Merge branch 'net-mlx5e-add-gbp-vxlan-hw-offload-support'

Gavin Li says:

====================
net/mlx5e: Add GBP VxLAN HW offload support

Patch-1: Remove unused argument from functions.
Patch-2: Expose helper function vxlan_build_gbp_hdr.
Patch-3: Add helper function for encap_info_equal for tunnels with options.
Patch-4: Preserving the const-ness of the pointer in ip_tunnel_info_opts.
Patch-5: Add HW offloading support for TC flows with VxLAN GBP encap/decap
        in mlx ethernet driver.
====================

Link: https://lore.kernel.org/r/20230316070758.83512-1-gavinl@nvidia.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h

@@ -115,6 +115,9 @@ int mlx5e_tc_tun_parse_udp_ports(struct mlx5e_priv *priv,
 bool mlx5e_tc_tun_encap_info_equal_generic(struct mlx5e_encap_key *a,
 					   struct mlx5e_encap_key *b);
 
+bool mlx5e_tc_tun_encap_info_equal_options(struct mlx5e_encap_key *a,
+					   struct mlx5e_encap_key *b,
+					   __be16 tun_flags);
 #endif /* CONFIG_MLX5_ESWITCH */
 
 #endif //__MLX5_EN_TC_TUNNEL_H__

drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c

@@ -3,6 +3,7 @@
 
 #include <net/fib_notifier.h>
 #include <net/nexthop.h>
+#include <net/ip_tunnels.h>
 #include "tc_tun_encap.h"
 #include "en_tc.h"
 #include "tc_tun.h"
@@ -571,6 +572,37 @@ bool mlx5e_tc_tun_encap_info_equal_generic(struct mlx5e_encap_key *a,
 		a->tc_tunnel->tunnel_type == b->tc_tunnel->tunnel_type;
 }
 
+bool mlx5e_tc_tun_encap_info_equal_options(struct mlx5e_encap_key *a,
+					   struct mlx5e_encap_key *b,
+					   __be16 tun_flags)
+{
+	struct ip_tunnel_info *a_info;
+	struct ip_tunnel_info *b_info;
+	bool a_has_opts, b_has_opts;
+
+	if (!mlx5e_tc_tun_encap_info_equal_generic(a, b))
+		return false;
+
+	a_has_opts = !!(a->ip_tun_key->tun_flags & tun_flags);
+	b_has_opts = !!(b->ip_tun_key->tun_flags & tun_flags);
+
+	/* keys are equal when both don't have any options attached */
+	if (!a_has_opts && !b_has_opts)
+		return true;
+
+	if (a_has_opts != b_has_opts)
+		return false;
+
+	/* options stored in memory next to ip_tunnel_info struct */
+	a_info = container_of(a->ip_tun_key, struct ip_tunnel_info, key);
+	b_info = container_of(b->ip_tun_key, struct ip_tunnel_info, key);
+
+	return a_info->options_len == b_info->options_len &&
+	       !memcmp(ip_tunnel_info_opts(a_info),
+		       ip_tunnel_info_opts(b_info),
+		       a_info->options_len);
+}
+
 static int cmp_decap_info(struct mlx5e_decap_key *a,
 			  struct mlx5e_decap_key *b)
 {

drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c

@@ -337,29 +337,7 @@ static int mlx5e_tc_tun_parse_geneve(struct mlx5e_priv *priv,
 static bool mlx5e_tc_tun_encap_info_equal_geneve(struct mlx5e_encap_key *a,
 						 struct mlx5e_encap_key *b)
 {
-	struct ip_tunnel_info *a_info;
-	struct ip_tunnel_info *b_info;
-	bool a_has_opts, b_has_opts;
-
-	if (!mlx5e_tc_tun_encap_info_equal_generic(a, b))
-		return false;
-
-	a_has_opts = !!(a->ip_tun_key->tun_flags & TUNNEL_GENEVE_OPT);
-	b_has_opts = !!(b->ip_tun_key->tun_flags & TUNNEL_GENEVE_OPT);
-
-	/* keys are equal when both don't have any options attached */
-	if (!a_has_opts && !b_has_opts)
-		return true;
-
-	if (a_has_opts != b_has_opts)
-		return false;
-
-	/* geneve options stored in memory next to ip_tunnel_info struct */
-	a_info = container_of(a->ip_tun_key, struct ip_tunnel_info, key);
-	b_info = container_of(b->ip_tun_key, struct ip_tunnel_info, key);
-
-	return a_info->options_len == b_info->options_len &&
-		memcmp(a_info + 1, b_info + 1, a_info->options_len) == 0;
+	return mlx5e_tc_tun_encap_info_equal_options(a, b, TUNNEL_GENEVE_OPT);
 }
 
