Received-SPF: Pass (protection.outlook.com: domain of nvidia.com designates
 216.228.117.161 as permitted sender) receiver=protection.outlook.com;
 client-ip=216.228.117.161; helo=mail.nvidia.com; pr=C
From:   Gavin Li <gavinl@nvidia.com>
To:     <davem@davemloft.net>, <edumazet@google.com>, <kuba@kernel.org>,
        <pabeni@redhat.com>, <roopa@nvidia.com>,
        <eng.alaamohamedsoliman.am@gmail.com>, <bigeasy@linutronix.de>
CC:     <netdev@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
        <gavi@nvidia.com>, <roid@nvidia.com>, <maord@nvidia.com>,
        <saeedm@nvidia.com>, Simon Horman <simon.horman@corigine.com>
Subject: [PATCH RESEND net-next v4 4/4] net/mlx5e: TC, Add support for VxLAN GBP encap/decap flows offload
Date:   Mon, 6 Mar 2023 05:03:02 +0200
Message-ID: <20230306030302.224414-5-gavinl@nvidia.com>
In-Reply-To: <20230306030302.224414-1-gavinl@nvidia.com>
References: <20230306030302.224414-1-gavinl@nvidia.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 06 Mar 2023 03:04:04.3588
 (UTC)
X-MS-Exchange-CrossTenant-Network-Message-Id: 56ba1979-6387-48c3-6828-08db1def71bc
X-MS-Exchange-CrossTenant-Id: 43083d15-7273-40c1-b7db-39efd9ccc17a
X-MS-Exchange-CrossTenant-OriginalAttributedTenantConnectingIp: TenantId=43083d15-7273-40c1-b7db-39efd9ccc17a;Ip=[216.228.117.161];Helo=[mail.nvidia.com]
X-MS-Exchange-CrossTenant-AuthSource: BN8NAM11FT092.eop-nam11.prod.protection.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Anonymous
X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem
X-MS-Exchange-Transport-CrossTenantHeadersStamped: MN6PR12MB8489
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

Add HW offloading support for TC flows with VxLAN GBP encap/decap.

Example of encap rule:
tc filter add dev eth0 protocol ip ingress flower \
    action tunnel_key set id 42 vxlan_opts 512 \
    action mirred egress redirect dev vxlan1

Example of decap rule:
tc filter add dev vxlan1 protocol ip ingress flower \
    enc_key_id 42 enc_dst_port 4789 vxlan_opts 1024 \
    action tunnel_key unset action mirred egress redirect dev eth0

Signed-off-by: Gavin Li <gavinl@nvidia.com>
Reviewed-by: Gavi Teitz <gavi@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Reviewed-by: Maor Dickman <maord@nvidia.com>
Acked-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
---
 .../mellanox/mlx5/core/en/tc_tun_vxlan.c      | 76 ++++++++++++++++++-
 include/linux/mlx5/device.h                   |  6 ++
 include/linux/mlx5/mlx5_ifc.h                 | 13 +++-
 3 files changed, 91 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
index 1f62c702b625..8ee5d9e67e0a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
 /* Copyright (c) 2018 Mellanox Technologies. */
 
+#include <net/ip_tunnels.h>
 #include <net/vxlan.h>
 #include "lib/vxlan.h"
 #include "en/tc_tun.h"
@@ -86,9 +87,11 @@ static int mlx5e_gen_ip_tunnel_header_vxlan(char buf[],
 	const struct ip_tunnel_key *tun_key = &e->tun_info->key;
 	__be32 tun_id = tunnel_id_to_key32(tun_key->tun_id);
 	struct udphdr *udp = (struct udphdr *)(buf);
+	struct vxlan_metadata *md;
 	struct vxlanhdr *vxh;
 
-	if (tun_key->tun_flags & TUNNEL_VXLAN_OPT)
+	if ((tun_key->tun_flags & TUNNEL_VXLAN_OPT) &&
+	    e->tun_info->options_len != sizeof(*md))
 		return -EOPNOTSUPP;
 	vxh = (struct vxlanhdr *)((char *)udp + sizeof(struct udphdr));
 	*ip_proto = IPPROTO_UDP;
@@ -96,6 +99,61 @@ static int mlx5e_gen_ip_tunnel_header_vxlan(char buf[],
 	udp->dest = tun_key->tp_dst;
 	vxh->vx_flags = VXLAN_HF_VNI;
 	vxh->vx_vni = vxlan_vni_field(tun_id);
+	if (tun_key->tun_flags & TUNNEL_VXLAN_OPT) {
+		md = ip_tunnel_info_opts((struct ip_tunnel_info *)e->tun_info);
+		vxlan_build_gbp_hdr(vxh, md);
+	}
+
+	return 0;
+}
+
+static int mlx5e_tc_tun_parse_vxlan_gbp_option(struct mlx5e_priv *priv,
+					       struct mlx5_flow_spec *spec,
+					       struct flow_cls_offload *f)
+{
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
+	struct netlink_ext_ack *extack = f->common.extack;
+	struct flow_match_enc_opts enc_opts;
+	void *misc5_c, *misc5_v;
+	u32 *gbp, *gbp_mask;
+
+	flow_rule_match_enc_opts(rule, &enc_opts);
+
+	if (memchr_inv(&enc_opts.mask->data, 0, sizeof(enc_opts.mask->data)) &&
+	    !MLX5_CAP_ESW_FT_FIELD_SUPPORT_2(priv->mdev, tunnel_header_0_1)) {
+		NL_SET_ERR_MSG_MOD(extack, "Matching on VxLAN GBP is not supported");
+		netdev_warn(priv->netdev, "Matching on VxLAN GBP is not supported\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (enc_opts.key->dst_opt_type != TUNNEL_VXLAN_OPT) {
+		NL_SET_ERR_MSG_MOD(extack, "Wrong VxLAN option type: not GBP");
+		netdev_warn(priv->netdev, "Wrong VxLAN option type: not GBP\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (enc_opts.key->len != sizeof(*gbp) ||
+	    enc_opts.mask->len != sizeof(*gbp_mask)) {
+		NL_SET_ERR_MSG_MOD(extack, "VxLAN GBP option/mask len is not 32 bits");
+		netdev_warn(priv->netdev, "VxLAN GBP option/mask len is not 32 bits\n");
+		return -EINVAL;
+	}
+
+	gbp = (u32 *)&enc_opts.key->data[0];
+	gbp_mask = (u32 *)&enc_opts.mask->data[0];
+
+	if (*gbp_mask & ~VXLAN_GBP_MASK) {
+		NL_SET_ERR_MSG_FMT_MOD(extack, "Wrong VxLAN GBP mask(0x%08X)\n", *gbp_mask);
+		netdev_warn(priv->netdev, "Wrong VxLAN GBP mask(0x%08X)\n", *gbp_mask);
+		return -EINVAL;
+	}
+
+	misc5_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters_5);
+	misc5_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters_5);
+	MLX5_SET(fte_match_set_misc5, misc5_c, tunnel_header_0, *gbp_mask);
+	MLX5_SET(fte_match_set_misc5, misc5_v, tunnel_header_0, *gbp);
+
+	spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_5;
 
