Merge tag 'mlx5-GRE-Offload' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5-updates-2017-08-31 (GRE Offloads support)

This series provides the support for MPLS RSS and GRE TX offloads and
RSS support.

The first patch from Gal and Ariel provides the mlx5 driver support for
ConnectX capability to perform IP version identification and matching in
order to distinguish between IPv4 and IPv6 without the need to specify the
encapsulation type, thus perform RSS in MPLS automatically without
specifying MPLS ethertyoe. This patch will also serve for inner GRE IPv4/6
classification for inner GRE RSS.

2nd patch from Gal, Adds the TX offloads support for GRE tunneled packets,
by reporting the needed netdev features.

3rd patch from Gal, Adds GRE inner RSS support by creating the needed device
resources (Steering Tables/rules and traffic classifiers) to Match GRE traffic
and perform RSS hashing on the inner headers.

Improvement:
Testing 8 TCP streams bandwidth over GRE:
    System: Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz
    NIC: Mellanox Technologies MT28800 Family [ConnectX-5 Ex]
    Before: 21.3 Gbps (Single RQ)
    Now   : 90.5 Gbps (RSS spread on 8 RQs)
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 383 insertions, 39 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 0039b4725405..a31912415264 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -620,6 +620,12 @@ enum mlx5e_traffic_types {
 	MLX5E_NUM_INDIR_TIRS = MLX5E_TT_ANY,
 };
 
+enum mlx5e_tunnel_types {
+	MLX5E_TT_IPV4_GRE,
+	MLX5E_TT_IPV6_GRE,
+	MLX5E_NUM_TUNNEL_TT,
+};
+
 enum {
 	MLX5E_STATE_ASYNC_EVENTS_ENABLED,
 	MLX5E_STATE_OPENED,
@@ -679,6 +685,7 @@ struct mlx5e_l2_table {
 struct mlx5e_ttc_table {
 	struct mlx5e_flow_table  ft;
 	struct mlx5_flow_handle	 *rules[MLX5E_NUM_TT];
+	struct mlx5_flow_handle  *tunnel_rules[MLX5E_NUM_TUNNEL_TT];
 };
 
 #define ARFS_HASH_SHIFT BITS_PER_BYTE
@@ -711,6 +718,7 @@ enum {
 	MLX5E_VLAN_FT_LEVEL = 0,
 	MLX5E_L2_FT_LEVEL,
 	MLX5E_TTC_FT_LEVEL,
+	MLX5E_INNER_TTC_FT_LEVEL,
 	MLX5E_ARFS_FT_LEVEL
 };
 
@@ -736,6 +744,7 @@ struct mlx5e_flow_steering {
 	struct mlx5e_vlan_table         vlan;
 	struct mlx5e_l2_table           l2;
 	struct mlx5e_ttc_table          ttc;
+	struct mlx5e_ttc_table          inner_ttc;
 	struct mlx5e_arfs_tables        arfs;
 };
 
@@ -769,6 +778,7 @@ struct mlx5e_priv {
 	u32                        tisn[MLX5E_MAX_NUM_TC];
 	struct mlx5e_rqt           indir_rqt;
 	struct mlx5e_tir           indir_tir[MLX5E_NUM_INDIR_TIRS];
+	struct mlx5e_tir           inner_indir_tir[MLX5E_NUM_INDIR_TIRS];
 	struct mlx5e_tir           direct_tir[MLX5E_MAX_NUM_CHANNELS];
 	u32                        tx_rates[MLX5E_MAX_NUM_SQS];
 	int                        hard_mtu;
@@ -903,7 +913,7 @@ int mlx5e_redirect_rqt(struct mlx5e_priv *priv, u32 rqtn, int sz,
 		       struct mlx5e_redirect_rqt_param rrp);
 void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_params *params,
 				    enum mlx5e_traffic_types tt,
-				    void *tirc);
+				    void *tirc, bool inner);
 
 int mlx5e_open_locked(struct net_device *netdev);
 int mlx5e_close_locked(struct net_device *netdev);
@@ -932,6 +942,12 @@ void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params,
 void mlx5e_set_rq_type_params(struct mlx5_core_dev *mdev,
 			      struct mlx5e_params *params, u8 rq_type);
 
