From 101f4de9dd521c6d06dfdacaa35e506a8db8494b Mon Sep 17 00:00:00 2001 From: Oz Shlomo Date: Sun, 2 Dec 2018 14:43:27 +0200 Subject: net/mlx5e: Move TC tunnel offloading code to separate source file Move tunnel offloading related code to a separate source file for better code maintainability. Code refactoring with no functional change. Signed-off-by: Oz Shlomo Reviewed-by: Eli Britstein Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/Makefile | 2 +- .../net/ethernet/mellanox/mlx5/core/en/tc_tun.c | 496 ++++++++++++++++++++ .../net/ethernet/mellanox/mlx5/core/en/tc_tun.h | 43 ++ drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 1 + drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 500 +-------------------- drivers/net/ethernet/mellanox/mlx5/core/en_tc.h | 2 - 6 files changed, 548 insertions(+), 496 deletions(-) create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h (limited to 'drivers') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index d499b3d00348..40764d87413a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -30,7 +30,7 @@ mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \ mlx5_core-$(CONFIG_MLX5_EN_ARFS) += en_arfs.o mlx5_core-$(CONFIG_MLX5_EN_RXNFC) += en_fs_ethtool.o mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o en/port_buffer.o -mlx5_core-$(CONFIG_MLX5_ESWITCH) += en_rep.o en_tc.o +mlx5_core-$(CONFIG_MLX5_ESWITCH) += en_rep.o en_tc.o en/tc_tun.o # # Core extra diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c new file mode 100644 index 000000000000..eaa43477e0ea --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -0,0 +1,496 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2018 Mellanox Technologies. */ + +#include +#include "lib/vxlan.h" +#include "en/tc_tun.h" + +static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv, + struct net_device *mirred_dev, + struct net_device **out_dev, + struct flowi4 *fl4, + struct neighbour **out_n, + u8 *out_ttl) +{ + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + struct mlx5e_rep_priv *uplink_rpriv; + struct rtable *rt; + struct neighbour *n = NULL; + +#if IS_ENABLED(CONFIG_INET) + int ret; + + rt = ip_route_output_key(dev_net(mirred_dev), fl4); + ret = PTR_ERR_OR_ZERO(rt); + if (ret) + return ret; +#else + return -EOPNOTSUPP; +#endif + uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH); + /* if the egress device isn't on the same HW e-switch, we use the uplink */ + if (!switchdev_port_same_parent_id(priv->netdev, rt->dst.dev)) + *out_dev = uplink_rpriv->netdev; + else + *out_dev = rt->dst.dev; + + if (!(*out_ttl)) + *out_ttl = ip4_dst_hoplimit(&rt->dst); + n = dst_neigh_lookup(&rt->dst, &fl4->daddr); + ip_rt_put(rt); + if (!n) + return -ENOMEM; + + *out_n = n; + return 0; +} + +static const char *mlx5e_netdev_kind(struct net_device *dev) +{ + if (dev->rtnl_link_ops) + return dev->rtnl_link_ops->kind; + else + return ""; +} + +static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv, + struct net_device *mirred_dev, + struct net_device **out_dev, + struct flowi6 *fl6, + struct neighbour **out_n, + u8 *out_ttl) +{ + struct neighbour *n = NULL; + struct dst_entry *dst; + +#if IS_ENABLED(CONFIG_INET) && IS_ENABLED(CONFIG_IPV6) + struct mlx5e_rep_priv *uplink_rpriv; + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + int ret; + + ret = ipv6_stub->ipv6_dst_lookup(dev_net(mirred_dev), NULL, &dst, + fl6); + if (ret < 0) + return ret; + + if (!(*out_ttl)) + *out_ttl = ip6_dst_hoplimit(dst); + + uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH); + /* if the egress device isn't on the same HW e-switch, we use the uplink */ + if (!switchdev_port_same_parent_id(priv->netdev, dst->dev)) + *out_dev = uplink_rpriv->netdev; + else + *out_dev = dst->dev; +#else + return -EOPNOTSUPP; +#endif + + n = dst_neigh_lookup(dst, &fl6->daddr); + dst_release(dst); + if (!n) + return -ENOMEM; + + *out_n = n; + return 0; +} + +static int mlx5e_gen_vxlan_header(char buf[], struct ip_tunnel_key *tun_key) +{ + __be32 tun_id = tunnel_id_to_key32(tun_key->tun_id); + struct udphdr *udp = (struct udphdr *)(buf); + struct vxlanhdr *vxh = (struct vxlanhdr *) + ((char *)udp + sizeof(struct udphdr)); + + udp->dest = tun_key->tp_dst; + vxh->vx_flags = VXLAN_HF_VNI; + vxh->vx_vni = vxlan_vni_field(tun_id); + + return 0; +} + +static int mlx5e_gen_ip_tunnel_header(char buf[], __u8 *ip_proto, + struct mlx5e_encap_entry *e) +{ + int err = 0; + struct ip_tunnel_key *key = &e->tun_info.key; + + if (e->tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN) { + *ip_proto = IPPROTO_UDP; + err = mlx5e_gen_vxlan_header(buf, key); + } else { + pr_warn("mlx5: Cannot generate tunnel header for tunnel type (%d)\n" + , e->tunnel_type); + err = -EOPNOTSUPP; + } + + return err; +} + +int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, + struct net_device *mirred_dev, + struct mlx5e_encap_entry *e) +{ + int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size); + int ipv4_encap_size = ETH_HLEN + + sizeof(struct iphdr) + + e->tunnel_hlen; + struct ip_tunnel_key *tun_key = &e->tun_info.key; + struct net_device *out_dev; + struct neighbour *n = NULL; + struct flowi4 fl4 = {}; + char *encap_header; + struct ethhdr *eth; + u8 nud_state, ttl; + struct iphdr *ip; + int err; + + if (max_encap_size < ipv4_encap_size) { + mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n", + ipv4_encap_size, max_encap_size); + return -EOPNOTSUPP; + } + + encap_header = kzalloc(ipv4_encap_size, GFP_KERNEL); + if (!encap_header) + return -ENOMEM; + + /* add the IP fields */ + fl4.flowi4_tos = tun_key->tos; + fl4.daddr = tun_key->u.ipv4.dst; + fl4.saddr = tun_key->u.ipv4.src; + ttl = tun_key->ttl; + + err = mlx5e_route_lookup_ipv4(priv, mirred_dev, &out_dev, + &fl4, &n, &ttl); + if (err) + goto free_encap; + + /* used by mlx5e_detach_encap to lookup a neigh hash table + * entry in the neigh hash table when a user deletes a rule + */ + e->m_neigh.dev = n->dev; + e->m_neigh.family = n->ops->family; + memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len); + e->out_dev = out_dev; + + /* It's important to add the neigh to the hash table before checking + * the neigh validity state. So if we'll get a notification, in case the + * neigh changes it's validity state, we would find the relevant neigh + * in the hash. + */ + err = mlx5e_rep_encap_entry_attach(netdev_priv(out_dev), e); + if (err) + goto free_encap; + + read_lock_bh(&n->lock); + nud_state = n->nud_state; + ether_addr_copy(e->h_dest, n->ha); + read_unlock_bh(&n->lock); + + /* add ethernet header */ + eth = (struct ethhdr *)encap_header; + ether_addr_copy(eth->h_dest, e->h_dest); + ether_addr_copy(eth->h_source, out_dev->dev_addr); + eth->h_proto = htons(ETH_P_IP); + + /* add ip header */ + ip = (struct iphdr *)((char *)eth + sizeof(struct ethhdr)); + ip->tos = tun_key->tos; + ip->version = 0x4; + ip->ihl = 0x5; + ip->ttl = ttl; + ip->daddr = fl4.daddr; + ip->saddr = fl4.saddr; + + /* add tunneling protocol header */ + err = mlx5e_gen_ip_tunnel_header((char *)ip + sizeof(struct iphdr), + &ip->protocol, e); + if (err) + goto destroy_neigh_entry; + + e->encap_size = ipv4_encap_size; + e->encap_header = encap_header; + + if (!(nud_state & NUD_VALID)) { + neigh_event_send(n, NULL); + err = -EAGAIN; + goto out; + } + + err = mlx5_packet_reformat_alloc(priv->mdev, + e->reformat_type, + ipv4_encap_size, encap_header, + MLX5_FLOW_NAMESPACE_FDB, + &e->encap_id); + if (err) + goto destroy_neigh_entry; + + e->flags |= MLX5_ENCAP_ENTRY_VALID; + mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev)); + neigh_release(n); + return err; + +destroy_neigh_entry: + mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e); +free_encap: + kfree(encap_header); +out: + if (n) + neigh_release(n); + return err; +} + +int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, + struct net_device *mirred_dev, + struct mlx5e_encap_entry *e) +{ + int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size); + int ipv6_encap_size = ETH_HLEN + + sizeof(struct ipv6hdr) + + e->tunnel_hlen; + struct ip_tunnel_key *tun_key = &e->tun_info.key; + struct net_device *out_dev; + struct neighbour *n = NULL; + struct flowi6 fl6 = {}; + struct ipv6hdr *ip6h; + char *encap_header; + struct