 	return 0;
 }
@@ -122,6 +180,14 @@ static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv,
 	if (!enc_keyid.mask->keyid)
 		return 0;
 
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_OPTS)) {
+		int err;
+
+		err = mlx5e_tc_tun_parse_vxlan_gbp_option(priv, spec, f);
+		if (err)
+			return err;
+	}
+
 	/* match on VNI is required */
 
 	if (!MLX5_CAP_ESW_FLOWTABLE_FDB(priv->mdev,
@@ -143,6 +209,12 @@ static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv,
 	return 0;
 }
 
+static bool mlx5e_tc_tun_encap_info_equal_vxlan(struct mlx5e_encap_key *a,
+						struct mlx5e_encap_key *b)
+{
+	return mlx5e_tc_tun_encap_info_equal_options(a, b, TUNNEL_VXLAN_OPT);
+}
+
 static int mlx5e_tc_tun_get_remote_ifindex(struct net_device *mirred_dev)
 {
 	const struct vxlan_dev *vxlan = netdev_priv(mirred_dev);
@@ -160,6 +232,6 @@ struct mlx5e_tc_tunnel vxlan_tunnel = {
 	.generate_ip_tun_hdr  = mlx5e_gen_ip_tunnel_header_vxlan,
 	.parse_udp_ports      = mlx5e_tc_tun_parse_udp_ports_vxlan,
 	.parse_tunnel         = mlx5e_tc_tun_parse_vxlan,
-	.encap_info_equal     = mlx5e_tc_tun_encap_info_equal_generic,
+	.encap_info_equal     = mlx5e_tc_tun_encap_info_equal_vxlan,
 	.get_remote_ifindex   = mlx5e_tc_tun_get_remote_ifindex,
 };
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 71b06ebad402..af4dd536a52c 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -1357,6 +1357,12 @@ enum mlx5_qcam_feature_groups {
 #define MLX5_CAP_ESW_INGRESS_ACL_MAX(mdev, cap) \
 	MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, flow_table_properties_esw_acl_ingress.cap)
 
+#define MLX5_CAP_ESW_FT_FIELD_SUPPORT_2(mdev, cap) \
+	MLX5_CAP_ESW_FLOWTABLE(mdev, ft_field_support_2_esw_fdb.cap)
+
+#define MLX5_CAP_ESW_FT_FIELD_SUPPORT_2_MAX(mdev, cap) \
+	MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, ft_field_support_2_esw_fdb.cap)
+
 #define MLX5_CAP_ESW(mdev, cap) \
 	MLX5_GET(e_switch_cap, \
 		 mdev->caps.hca[MLX5_CAP_ESWITCH]->cur, cap)
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 5ad5126615a1..163cc0638c37 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -404,10 +404,13 @@ struct mlx5_ifc_flow_table_fields_supported_bits {
 	u8         metadata_reg_c_0[0x1];
 };
 
+/* Table 2170 - Flow Table Fields Supported 2 Format */
 struct mlx5_ifc_flow_table_fields_supported_2_bits {
 	u8         reserved_at_0[0xe];
 	u8         bth_opcode[0x1];
-	u8         reserved_at_f[0x11];
+	u8         reserved_at_f[0x1];
+	u8         tunnel_header_0_1[0x1];
+	u8         reserved_at_11[0xf];
 
 	u8         reserved_at_20[0x60];
 };
@@ -895,7 +898,13 @@ struct mlx5_ifc_flow_table_eswitch_cap_bits {
 
 	struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_esw_acl_egress;
 
-	u8      reserved_at_800[0x1000];
+	u8      reserved_at_800[0xC00];
+
+	struct mlx5_ifc_flow_table_fields_supported_2_bits ft_field_support_2_esw_fdb;
+
+	struct mlx5_ifc_flow_table_fields_supported_2_bits ft_field_bitmask_support_2_esw_fdb;
+
+	u8      reserved_at_1500[0x300];
 
 	u8      sw_steering_fdb_action_drop_icm_address_rx[0x40];
 
-- 
2.31.1