+static inline bool mlx5e_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev)
+{
+	return (MLX5_CAP_ETH(mdev, tunnel_stateless_gre) &&
+		MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ft_field_support.inner_ip_version));
+}
+
 static inline
 struct mlx5e_tx_wqe *mlx5e_post_nop(struct mlx5_wq_cyc *wq, u32 sqn, u16 *pc)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 0dd7e9caf150..c6ec90e9c95b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1212,9 +1212,18 @@ static void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen)
 
 	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
 		memset(tirc, 0, ctxlen);
-		mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc);
+		mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc, false);
 		mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in, inlen);
 	}
+
+	if (!mlx5e_tunnel_inner_ft_supported(priv->mdev))
+		return;
+
+	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
+		memset(tirc, 0, ctxlen);
+		mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc, true);
+		mlx5_core_modify_tir(mdev, priv->inner_indir_tir[tt].tirn, in, inlen);
+	}
 }
 
 static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
index eecbc6d4f51f..f11fd07ac4dd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
@@ -608,12 +608,21 @@ static void mlx5e_cleanup_ttc_rules(struct mlx5e_ttc_table *ttc)
 			ttc->rules[i] = NULL;
 		}
 	}
+
+	for (i = 0; i < MLX5E_NUM_TUNNEL_TT; i++) {
+		if (!IS_ERR_OR_NULL(ttc->tunnel_rules[i])) {
+			mlx5_del_flow_rules(ttc->tunnel_rules[i]);
+			ttc->tunnel_rules[i] = NULL;
+		}
+	}
 }
 
-static struct {
+struct mlx5e_etype_proto {
 	u16 etype;
 	u8 proto;
-} ttc_rules[] = {
+};
+
+static struct mlx5e_etype_proto ttc_rules[] = {
 	[MLX5E_TT_IPV4_TCP] = {
 		.etype = ETH_P_IP,
 		.proto = IPPROTO_TCP,
@@ -660,6 +669,28 @@ static struct {
 	},
 };
 
+static struct mlx5e_etype_proto ttc_tunnel_rules[] = {
+	[MLX5E_TT_IPV4_GRE] = {
+		.etype = ETH_P_IP,
+		.proto = IPPROTO_GRE,
+	},
+	[MLX5E_TT_IPV6_GRE] = {
+		.etype = ETH_P_IPV6,
+		.proto = IPPROTO_GRE,
+	},
+};
+
+static u8 mlx5e_etype_to_ipv(u16 ethertype)
+{
+	if (ethertype == ETH_P_IP)
+		return 4;
+
+	if (ethertype == ETH_P_IPV6)
+		return 6;
+
+	return 0;
+}
+
 static struct mlx5_flow_handle *
 mlx5e_generate_ttc_rule(struct mlx5e_priv *priv,
 			struct mlx5_flow_table *ft,
@@ -667,10 +698,12 @@ mlx5e_generate_ttc_rule(struct mlx5e_priv *priv,
 			u16 etype,
 			u8 proto)
 {
+	int match_ipv_outer = MLX5_CAP_FLOWTABLE_NIC_RX(priv->mdev, ft_field_support.outer_ip_version);
 	MLX5_DECLARE_FLOW_ACT(flow_act);
 	struct mlx5_flow_handle *rule;
 	struct mlx5_flow_spec *spec;
 	int err = 0;
+	u8 ipv;
 
 	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
 	if (!spec)
@@ -681,7 +714,13 @@ mlx5e_generate_ttc_rule(struct mlx5e_priv *priv,
 		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, proto);
 	}
-	if (etype) {
+
+	ipv = mlx5e_etype_to_ipv(etype);
+	if (match_ipv_outer && ipv) {
+		spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ip_version);
+		MLX5_SET(fte_match_param, spec->match_value, outer_headers.ip_version, ipv);
+	} else if (etype) {
 		spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
 		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ethertype);
 		MLX5_SET(fte_match_param, spec->match_value, outer_headers.ethertype, etype);
@@ -723,6 +762,20 @@ static int mlx5e_generate_ttc_table_rules(struct mlx5e_priv *priv)
 			goto del_rules;
 	}
 