 struct mlx5e_tc_tunnel geneve_tunnel = {

drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c

 // 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);
+	const 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 +99,57 @@ 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(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");
+		return -EOPNOTSUPP;
+	}
+
+	if (enc_opts.key->dst_opt_type != TUNNEL_VXLAN_OPT) {
+		NL_SET_ERR_MSG_MOD(extack, "Wrong VxLAN option type: not GBP");
+		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");
+		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);
+		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 +176,14 @@ 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 +205,12 @@ 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 +228,6 @@ 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,
 };

drivers/net/vxlan/vxlan_core.c

@@ -2093,28 +2093,7 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb)
 	return false;
 }
 
-static void vxlan_build_gbp_hdr(struct vxlanhdr *vxh, u32 vxflags,
-				struct vxlan_metadata *md)
-{
-	struct vxlanhdr_gbp *gbp;
-
-	if (!md->gbp)
-		return;
-
-	gbp = (struct vxlanhdr_gbp *)vxh;
-	vxh->vx_flags |= VXLAN_HF_GBP;
-
-	if (md->gbp & VXLAN_GBP_DONT_LEARN)
-		gbp->dont_learn = 1;
-
-	if (md->gbp & VXLAN_GBP_POLICY_APPLIED)
-		gbp->policy_applied = 1;
-
-	gbp->policy_id = htons(md->gbp & VXLAN_GBP_ID_MASK);
-}
-
-static int vxlan_build_gpe_hdr(struct vxlanhdr *vxh, u32 vxflags,
-			       __be16 protocol)
+static int vxlan_build_gpe_hdr(struct vxlanhdr *vxh, __be16 protocol)
 {
 	struct vxlanhdr_gpe *gpe = (struct vxlanhdr_gpe *)vxh;
 
@@ -2177,9 +2156,9 @@ static int vxlan_build_skb(struct sk_buff *skb, struct dst_entry *dst,
 	}
 
 	if (vxflags & VXLAN_F_GBP)
-		vxlan_build_gbp_hdr(vxh, vxflags, md);
+		vxlan_build_gbp_hdr(vxh, md);
 	if (vxflags & VXLAN_F_GPE) {
-		err = vxlan_build_gpe_hdr(vxh, vxflags, skb->protocol);
+		err = vxlan_build_gpe_hdr(vxh, skb->protocol);
 		if (err < 0)
 			return err;
 		inner_protocol = skb->protocol;

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)

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];
 

include/net/ip_tunnels.h

@@ -67,6 +67,12 @@ struct ip_tunnel_key {
 	GENMASK((sizeof_field(struct ip_tunnel_info,		\
 			      options_len) * BITS_PER_BYTE) - 1, 0)
 
+#define ip_tunnel_info_opts(info)				\
+	_Generic(info,						\
+		 const struct ip_tunnel_info * : ((const void *)((info) + 1)),\
+		 struct ip_tunnel_info * : ((void *)((info) + 1))\
+	)
+
 struct ip_tunnel_info {
 	struct ip_tunnel_key	key;
 #ifdef CONFIG_DST_CACHE
@@ -485,11 +491,6 @@ static inline void iptunnel_xmit_stats(struct net_device *dev, int pkt_len)
 	}
 }
 
-static inline void *ip_tunnel_info_opts(struct ip_tunnel_info *info)
-{
-	return info + 1;
-}
-
 static inline void ip_tunnel_info_opts_get(void *to,
 					   const struct ip_tunnel_info *info)
 {

include/net/vxlan.h

@@ -572,4 +572,23 @@ static inline bool vxlan_fdb_nh_path_select(struct nexthop *nh,
 	return true;
 }
 
+static inline void vxlan_build_gbp_hdr(struct vxlanhdr *vxh, const struct vxlan_metadata *md)
+{
+	struct vxlanhdr_gbp *gbp;
+
+	if (!md->gbp)
+		return;
+
+	gbp = (struct vxlanhdr_gbp *)vxh;
+	vxh->vx_flags |= VXLAN_HF_GBP;
+
+	if (md->gbp & VXLAN_GBP_DONT_LEARN)
+		gbp->dont_learn = 1;
+
+	if (md->gbp & VXLAN_GBP_POLICY_APPLIED)
+		gbp->policy_applied = 1;
+
+	gbp->policy_id = htons(md->gbp & VXLAN_GBP_ID_MASK);
+}
+
 #endif