ethhdr *eth; + u8 nud_state, ttl; + int err; + + if (max_encap_size < ipv6_encap_size) { + mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n", + ipv6_encap_size, max_encap_size); + return -EOPNOTSUPP; + } + + encap_header = kzalloc(ipv6_encap_size, GFP_KERNEL); + if (!encap_header) + return -ENOMEM; + + ttl = tun_key->ttl; + + fl6.flowlabel = ip6_make_flowinfo(RT_TOS(tun_key->tos), tun_key->label); + fl6.daddr = tun_key->u.ipv6.dst; + fl6.saddr = tun_key->u.ipv6.src; + + err = mlx5e_route_lookup_ipv6(priv, mirred_dev, &out_dev, + &fl6, &n, &ttl); + if (err) + goto free_encap; + + /* used by mlx5e_detach_encap to lookup a neigh hash table + * entry in the neigh hash table when a user deletes a rule + */ + e->m_neigh.dev = n->dev; + e->m_neigh.family = n->ops->family; + memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len); + e->out_dev = out_dev; + + /* It's importent to add the neigh to the hash table before checking + * the neigh validity state. So if we'll get a notification, in case the + * neigh changes it's validity state, we would find the relevant neigh + * in the hash. + */ + err = mlx5e_rep_encap_entry_attach(netdev_priv(out_dev), e); + if (err) + goto free_encap; + + read_lock_bh(&n->lock); + nud_state = n->nud_state; + ether_addr_copy(e->h_dest, n->ha); + read_unlock_bh(&n->lock); + + /* add ethernet header */ + eth = (struct ethhdr *)encap_header; + ether_addr_copy(eth->h_dest, e->h_dest); + ether_addr_copy(eth->h_source, out_dev->dev_addr); + eth->h_proto = htons(ETH_P_IPV6); + + /* add ip header */ + ip6h = (struct ipv6hdr *)((char *)eth + sizeof(struct ethhdr)); + ip6_flow_hdr(ip6h, tun_key->tos, 0); + /* the HW fills up ipv6 payload len */ + ip6h->hop_limit = ttl; + ip6h->daddr = fl6.daddr; + ip6h->saddr = fl6.saddr; + + /* add tunneling protocol header */ + err = mlx5e_gen_ip_tunnel_header((char *)ip6h + sizeof(struct ipv6hdr), + &ip6h->nexthdr, e); + if (err) + goto destroy_neigh_entry; + + e->encap_size = ipv6_encap_size; + e->encap_header = encap_header; + + if (!(nud_state & NUD_VALID)) { + neigh_event_send(n, NULL); + err = -EAGAIN; + goto out; + } + + err = mlx5_packet_reformat_alloc(priv->mdev, + e->reformat_type, + ipv6_encap_size, encap_header, + MLX5_FLOW_NAMESPACE_FDB, + &e->encap_id); + if (err) + goto destroy_neigh_entry; + + e->flags |= MLX5_ENCAP_ENTRY_VALID; + mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev)); + neigh_release(n); + return err; + +destroy_neigh_entry: + mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e); +free_encap: + kfree(encap_header); +out: + if (n) + neigh_release(n); + return err; +} + +int mlx5e_tc_tun_get_type(struct net_device *tunnel_dev) +{ + if (netif_is_vxlan(tunnel_dev)) + return MLX5E_TC_TUNNEL_TYPE_VXLAN; + else + return MLX5E_TC_TUNNEL_TYPE_UNKNOWN; +} + +bool mlx5e_tc_tun_device_to_offload(struct mlx5e_priv *priv, + struct net_device *netdev) +{ + int tunnel_type = mlx5e_tc_tun_get_type(netdev); + + if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN && + MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap)) + return true; + else + return false; +} + +int mlx5e_tc_tun_init_encap_attr(struct net_device *tunnel_dev, + struct mlx5e_priv *priv, + struct mlx5e_encap_entry *e, + struct netlink_ext_ack *extack) +{ + e->tunnel_type = mlx5e_tc_tun_get_type(tunnel_dev); + + if (e->tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN) { + int dst_port = be16_to_cpu(e->tun_info.key.tp_dst); + + if (!mlx5_vxlan_lookup_port(priv->mdev->vxlan, dst_port)) { + NL_SET_ERR_MSG_MOD(extack, + "vxlan udp dport was not registered with the HW"); + netdev_warn(priv->netdev, + "%d isn't an offloaded vxlan udp dport\n", + dst_port); + return -EOPNOTSUPP; + } + e->reformat_type = MLX5_REFORMAT_TYPE_L2_TO_VXLAN; + e->tunnel_hlen = VXLAN_HLEN; + } else { + e->reformat_type = -1; + e->tunnel_hlen = -1; + return -EOPNOTSUPP; + } + return 0; +} + +static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv, + struct mlx5_flow_spec *spec, + struct tc_cls_flower_offload *f, + void *headers_c, + void *headers_v) +{ + struct netlink_ext_ack *extack = f->common.extack; + struct flow_dissector_key_ports *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ENC_PORTS, + f->key); + struct flow_dissector_key_ports *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ENC_PORTS, + f->mask); + void *misc_c = MLX5_ADDR_OF(fte_match_param, + spec->match_criteria, + misc_parameters); + void *misc_v = MLX5_ADDR_OF(fte_match_param, + spec->match_value, + misc_parameters); + + /* Full udp dst port must be given */ + if (!dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_PORTS) || + memchr_inv(&mask->dst, 0xff, sizeof(mask->dst))) { + NL_SET_ERR_MSG_MOD(extack, + "VXLAN decap filter must include enc_dst_port condition"); + netdev_warn(priv->netdev, + "VXLAN decap filter must include enc_dst_port condition\n"); + return -EOPNOTSUPP; + } + + /* udp dst port must be knonwn as a VXLAN port */ + if (!mlx5_vxlan_lookup_port(priv->mdev->vxlan, be16_to_cpu(key->dst))) { + NL_SET_ERR_MSG_MOD(extack, + "Matched UDP port is not registered as a VXLAN port"); + netdev_warn(priv->netdev, + "UDP port %d is not registered as a VXLAN port\n", + be16_to_cpu(key->dst)); + return -EOPNOTSUPP; + } + + /* dst UDP port is valid here */ + MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ip_protocol); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol, IPPROTO_UDP); + + MLX5_SET(fte_match_set_lyr_2_4, headers_c, udp_dport, ntohs(mask->dst)); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, udp_dport, ntohs(key->dst)); + + MLX5_SET(fte_match_set_lyr_2_4, headers_c, udp_sport, ntohs(mask->src)); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, udp_sport, ntohs(key->src)); + + /* match on VNI */ + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) { + struct flow_dissector_key_keyid *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ENC_KEYID, + f->key); + struct flow_dissector_key_keyid *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ENC_KEYID, + f->mask); + MLX5_SET(fte_match_set_misc, misc_c, vxlan_vni, + be32_to_cpu(mask->keyid)); + MLX5_SET(fte_match_set_misc, misc_v, vxlan_vni, + be32_to_cpu(key->keyid)); + } + return 0; +} + +int mlx5e_tc_tun_parse(struct net_device *filter_dev, + struct mlx5e_priv *priv, + struct mlx5_flow_spec *spec, + struct tc_cls_flower_offload *f, + void *headers_c, + void *headers_v) +{ + int tunnel_type; + int err = 0; + + tunnel_type = mlx5e_tc_tun_get_type(filter_dev); + if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN) { + err = mlx5e_tc_tun_parse_vxlan(priv, spec, f, + headers_c, headers_v); + } else { + netdev_warn(priv->netdev, + "decapsulation offload is not supported for %s net device (%d)\n", + mlx5e_netdev_kind(filter_dev), tunnel_type); + return -EOPNOTSUPP; + } + return err; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h new file mode 100644 index 000000000000..ad4fc93b17a1 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2018 Mellanox Technologies. */ + +#ifndef __MLX5_EN_TC_TUNNEL_H__ +#define __MLX5_EN_TC_TUNNEL_H__ + +#include +#include +#include +#include +#include "en.h" +#include "en_rep.h" + +enum { + MLX5E_TC_TUNNEL_TYPE_UNKNOWN, + MLX5E_TC_TUNNEL_TYPE_VXLAN +}; + +int mlx5e_tc_tun_init_encap_attr(struct net_device *tunnel_dev, + struct mlx5e_priv *priv, + struct mlx5e_encap_entry *e, + struct netlink_ext_ack *extack); + +int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, + struct net_device *mirred_dev, + struct mlx5e_encap_entry *e); + +int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, + struct net_device *mirred_dev, + struct mlx5e_encap_entry *e); + +int mlx5e_tc_tun_get_type(struct net_device *tunnel_dev); +bool mlx5e_tc_tun_device_to_offload(struct mlx5e_priv *priv, + struct net_device *netdev); + +int mlx5e_tc_tun_parse(struct net_device *filter_dev, + struct mlx5e_priv *priv, + struct mlx5_flow_spec *spec, + struct tc_cls_flower_offload *f, + void *headers_c, + void *headers_v); + +#endif //__MLX5_EN_TC_TUNNEL_H__ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 5cac4de435c9..85e51bd4147f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -42,6 +42,7 @@ #include "en.h" #include "en_rep.h" #include "en_tc.h" +#include "en/tc_tun.h" #include "fs_core.h" #define MLX5E_REP_PARAMS_LOG_SQ_SIZE \ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 7d7f490d8ff1..abc200947e84 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -44,15 +44,14 @@ #include #include #include -#include #include #include "en.h" #include "en_rep.h" #include "en_tc.h" #include "eswitch.h" -#include "lib/vxlan.h" #include "fs_core.h" #include "en/port.h" +#include "en/tc_tun.h" struct mlx5_nic_flow_attr { u32 action; @@ -79,13 +78,6 @@ enum { #define MLX5E_TC_MAX_SPLITS 1 -enum { - MLX5E_TC_TUNNEL_TYPE_UNKNOWN, - MLX5E_TC_TUNNEL_TYPE_VXLAN -}; - -static int mlx5e_get_tunnel_type(struct net_device *tunnel_dev); - struct mlx5e_tc_flow { struct rhash_head node; struct mlx5e_priv *priv; @@ -684,14 +676,6 @@ static void mlx5e_hairpin_flow_del(struct mlx5e_priv *priv, } } -static const char *mlx5e_netdev_kind(struct net_device *dev) -{ - if (dev->rtnl_link_ops) - return dev->rtnl_link_ops->kind; - else - return ""; -} - static int mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, struct mlx5e_tc_flow_parse_attr *parse_attr, @@ -1209,75 +1193,6 @@ static void mlx5e_tc_del_flow(struct mlx5e_priv *priv, mlx5e_tc_del_nic_flow(priv, flow); } -static int parse_tunnel_vxlan_attr(struct mlx5e_priv *priv, - struct mlx5_flow_spec *spec, - struct tc_cls_flower_offload *f, - void *headers_c, - void *headers_v) -{ - struct netlink_ext_ack *extack = f->common.extack; - struct flow_dissector_key_ports *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_PORTS, - f->key); - struct flow_dissector_key_ports *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_PORTS, - f->mask); - void *misc_c = MLX5_ADDR_OF(fte_match_param, - spec->match_criteria, - misc_parameters); - void *misc_v = MLX5_ADDR_OF(fte_match_param, - spec->match_value, - misc_parameters); - - /* Full udp dst port must be given */ - if (!dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_PORTS) || - memchr_inv(&mask->dst, 0xff, sizeof(mask->dst))) { - NL_SET_ERR_MSG_MOD(extack, - "VXLAN decap filter must include enc_dst_port condition"); - netdev_warn(priv->netdev, - "VXLAN decap filter must include enc_dst_port condition\n"); - return -EOPNOTSUPP; - } - - /* udp dst port must be knonwn as a VXLAN port */ - if (!mlx5_vxlan_lookup_port(priv->mdev->vxlan, be16_to_cpu(key->dst))) { - NL_SET_ERR_MSG_MOD(extack, - "Matched UDP port is not registered as a VXLAN port"); - netdev_warn(priv->netdev, - "UDP port %d is not registered as a VXLAN port\n", - be16_to_cpu(key->dst)); - return -EOPNOTSUPP; - } - - /* dst UDP port is valid here */ - MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ip_protocol); - MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol, IPPROTO_UDP); - - MLX5_SET(fte_match_set_lyr_2_4, headers_c, udp_dport, ntohs(mask->dst)); - MLX5_SET(fte_match_set_lyr_2_4, headers_v, udp_dport, ntohs(key->dst)); - - MLX5_SET(fte_match_set_lyr_2_4, headers_c, udp_sport, ntohs(mask->src)); - MLX5_SET(fte_match_set_lyr_2_4, headers_v, udp_sport, ntohs(key->src)); - - /* match on VNI */ - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) { - struct flow_dissector_key_keyid *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_KEYID, - f->key); - struct flow_dissector_key_keyid *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_KEYID, - f->mask); - MLX5_SET(fte_match_set_misc, misc_c, vxlan_vni, - be32_to_cpu(mask->keyid)); - MLX5_SET(fte_match_set_misc, misc_v, vxlan_vni, - be32_to_cpu(key->keyid)); - } - return 0; -} static int parse_tunnel_attr(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec, @@ -1294,29 +1209,14 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv, skb_flow_dissector_target(f->dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL, f->key); - int tunnel_type; int err = 0; - tunnel_type = mlx5e_get_tunnel_type(filter_dev); - if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN) { - err = parse_tunnel_vxlan_attr(priv, spec, f, - headers_c, headers_v); - } else { - NL_SET_ERR_MSG_MOD(extack, - "decapsulation offload is not supported"); - netdev_warn(priv->netdev, - "decapsulation