+	if (!mlx5e_tunnel_inner_ft_supported(priv->mdev))
+		return 0;
+
+	rules     = ttc->tunnel_rules;
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+	dest.ft   = priv->fs.inner_ttc.ft.t;
+	for (tt = 0; tt < MLX5E_NUM_TUNNEL_TT; tt++) {
+		rules[tt] = mlx5e_generate_ttc_rule(priv, ft, &dest,
+						    ttc_tunnel_rules[tt].etype,
+						    ttc_tunnel_rules[tt].proto);
+		if (IS_ERR(rules[tt]))
+			goto del_rules;
+	}
+
 	return 0;
 
 del_rules:
@@ -733,13 +786,23 @@ del_rules:
 }
 
 #define MLX5E_TTC_NUM_GROUPS	3
-#define MLX5E_TTC_GROUP1_SIZE	BIT(3)
-#define MLX5E_TTC_GROUP2_SIZE	BIT(1)
-#define MLX5E_TTC_GROUP3_SIZE	BIT(0)
+#define MLX5E_TTC_GROUP1_SIZE	(BIT(3) + MLX5E_NUM_TUNNEL_TT)
+#define MLX5E_TTC_GROUP2_SIZE	 BIT(1)
+#define MLX5E_TTC_GROUP3_SIZE	 BIT(0)
 #define MLX5E_TTC_TABLE_SIZE	(MLX5E_TTC_GROUP1_SIZE +\
 				 MLX5E_TTC_GROUP2_SIZE +\
 				 MLX5E_TTC_GROUP3_SIZE)
-static int mlx5e_create_ttc_table_groups(struct mlx5e_ttc_table *ttc)
+
+#define MLX5E_INNER_TTC_NUM_GROUPS	3
+#define MLX5E_INNER_TTC_GROUP1_SIZE	BIT(3)
+#define MLX5E_INNER_TTC_GROUP2_SIZE	BIT(1)
+#define MLX5E_INNER_TTC_GROUP3_SIZE	BIT(0)
+#define MLX5E_INNER_TTC_TABLE_SIZE	(MLX5E_INNER_TTC_GROUP1_SIZE +\
+					 MLX5E_INNER_TTC_GROUP2_SIZE +\
+					 MLX5E_INNER_TTC_GROUP3_SIZE)
+
+static int mlx5e_create_ttc_table_groups(struct mlx5e_ttc_table *ttc,
+					 bool use_ipv)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
 	struct mlx5e_flow_table *ft = &ttc->ft;
@@ -761,7 +824,10 @@ static int mlx5e_create_ttc_table_groups(struct mlx5e_ttc_table *ttc)
 	/* L4 Group */
 	mc = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria);
 	MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ip_protocol);
-	MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ethertype);
+	if (use_ipv)
+		MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ip_version);
+	else
+		MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ethertype);
 	MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS);
 	MLX5_SET_CFG(in, start_flow_index, ix);
 	ix += MLX5E_TTC_GROUP1_SIZE;
@@ -802,6 +868,190 @@ err:
 	return err;
 }
 
