, skb, zone_restore_id))
+			return false;
+
 		tc_skb_ext = tc_skb_ext_alloc(skb);
-		if (WARN_ON(!tc_skb_ext))
+		if (!tc_skb_ext) {
+			WARN_ON(1);
 			return false;
+		}
 
 		tc_skb_ext->chain = chain;
+	}
+#endif /* CONFIG_NET_TC_SKB_EXT */
 
-		zone_restore_id = (reg_b >> MLX5_REG_MAPPING_MOFFSET(NIC_ZONE_RESTORE_TO_REG)) &
-			ESW_ZONE_ID_MASK;
+	if (tc_priv)
+		return mlx5e_tc_restore_tunnel(priv, skb, tc_priv, tunnel_id);
 
-		if (!mlx5e_tc_ct_restore_flow(tc->ct, skb,
-					      zone_restore_id))
-			return false;
-	} else {
+	return true;
+}
+
+static void mlx5e_tc_restore_skb_sample(struct mlx5e_priv *priv, struct sk_buff *skb,
+					struct mlx5_mapped_obj *mapped_obj,
+					struct mlx5e_tc_update_priv *tc_priv)
+{
+	if (!mlx5e_tc_restore_tunnel(priv, skb, tc_priv, mapped_obj->sample.tunnel_id)) {
+		netdev_dbg(priv->netdev,
+			   "Failed to restore tunnel info for sampled packet\n");
+		return;
+	}
+	mlx5e_tc_sample_skb(skb, mapped_obj);
+}
+
+static bool mlx5e_tc_restore_skb_int_port(struct mlx5e_priv *priv, struct sk_buff *skb,
+					  struct mlx5_mapped_obj *mapped_obj,
+					  struct mlx5e_tc_update_priv *tc_priv,
+					  u32 tunnel_id)
+{
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	struct mlx5_rep_uplink_priv *uplink_priv;
+	struct mlx5e_rep_priv *uplink_rpriv;
+	bool forward_tx = false;
+
+	/* Tunnel restore takes precedence over int port restore */
+	if (tunnel_id)
+		return mlx5e_tc_restore_tunnel(priv, skb, tc_priv, tunnel_id);
+
+	uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
+	uplink_priv = &uplink_rpriv->uplink_priv;
+
+	if (mlx5e_tc_int_port_dev_fwd(uplink_priv->int_port_priv, skb,
+				      mapped_obj->int_port_metadata, &forward_tx)) {
+		/* Set fwd_dev for future dev_put */
+		tc_priv->fwd_dev = skb->dev;
+		tc_priv->forward_tx = forward_tx;
+
+		return true;
+	}
+
+	return false;
+}
+
+bool mlx5e_tc_update_skb(struct mlx5_cqe64 *cqe, struct sk_buff *skb,
+			 struct mapping_ctx *mapping_ctx, u32 mapped_obj_id,
+			 struct mlx5_tc_ct_priv *ct_priv,
+			 u32 zone_restore_id, u32 tunnel_id,
+			 struct mlx5e_tc_update_priv *tc_priv)
+{
+	struct mlx5e_priv *priv = netdev_priv(skb->dev);
+	struct mlx5_mapped_obj mapped_obj;
+	int err;
+
+	err = mapping_find(mapping_ctx, mapped_obj_id, &mapped_obj);
+	if (err) {
+		netdev_dbg(skb->dev,
+			   "Couldn't find mapped object for mapped_obj_id: %d, err: %d\n",
+			   mapped_obj_id, err);
+		return false;
+	}
+
+	switch (mapped_obj.type) {
+	case MLX5_MAPPED_OBJ_CHAIN:
+		return mlx5e_tc_restore_skb_chain(skb, ct_priv, mapped_obj.chain, zone_restore_id,
+						  tunnel_id, tc_priv);
+	case MLX5_MAPPED_OBJ_SAMPLE:
+		mlx5e_tc_restore_skb_sample(priv, skb, &mapped_obj, tc_priv);
+		tc_priv->skb_done = true;
+		return true;
+	case MLX5_MAPPED_OBJ_INT_PORT_METADATA:
+		return mlx5e_tc_restore_skb_int_port(priv, skb, &mapped_obj, tc_priv, tunnel_id);
+	default:
 		netdev_dbg(priv->netdev, "Invalid mapped object type: %d\n", mapped_obj.type);
 		return false;
 	}
+
+	return false;
+}
+
+bool mlx5e_tc_update_skb_nic(struct mlx5_cqe64 *cqe, struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
+	struct mlx5e_priv *priv = netdev_priv(skb->dev);
+	u32 mapped_obj_id, reg_b, zone_restore_id;
+	struct mlx5_tc_ct_priv *ct_priv;
+	struct mapping_ctx *mapping_ctx;
+	struct mlx5e_tc_table *tc;
+
+	reg_b = be32_to_cpu(cqe->ft_metadata);
+	tc = mlx5e_fs_get_tc(priv->fs);
+	mapped_obj_id = reg_b & MLX5E_TC_TABLE_CHAIN_TAG_MASK;
+	zone_restore_id = (reg_b >> MLX5_REG_MAPPING_MOFFSET(NIC_ZONE_RESTORE_TO_REG)) &
+			  ESW_ZONE_ID_MASK;
+	ct_priv = tc->ct;
+	mapping_ctx = tc->mapping;
+
+	return mlx5e_tc_update_skb(cqe, skb, mapping_ctx, mapped_obj_id, ct_priv, zone_restore_id,
+				   0, NULL);
 #endif /* CONFIG_NET_TC_SKB_EXT */
 
 	return true;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index ce516dc7f3fd..4fa5d4e024cd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -59,6 +59,8 @@  int mlx5e_tc_num_filters(struct mlx5e_priv *priv, unsigned long flags);
 
 struct mlx5e_tc_update_priv {
 	struct net_device *fwd_dev;
+	bool skb_done;
+	bool forward_tx;
 };
 
 struct mlx5_nic_flow_attr {
@@ -386,14 +388,19 @@  static inline bool mlx5e_cqe_regb_chain(struct mlx5_cqe64 *cqe)
 	return false;
 }
 
-bool mlx5e_tc_update_skb(struct mlx5_cqe64 *cqe, struct sk_buff *skb);
+bool mlx5e_tc_update_skb_nic(struct mlx5_cqe64 *cqe, struct sk_buff *skb);
+bool mlx5e_tc_update_skb(struct mlx5_cqe64 *cqe, struct sk_buff *skb,
+			 struct mapping_ctx *mapping_ctx, u32 mapped_obj_id,
+			 struct mlx5_tc_ct_priv *ct_priv,
+			 u32 zone_restore_id, u32 tunnel_id,
+			 struct mlx5e_tc_update_priv *tc_priv);
 #else /* CONFIG_MLX5_CLS_ACT */
 static inline struct mlx5e_tc_table *mlx5e_tc_table_alloc(void) { return NULL; }
 static inline void mlx5e_tc_table_free(struct mlx5e_tc_table *tc) {}
 static inline bool mlx5e_cqe_regb_chain(struct mlx5_cqe64 *cqe)
 { return false; }
 static inline bool
-mlx5e_tc_update_skb(struct mlx5_cqe64 *cqe, struct sk_buff *skb)
+mlx5e_tc_update_skb_nic(struct mlx5_cqe64 *cqe, struct sk_buff *skb)
 { return true; }
 #endif