offload is not supported for %s net device (%d)\n", - mlx5e_netdev_kind(filter_dev), tunnel_type); - return -EOPNOTSUPP; - } - + err = mlx5e_tc_tun_parse(filter_dev, priv, spec, f, + headers_c, headers_v); if (err) { NL_SET_ERR_MSG_MOD(extack, "failed to parse tunnel attributes"); - netdev_warn(priv->netdev, - "failed to parse %s tunnel attributes (%d)\n", - mlx5e_netdev_kind(filter_dev), tunnel_type); - return -EOPNOTSUPP; + return err; } if (enc_control->addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { @@ -2359,45 +2259,6 @@ static inline int hash_encap_info(struct ip_tunnel_key *key) return jhash(key, sizeof(*key), 0); } -static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv, - struct net_device *mirred_dev, - struct net_device **out_dev, - struct flowi4 *fl4, - struct neighbour **out_n, - u8 *out_ttl) -{ - struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - struct mlx5e_rep_priv *uplink_rpriv; - struct rtable *rt; - struct neighbour *n = NULL; - -#if IS_ENABLED(CONFIG_INET) - int ret; - - rt = ip_route_output_key(dev_net(mirred_dev), fl4); - ret = PTR_ERR_OR_ZERO(rt); - if (ret) - return ret; -#else - return -EOPNOTSUPP; -#endif - uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH); - /* if the egress device isn't on the same HW e-switch, we use the uplink */ - if (!switchdev_port_same_parent_id(priv->netdev, rt->dst.dev)) - *out_dev = uplink_rpriv->netdev; - else - *out_dev = rt->dst.dev; - - if (!(*out_ttl)) - *out_ttl = ip4_dst_hoplimit(&rt->dst); - n = dst_neigh_lookup(&rt->dst, &fl4->daddr); - ip_rt_put(rt); - if (!n) - return -ENOMEM; - - *out_n = n; - return 0; -} static bool is_merged_eswitch_dev(struct mlx5e_priv *priv, struct net_device *peer_netdev) @@ -2413,354 +2274,7 @@ static bool is_merged_eswitch_dev(struct mlx5e_priv *priv, (peer_priv->mdev->priv.eswitch->mode == SRIOV_OFFLOADS)); } -static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv, - struct net_device *mirred_dev, - struct net_device **out_dev, - struct flowi6 *fl6, - struct neighbour **out_n, - u8 *out_ttl) -{ - struct neighbour *n = NULL; - struct dst_entry *dst; - -#if IS_ENABLED(CONFIG_INET) && IS_ENABLED(CONFIG_IPV6) - struct mlx5e_rep_priv *uplink_rpriv; - struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - int ret; - - ret = ipv6_stub->ipv6_dst_lookup(dev_net(mirred_dev), NULL, &dst, - fl6); - if (ret < 0) - return ret; - - if (!(*out_ttl)) - *out_ttl = ip6_dst_hoplimit(dst); - - uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH); - /* if the egress device isn't on the same HW e-switch, we use the uplink */ - if (!switchdev_port_same_parent_id(priv->netdev, dst->dev)) - *out_dev = uplink_rpriv->netdev; - else - *out_dev = dst->dev; -#else - return -EOPNOTSUPP; -#endif - - n = dst_neigh_lookup(dst, &fl6->daddr); - dst_release(dst); - if (!n) - return -ENOMEM; - - *out_n = n; - return 0; -} - -static int mlx5e_gen_vxlan_header(char buf[], struct ip_tunnel_key *tun_key) -{ - __be32 tun_id = tunnel_id_to_key32(tun_key->tun_id); - struct udphdr *udp = (struct udphdr *)(buf); - struct vxlanhdr *vxh = (struct vxlanhdr *) - ((char *)udp + sizeof(struct udphdr)); - - udp->dest = tun_key->tp_dst; - vxh->vx_flags = VXLAN_HF_VNI; - vxh->vx_vni = vxlan_vni_field(tun_id); - - return 0; -} - -static int mlx5e_gen_ip_tunnel_header(char buf[], __u8 *ip_proto, - struct mlx5e_encap_entry *e) -{ - int err = 0; - struct ip_tunnel_key *key = &e->tun_info.key; - - if (e->tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN) { - *ip_proto = IPPROTO_UDP; - err = mlx5e_gen_vxlan_header(buf, key); - } else { - pr_warn("mlx5: Cannot generate tunnel header for tunnel type (%d)\n" - , e->tunnel_type); - err = -EOPNOTSUPP; - } - - return err; -} - -static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv, - struct net_device *mirred_dev, - struct mlx5e_encap_entry *e) -{ - int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size); - int ipv4_encap_size = ETH_HLEN + - sizeof(struct iphdr) + - e->tunnel_hlen; - struct ip_tunnel_key *tun_key = &e->tun_info.key; - struct net_device *out_dev; - struct neighbour *n = NULL; - struct flowi4 fl4 = {}; - char *encap_header; - struct ethhdr *eth; - u8 nud_state, ttl; - struct iphdr *ip; - int err; - - if (max_encap_size < ipv4_encap_size) { - mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n", - ipv4_encap_size, max_encap_size); - return -EOPNOTSUPP; - } - - encap_header = kzalloc(ipv4_encap_size, GFP_KERNEL); - if (!encap_header) - return -ENOMEM; - - /* add the IP fields */ - fl4.flowi4_tos = tun_key->tos; - fl4.daddr = tun_key->u.ipv4.dst; - fl4.saddr = tun_key->u.ipv4.src; - ttl = tun_key->ttl; - - err = mlx5e_route_lookup_ipv4(priv, mirred_dev, &out_dev, - &fl4, &n, &ttl); - if (err) - goto free_encap; - - /* used by mlx5e_detach_encap to lookup a neigh hash table - * entry in the neigh hash table when a user deletes a rule - */ - e->m_neigh.dev = n->dev; - e->m_neigh.family = n->ops->family; - memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len); - e->out_dev = out_dev; - - /* It's important to add the neigh to the hash table before checking - * the neigh validity state. So if we'll get a notification, in case the - * neigh changes it's validity state, we would find the relevant neigh - * in the hash. - */ - err = mlx5e_rep_encap_entry_attach(netdev_priv(out_dev), e); - if (err) - goto free_encap; - - read_lock_bh(&n->lock); - nud_state = n->nud_state; - ether_addr_copy(e->h_dest, n->ha); - read_unlock_bh(&n->lock); - - /* add ethernet header */ - eth = (struct ethhdr *)encap_header; - ether_addr_copy(eth->h_dest, e->h_dest); - ether_addr_copy(eth->h_source, out_dev->dev_addr); - eth->h_proto = htons(ETH_P_IP); - - /* add ip header */ - ip = (struct iphdr *)((char *)eth + sizeof(struct ethhdr)); - ip->tos = tun_key->tos; - ip->version = 0x4; - ip->ihl = 0x5; - ip->ttl = ttl; - ip->daddr = fl4.daddr; - ip->saddr = fl4.saddr; - - /* add tunneling protocol header */ - err = mlx5e_gen_ip_tunnel_header((char *)ip + sizeof(struct iphdr), - &ip->protocol, e); - if (err) - goto destroy_neigh_entry; - - e->encap_size = ipv4_encap_size; - e->encap_header = encap_header; - - if (!(nud_state & NUD_VALID)) { - neigh_event_send(n, NULL); - err = -EAGAIN; - goto out; - } - - err = mlx5_packet_reformat_alloc(priv->mdev, - e->reformat_type, - ipv4_encap_size, encap_header, - MLX5_FLOW_NAMESPACE_FDB, - &e->encap_id); - if (err) - goto destroy_neigh_entry; - - e->flags |= MLX5_ENCAP_ENTRY_VALID; - mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev)); - neigh_release(n); - return err; - -destroy_neigh_entry: - mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e); -free_encap: - kfree(encap_header); -out: - if (n) - neigh_release(n); - return err; -} - -static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv, - struct net_device *mirred_dev, - struct mlx5e_encap_entry *e) -{ - int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size); - int ipv6_encap_size = ETH_HLEN + - sizeof(struct ipv6hdr) + - e->tunnel_hlen; - struct ip_tunnel_key *tun_key = &e->tun_info.key; - struct net_device *out_dev; - struct neighbour *n = NULL; - struct flowi6 fl6 = {}; - struct ipv6hdr *ip6h; - char *encap_header; - struct ethhdr *eth; - u8 nud_state, ttl; - int err; - - if (max_encap_size < ipv6_encap_size) { - mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n", - ipv6_encap_size, max_encap_size); - return -EOPNOTSUPP; - } - - encap_header = kzalloc(ipv6_encap_size, GFP_KERNEL); - if (!encap_header) - return -ENOMEM; - - ttl = tun_key->ttl; - - fl6.flowlabel = ip6_make_flowinfo(RT_TOS(tun_key->tos), tun_key->label); - fl6.daddr = tun_key->u.ipv6.dst; - fl6.saddr = tun_key->u.ipv6.src; - - err = mlx5e_route_lookup_ipv6(priv, mirred_dev, &out_dev, - &fl6, &n, &ttl); - if (err) - goto free_encap; - - /* used by mlx5e_detach_encap to lookup a neigh hash table - * entry in the neigh hash table when a user deletes a rule - */ - e->m_neigh.dev = n->dev; - e->m_neigh.family = n->ops->family; - memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len); - e->out_dev = out_dev; - - /* It's importent to add the neigh to the hash table before checking - * the neigh validity state. So if we'll get a notification, in