+static struct mlx5_flow_handle *
+mlx5e_generate_inner_ttc_rule(struct mlx5e_priv *priv,
+			      struct mlx5_flow_table *ft,
+			      struct mlx5_flow_destination *dest,
+			      u16 etype, u8 proto)
+{
+	MLX5_DECLARE_FLOW_ACT(flow_act);
+	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_spec *spec;
+	int err = 0;
+	u8 ipv;
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec)
+		return ERR_PTR(-ENOMEM);
+
+	ipv = mlx5e_etype_to_ipv(etype);
+	if (etype && ipv) {
+		spec->match_criteria_enable = MLX5_MATCH_INNER_HEADERS;
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, inner_headers.ip_version);
+		MLX5_SET(fte_match_param, spec->match_value, inner_headers.ip_version, ipv);
+	}
+
+	if (proto) {
+		spec->match_criteria_enable = MLX5_MATCH_INNER_HEADERS;
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, inner_headers.ip_protocol);
+		MLX5_SET(fte_match_param, spec->match_value, inner_headers.ip_protocol, proto);
+	}
+
+	rule = mlx5_add_flow_rules(ft, spec, &flow_act, dest, 1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		netdev_err(priv->netdev, "%s: add rule failed\n", __func__);
+	}
+
+	kvfree(spec);
+	return err ? ERR_PTR(err) : rule;
+}
+
+static int mlx5e_generate_inner_ttc_table_rules(struct mlx5e_priv *priv)
+{
+	struct mlx5_flow_destination dest;
+	struct mlx5_flow_handle **rules;
+	struct mlx5e_ttc_table *ttc;
+	struct mlx5_flow_table *ft;
+	int err;
+	int tt;
+
+	ttc =  &priv->fs.inner_ttc;
+	ft = ttc->ft.t;
+	rules = ttc->rules;
+
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_TIR;
+	for (tt = 0; tt < MLX5E_NUM_TT; tt++) {
+		if (tt == MLX5E_TT_ANY)
+			dest.tir_num = priv->direct_tir[0].tirn;
+		else
+			dest.tir_num = priv->inner_indir_tir[tt].tirn;
+
+		rules[tt] = mlx5e_generate_inner_ttc_rule(priv, ft, &dest,
+							  ttc_rules[tt].etype,
+							  ttc_rules[tt].proto);
+		if (IS_ERR(rules[tt]))
+			goto del_rules;
+	}
+
+	return 0;
+
+del_rules:
+	err = PTR_ERR(rules[tt]);
+	rules[tt] = NULL;
+	mlx5e_cleanup_ttc_rules(ttc);
+	return err;
+}
+
+static int mlx5e_create_inner_ttc_table_groups(struct mlx5e_ttc_table *ttc)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5e_flow_table *ft = &ttc->ft;
+	int ix = 0;
+	u32 *in;
+	int err;
+	u8 *mc;
+
+	ft->g = kcalloc(MLX5E_INNER_TTC_NUM_GROUPS, sizeof(*ft->g), GFP_KERNEL);
+	if (!ft->g)
+		return -ENOMEM;
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in) {
+		kfree(ft->g);
+		return -ENOMEM;
+	}
+
+	/* L4 Group */
+	mc = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria);
+	MLX5_SET_TO_ONES(fte_match_param, mc, inner_headers.ip_protocol);
+	MLX5_SET_TO_ONES(fte_match_param, mc, inner_headers.ip_version);
+	MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_INNER_HEADERS);
+	MLX5_SET_CFG(in, start_flow_index, ix);
+	ix += MLX5E_INNER_TTC_GROUP1_SIZE;
+	MLX5_SET_CFG(in, end_flow_index, ix - 1);
+	ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in);
+	if (IS_ERR(ft->g[ft->num_groups]))
+		goto err;
+	ft->num_groups++;
+
+	/* L3 Group */
+	MLX5_SET(fte_match_param, mc, inner_headers.ip_protocol, 0);
+	MLX5_SET_CFG(in, start_flow_index, ix);
+	ix += MLX5E_INNER_TTC_GROUP2_SIZE;
+	MLX5_SET_CFG(in, end_flow_index, ix - 1);
+	ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in);
+	if (IS_ERR(ft->g[ft->num_groups]))
+		goto err;
+	ft->num_groups++;
+
+	/* Any Group */
+	memset(in, 0, inlen);
+	MLX5_SET_CFG(in, start_flow_index, ix);
+	ix += MLX5E_INNER_TTC_GROUP3_SIZE;
+	MLX5_SET_CFG(in, end_flow_index, ix - 1);
+	ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in);
+	if (IS_ERR(ft->g[ft->num_groups]))
+		goto err;
+	ft->num_groups++;
+
+	kvfree(in);
+	return 0;
+
+err:
+	err = PTR_ERR(ft->g[ft->num_groups]);
+	ft->g[ft->num_groups] = NULL;
+	kvfree(in);
+
+	return err;
+}
+
+static int mlx5e_create_inner_ttc_table(struct mlx5e_priv *priv)
+{
+	struct mlx5e_ttc_table *ttc = &priv->fs.inner_ttc;
+	struct mlx5_flow_table_attr ft_attr = {};
+	struct mlx5e_flow_table *ft = &ttc->ft;
+	int err;
+
+	if (!mlx5e_tunnel_inner_ft_supported(priv->mdev))
+		return 0;
+
+	ft_attr.max_fte = MLX5E_INNER_TTC_TABLE_SIZE;
+	ft_attr.level   = MLX5E_INNER_TTC_FT_LEVEL;
+	ft_attr.prio    = MLX5E_NIC_PRIO;
+
+	ft->t = mlx5_create_flow_table(priv->fs.ns, &ft_attr);
+	if (IS_ERR(ft->t)) {
+		err = PTR_ERR(ft->t);
+		ft->t = NULL;
+		return err;
+	}
+
+	err = mlx5e_create_inner_ttc_table_groups(ttc);
+	if (err)
+		goto err;
+
+	err = mlx5e_generate_inner_ttc_table_rules(priv);
+	if (err)
+		goto err;
+
+	return 0;
+
+err:
+	mlx5e_destroy_flow_table(ft);
+	return err;
+}
+
+static void mlx5e_destroy_inner_ttc_table(struct mlx5e_priv *priv)
+{
+	struct mlx5e_ttc_table *ttc = &priv->fs.inner_ttc;
+
+	if (!mlx5e_tunnel_inner_ft_supported(priv->mdev))
+		return;
+
+	mlx5e_cleanup_ttc_rules(ttc);
+	mlx5e_destroy_flow_table(&ttc->ft);
+}
+
 void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv)
 {
 	struct mlx5e_ttc_table *ttc = &priv->fs.ttc;
@@ -812,6 +1062,7 @@ void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv)
 
 int mlx5e_create_ttc_table(struct mlx5e_priv *priv)
 {
+	bool match_ipv_outer = MLX5_CAP_FLOWTABLE_NIC_RX(priv->mdev, ft_field_support.outer_ip_version);
 	struct mlx5e_ttc_table *ttc = &priv->fs.ttc;
 	struct mlx5_flow_table_attr ft_attr = {};
 	struct mlx5e_flow_table *ft = &ttc->ft;
@@ -828,7 +1079,7 @@ int mlx5e_create_ttc_table(struct mlx5e_priv *priv)
 		return err;
 	}
 
-	err = mlx5e_create_ttc_table_groups(ttc);
+	err = mlx5e_create_ttc_table_groups(ttc, match_ipv_outer);
 	if (err)
 		goto err;
 
@@ -1154,11 +1405,18 @@ int mlx5e_create_flow_steering(struct mlx5e_priv *priv)
 		priv->netdev->hw_features &= ~NETIF_F_NTUPLE;
 	}
 
+	err = mlx5e_create_inner_ttc_table(priv);
+	if (err) {
+		netdev_err(priv->netdev, "Failed to create inner ttc table, err=%d\n",
+			   err);
+		goto err_destroy_arfs_tables;
+	}
+
 	err = mlx5e_create_ttc_table(priv);
 	if (err) {
 		netdev_err(priv->netdev, "Failed to create ttc table, err=%d\n",
 			   err);
-		goto err_destroy_arfs_tables;
+		goto err_destroy_inner_ttc_table;
 	}
 
 	err = mlx5e_create_l2_table(priv);
@@ -1183,6 +1441,8 @@ err_destroy_l2_table:
 	mlx5e_destroy_l2_table(priv);
 err_destroy_ttc_table:
 	mlx5e_destroy_ttc_table(priv);
+err_destroy_inner_ttc_table:
+	mlx5e_destroy_inner_ttc_table(priv);
 err_destroy_arfs_tables:
 	mlx5e_arfs_destroy_tables(priv);
 
@@ -1194,6 +1454,7 @@ void mlx5e_destroy_flow_steering(struct mlx5e_priv *priv)
 	mlx5e_destroy_vlan_table(priv);
 	mlx5e_destroy_l2_table(priv);
 	mlx5e_destroy_ttc_table(priv);
+	mlx5e_destroy_inner_ttc_table(priv);
 	mlx5e_arfs_destroy_tables(priv);
 	mlx5e_ethtool_cleanup_steering(priv);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index fdc2b92f020b..111c7523d448 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2349,9 +2349,10 @@ static void mlx5e_build_tir_ctx_lro(struct mlx5e_params *params, void *tirc)
 
 void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_params *params,
 				    enum mlx5e_traffic_types tt,
-				    void *tirc)
+				    void *tirc, bool inner)
 {
-	void *hfso = MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_outer);
+	void *hfso = inner ? MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_inner) :
+			     MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_outer);
 
 #define MLX5_HASH_IP            (MLX5_HASH_FIELD_SEL_SRC_IP   |\
 				 MLX5_HASH_FIELD_SEL_DST_IP)
@@ -2500,6 +2501,21 @@ free_in:
 	return err;
 }
 