case the - * neigh changes it's validity state, we would find the relevant neigh - * in the hash. - */ - err = mlx5e_rep_encap_entry_attach(netdev_priv(out_dev), e); - if (err) - goto free_encap; - - read_lock_bh(&n->lock); - nud_state = n->nud_state; - ether_addr_copy(e->h_dest, n->ha); - read_unlock_bh(&n->lock); - - /* add ethernet header */ - eth = (struct ethhdr *)encap_header; - ether_addr_copy(eth->h_dest, e->h_dest); - ether_addr_copy(eth->h_source, out_dev->dev_addr); - eth->h_proto = htons(ETH_P_IPV6); - - /* add ip header */ - ip6h = (struct ipv6hdr *)((char *)eth + sizeof(struct ethhdr)); - ip6_flow_hdr(ip6h, tun_key->tos, 0); - /* the HW fills up ipv6 payload len */ - ip6h->hop_limit = ttl; - ip6h->daddr = fl6.daddr; - ip6h->saddr = fl6.saddr; - - /* add tunneling protocol header */ - err = mlx5e_gen_ip_tunnel_header((char *)ip6h + sizeof(struct ipv6hdr), - &ip6h->nexthdr, e); - if (err) - goto destroy_neigh_entry; - - e->encap_size = ipv6_encap_size; - e->encap_header = encap_header; - - if (!(nud_state & NUD_VALID)) { - neigh_event_send(n, NULL); - err = -EAGAIN; - goto out; - } - - err = mlx5_packet_reformat_alloc(priv->mdev, - e->reformat_type, - ipv6_encap_size, encap_header, - MLX5_FLOW_NAMESPACE_FDB, - &e->encap_id); - if (err) - goto destroy_neigh_entry; - - e->flags |= MLX5_ENCAP_ENTRY_VALID; - mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev)); - neigh_release(n); - return err; - -destroy_neigh_entry: - mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e); -free_encap: - kfree(encap_header); -out: - if (n) - neigh_release(n); - return err; -} - -static int mlx5e_get_tunnel_type(struct net_device *tunnel_dev) -{ - if (netif_is_vxlan(tunnel_dev)) - return MLX5E_TC_TUNNEL_TYPE_VXLAN; - else - return MLX5E_TC_TUNNEL_TYPE_UNKNOWN; -} - -bool mlx5e_tc_tun_device_to_offload(struct mlx5e_priv *priv, - struct net_device *netdev) -{ - int tunnel_type = mlx5e_get_tunnel_type(netdev); - - if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN && - MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap)) - return true; - else - return false; -} -static int mlx5e_init_tunnel_attr(struct net_device *tunnel_dev, - struct mlx5e_priv *priv, - struct mlx5e_encap_entry *e, - struct netlink_ext_ack *extack) -{ - e->tunnel_type = mlx5e_get_tunnel_type(tunnel_dev); - - if (e->tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN) { - int dst_port = be16_to_cpu(e->tun_info.key.tp_dst); - - if (!mlx5_vxlan_lookup_port(priv->mdev->vxlan, dst_port)) { - NL_SET_ERR_MSG_MOD(extack, - "vxlan udp dport was not registered with the HW"); - netdev_warn(priv->netdev, - "%d isn't an offloaded vxlan udp dport\n", - dst_port); - return -EOPNOTSUPP; - } - e->reformat_type = MLX5_REFORMAT_TYPE_L2_TO_VXLAN; - e->tunnel_hlen = VXLAN_HLEN; - } else { - e->reformat_type = -1; - e->tunnel_hlen = -1; - return -EOPNOTSUPP; - } - return 0; -} static int mlx5e_attach_encap(struct mlx5e_priv *priv, struct ip_tunnel_info *tun_info, @@ -2797,16 +2311,16 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv, return -ENOMEM; e->tun_info = *tun_info; - err = mlx5e_init_tunnel_attr(mirred_dev, priv, e, extack); + err = mlx5e_tc_tun_init_encap_attr(mirred_dev, priv, e, extack); if (err) goto out_err; INIT_LIST_HEAD(&e->flows); if (family == AF_INET) - err = mlx5e_create_encap_header_ipv4(priv, mirred_dev, e); + err = mlx5e_tc_tun_create_header_ipv4(priv, mirred_dev, e); else if (family == AF_INET6) - err = mlx5e_create_encap_header_ipv6(priv, mirred_dev, e); + err = mlx5e_tc_tun_create_header_ipv6(priv, mirred_dev, e); if (err && err != -EAGAIN) goto out_err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h index 004e679a4f53..a15c08a35054 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h @@ -70,8 +70,6 @@ void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe); int mlx5e_tc_num_filters(struct mlx5e_priv *priv); -bool mlx5e_tc_tun_device_to_offload(struct mlx5e_priv *priv, - struct net_device *netdev); #else /* CONFIG_MLX5_ESWITCH */ static inline int mlx5e_tc_nic_init(struct mlx5e_priv *priv) { return 0; } -- cgit v1.2.3-59-g8ed1b