+static void mlx5e_build_inner_indir_tir_ctx(struct mlx5e_priv *priv,
+					    enum mlx5e_traffic_types tt,
+					    u32 *tirc)
+{
+	MLX5_SET(tirc, tirc, transport_domain, priv->mdev->mlx5e_res.td.tdn);
+
+	mlx5e_build_tir_ctx_lro(&priv->channels.params, tirc);
+
+	MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT);
+	MLX5_SET(tirc, tirc, indirect_table, priv->indir_rqt.rqtn);
+	MLX5_SET(tirc, tirc, tunneled_offload_en, 0x1);
+
+	mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc, true);
+}
+
 static int mlx5e_set_mtu(struct mlx5e_priv *priv, u16 mtu)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
@@ -2865,7 +2881,7 @@ static void mlx5e_build_indir_tir_ctx(struct mlx5e_priv *priv,
 
 	MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT);
 	MLX5_SET(tirc, tirc, indirect_table, priv->indir_rqt.rqtn);
-	mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc);
+	mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc, false);
 }
 
 static void mlx5e_build_direct_tir_ctx(struct mlx5e_priv *priv, u32 rqtn, u32 *tirc)
@@ -2884,6 +2900,7 @@ int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv)
 	struct mlx5e_tir *tir;
 	void *tirc;
 	int inlen;
+	int i = 0;
 	int err;
 	u32 *in;
 	int tt;
@@ -2899,16 +2916,36 @@ int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv)
 		tirc = MLX5_ADDR_OF(create_tir_in, in, ctx);
 		mlx5e_build_indir_tir_ctx(priv, tt, tirc);
 		err = mlx5e_create_tir(priv->mdev, tir, in, inlen);
-		if (err)
-			goto err_destroy_tirs;
+		if (err) {
+			mlx5_core_warn(priv->mdev, "create indirect tirs failed, %d\n", err);
+			goto err_destroy_inner_tirs;
+		}
 	}
 
+	if (!mlx5e_tunnel_inner_ft_supported(priv->mdev))
+		goto out;
+
+	for (i = 0; i < MLX5E_NUM_INDIR_TIRS; i++) {
+		memset(in, 0, inlen);
+		tir = &priv->inner_indir_tir[i];
+		tirc = MLX5_ADDR_OF(create_tir_in, in, ctx);
+		mlx5e_build_inner_indir_tir_ctx(priv, i, tirc);
+		err = mlx5e_create_tir(priv->mdev, tir, in, inlen);
+		if (err) {
+			mlx5_core_warn(priv->mdev, "create inner indirect tirs failed, %d\n", err);
+			goto err_destroy_inner_tirs;
+		}
+	}
+
+out:
 	kvfree(in);
 
 	return 0;
 
-err_destroy_tirs:
-	mlx5_core_warn(priv->mdev, "create indirect tirs failed, %d\n", err);
+err_destroy_inner_tirs:
+	for (i--; i >= 0; i--)
+		mlx5e_destroy_tir(priv->mdev, &priv->inner_indir_tir[i]);
+
 	for (tt--; tt >= 0; tt--)
 		mlx5e_destroy_tir(priv->mdev, &priv->indir_tir[tt]);
 
@@ -2962,6 +2999,12 @@ void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv)
 
 	for (i = 0; i < MLX5E_NUM_INDIR_TIRS; i++)
 		mlx5e_destroy_tir(priv->mdev, &priv->indir_tir[i]);
+
+	if (!mlx5e_tunnel_inner_ft_supported(priv->mdev))
+		return;
+
+	for (i = 0; i < MLX5E_NUM_INDIR_TIRS; i++)
+		mlx5e_destroy_tir(priv->mdev, &priv->inner_indir_tir[i]);
 }
 
 void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv)
@@ -3499,13 +3542,13 @@ static void mlx5e_del_vxlan_port(struct net_device *netdev,
 	mlx5e_vxlan_queue_work(priv, ti->sa_family, be16_to_cpu(ti->port), 0);
 }
 
-static netdev_features_t mlx5e_vxlan_features_check(struct mlx5e_priv *priv,
-						    struct sk_buff *skb,
-						    netdev_features_t features)
+static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv,
+						     struct sk_buff *skb,
+						     netdev_features_t features)
 {
 	struct udphdr *udph;
-	u16 proto;
-	u16 port = 0;
+	u8 proto;
+	u16 port;
 
 	switch (vlan_get_protocol(skb)) {
 	case htons(ETH_P_IP):
@@ -3518,14 +3561,17 @@ static netdev_features_t mlx5e_vxlan_features_check(struct mlx5e_priv *priv,
 		goto out;
 	}
 
-	if (proto == IPPROTO_UDP) {
+	switch (proto) {
+	case IPPROTO_GRE:
+		return features;
+	case IPPROTO_UDP:
 		udph = udp_hdr(skb);
 		port = be16_to_cpu(udph->dest);
-	}
 
-	/* Verify if UDP port is being offloaded by HW */
-	if (port && mlx5e_vxlan_lookup_port(priv, port))
-		return features;
+		/* Verify if UDP port is being offloaded by HW */
+		if (mlx5e_vxlan_lookup_port(priv, port))
+			return features;
+	}
 
 out:
 	/* Disable CSUM and GSO if the udp dport is not offloaded by HW */
@@ -3549,7 +3595,7 @@ static netdev_features_t mlx5e_features_check(struct sk_buff *skb,
 	/* Validate if the tunneled packet is being offloaded by HW */
 	if (skb->encapsulation &&
 	    (features & NETIF_F_CSUM_MASK || features & NETIF_F_GSO_MASK))
-		return mlx5e_vxlan_features_check(priv, skb, features);
+		return mlx5e_tunnel_features_check(priv, skb, features);
 
 	return features;
 }
@@ -4014,20 +4060,32 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	netdev->hw_features      |= NETIF_F_HW_VLAN_CTAG_RX;
 	netdev->hw_features      |= NETIF_F_HW_VLAN_CTAG_FILTER;
 
-	if (mlx5e_vxlan_allowed(mdev)) {
-		netdev->hw_features     |= NETIF_F_GSO_UDP_TUNNEL |
-					   NETIF_F_GSO_UDP_TUNNEL_CSUM |
-					   NETIF_F_GSO_PARTIAL;
+	if (mlx5e_vxlan_allowed(mdev) || MLX5_CAP_ETH(mdev, tunnel_stateless_gre)) {
+		netdev->hw_features     |= NETIF_F_GSO_PARTIAL;
 		netdev->hw_enc_features |= NETIF_F_IP_CSUM;
 		netdev->hw_enc_features |= NETIF_F_IPV6_CSUM;
 		netdev->hw_enc_features |= NETIF_F_TSO;
 		netdev->hw_enc_features |= NETIF_F_TSO6;
-		netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL;
-		netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM |
-					   NETIF_F_GSO_PARTIAL;
+		netdev->hw_enc_features |= NETIF_F_GSO_PARTIAL;
+	}
+
+	if (mlx5e_vxlan_allowed(mdev)) {
+		netdev->hw_features     |= NETIF_F_GSO_UDP_TUNNEL |
+					   NETIF_F_GSO_UDP_TUNNEL_CSUM;
+		netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL |
+					   NETIF_F_GSO_UDP_TUNNEL_CSUM;
 		netdev->gso_partial_features = NETIF_F_GSO_UDP_TUNNEL_CSUM;
 	}
 
+	if (MLX5_CAP_ETH(mdev, tunnel_stateless_gre)) {
+		netdev->hw_features     |= NETIF_F_GSO_GRE |
+					   NETIF_F_GSO_GRE_CSUM;
+		netdev->hw_enc_features |= NETIF_F_GSO_GRE |
+					   NETIF_F_GSO_GRE_CSUM;
+		netdev->gso_partial_features |= NETIF_F_GSO_GRE |
+						NETIF_F_GSO_GRE_CSUM;
+	}
+
 	mlx5_query_port_fcs(mdev, &fcs_supported, &fcs_enabled);
 
 	if (fcs_supported)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index d731d57a996a..5a7bea688ec8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -83,8 +83,8 @@
 #define ETHTOOL_PRIO_NUM_LEVELS 1
 #define ETHTOOL_NUM_PRIOS 11
 #define ETHTOOL_MIN_LEVEL (KERNEL_MIN_LEVEL + ETHTOOL_NUM_PRIOS)
-/* Vlan, mac, ttc, aRFS */
-#define KERNEL_NIC_PRIO_NUM_LEVELS 4
+/* Vlan, mac, ttc, inner ttc, aRFS */
+#define KERNEL_NIC_PRIO_NUM_LEVELS 5
 #define KERNEL_NIC_NUM_PRIOS 1
 /* One more level for tc */
 #define KERNEL_MIN_LEVEL (KERNEL_NIC_PRIO_NUM_LEVELS + 1)