// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* Copyright (c) 2020 Mellanox Technologies. */ #include #include #include #include #include #include #include #include "tc.h" #include "neigh.h" #include "en_rep.h" #include "eswitch.h" #include "lib/fs_chains.h" #include "en/tc_ct.h" #include "en/mapping.h" #include "en/tc_tun.h" #include "lib/port_tun.h" struct mlx5e_rep_indr_block_priv { struct net_device *netdev; struct mlx5e_rep_priv *rpriv; struct list_head list; }; int mlx5e_rep_encap_entry_attach(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e) { struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_rep_uplink_priv *uplink_priv = &rpriv->uplink_priv; struct mlx5_tun_entropy *tun_entropy = &uplink_priv->tun_entropy; struct mlx5e_neigh_hash_entry *nhe; int err; err = mlx5_tun_entropy_refcount_inc(tun_entropy, e->reformat_type); if (err) return err; mutex_lock(&rpriv->neigh_update.encap_lock); nhe = mlx5e_rep_neigh_entry_lookup(priv, &e->m_neigh); if (!nhe) { err = mlx5e_rep_neigh_entry_create(priv, e, &nhe); if (err) { mutex_unlock(&rpriv->neigh_update.encap_lock); mlx5_tun_entropy_refcount_dec(tun_entropy, e->reformat_type); return err; } } e->nhe = nhe; spin_lock(&nhe->encap_list_lock); list_add_rcu(&e->encap_list, &nhe->encap_list); spin_unlock(&nhe->encap_list_lock); mutex_unlock(&rpriv->neigh_update.encap_lock); return 0; } void mlx5e_rep_encap_entry_detach(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e) { struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_rep_uplink_priv *uplink_priv = &rpriv->uplink_priv; struct mlx5_tun_entropy *tun_entropy = &uplink_priv->tun_entropy; if (!e->nhe) return; spin_lock(&e->nhe->encap_list_lock); list_del_rcu(&e->encap_list); spin_unlock(&e->nhe->encap_list_lock); mlx5e_rep_neigh_entry_release(e->nhe); e->nhe = NULL; mlx5_tun_entropy_refcount_dec(tun_entropy, e->reformat_type); } void mlx5e_rep_update_flows(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e, bool neigh_connected, unsigned char ha[ETH_ALEN]) { struct ethhdr *eth = (struct ethhdr *)e->encap_header; struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; bool encap_connected; LIST_HEAD(flow_list); ASSERT_RTNL(); /* wait for encap to be fully initialized */ wait_for_completion(&e->res_ready); mutex_lock(&esw->offloads.encap_tbl_lock); encap_connected = !!(e->flags & MLX5_ENCAP_ENTRY_VALID); if (e->compl_result < 0 || (encap_connected == neigh_connected && ether_addr_equal(e->h_dest, ha))) goto unlock; mlx5e_take_all_encap_flows(e, &flow_list); if ((e->flags & MLX5_ENCAP_ENTRY_VALID) && (!neigh_connected || !ether_addr_equal(e->h_dest, ha))) mlx5e_tc_encap_flows_del(priv, e, &flow_list); if (neigh_connected && !(e->flags & MLX5_ENCAP_ENTRY_VALID)) { struct net_device *route_dev; ether_addr_copy(e->h_dest, ha); ether_addr_copy(eth->h_dest, ha); /* Update the encap source mac, in case that we delete * the flows when encap source mac changed. */ route_dev = __dev_get_by_index(dev_net(priv->netdev), e->route_dev_ifindex); if (route_dev) ether_addr_copy(eth->h_source, route_dev->dev_addr); mlx5e_tc_encap_flows_add(priv, e, &flow_list); } unlock: mutex_unlock(&esw->offloads.encap_tbl_lock); mlx5e_put_encap_flow_list(priv, &flow_list); } static int mlx5e_rep_setup_tc_cls_flower(struct mlx5e_priv *priv, struct flow_cls_offload *cls_flower, int flags) { switch (cls_flower->command) { case FLOW_CLS_REPLACE: return mlx5e_configure_flower(priv->netdev, priv, cls_flower, flags); case FLOW_CLS_DESTROY: return mlx5e_delete_flower(priv->netdev, priv, cls_flower, flags); case FLOW_CLS_STATS: return mlx5e_stats_flower(priv->netdev, priv, cls_flower, flags); default: return -EOPNOTSUPP; } } static int mlx5e_rep_setup_tc_cls_matchall(struct mlx5e_priv *priv, struct tc_cls_matchall_offload *ma) { switch (ma->command) { case TC_CLSMATCHALL_REPLACE: return mlx5e_tc_configure_matchall(priv, ma); case TC_CLSMATCHALL_DESTROY: return mlx5e_tc_delete_matchall(priv, ma); case TC_CLSMATCHALL_STATS: mlx5e_tc_stats_matchall(priv, ma); return 0; default: return -EOPNOTSUPP; } } static int mlx5e_rep_setup_tc_cb(enum tc_setup_type type, void *type_data, void *cb_priv) { unsigned long flags = MLX5_TC_FLAG(INGRESS) | MLX5_TC_FLAG(ESW_OFFLOAD); struct mlx5e_priv *priv = cb_priv; switch (type) { case TC_SETUP_CLSFLOWER: return mlx5e_rep_setup_tc_cls_flower(priv, type_data, flags); case TC_SETUP_CLSMATCHALL: return mlx5e_rep_setup_tc_cls_matchall(priv, type_data); default: return -EOPNOTSUPP; } } static int mlx5e_rep_setup_ft_cb(enum tc_setup_type type, void *type_data, void *cb_priv) { struct flow_cls_offload tmp, *f = type_data; struct mlx5e_priv *priv = cb_priv; struct mlx5_eswitch *esw; unsigned long flags; int err; flags = MLX5_TC_FLAG(INGRESS) | MLX5_TC_FLAG(ESW_OFFLOAD) | MLX5_TC_FLAG(FT_OFFLOAD); esw = priv->mdev->priv.eswitch; switch (type) { case TC_SETUP_CLSFLOWER: memcpy(&tmp, f, sizeof(*f)); if (!mlx5_chains_prios_supported(esw_chains(esw))) return -EOPNOTSUPP; /* Re-use tc offload path by moving the ft flow to the * reserved ft chain. * * FT offload can use prio range [0, INT_MAX], so we normalize * it to range [1, mlx5_esw_chains_get_prio_range(esw)] * as with tc, where prio 0 isn't supported. * * We only support chain 0 of FT offload. */ if (tmp.common.prio >= mlx5_chains_get_prio_range(esw_chains(esw))) return -EOPNOTSUPP; if (tmp.common.chain_index != 0) return -EOPNOTSUPP; tmp.common.chain_index = mlx5_chains_get_nf_ft_chain(esw_chains(esw)); tmp.common.prio++; err = mlx5e_rep_setup_tc_cls_flower(priv, &tmp, flags); memcpy(&f->stats, &tmp.stats, sizeof(f->stats)); return err; default: return -EOPNOTSUPP; } } static LIST_HEAD(mlx5e_rep_block_tc_cb_list); static LIST_HEAD(mlx5e_rep_block_ft_cb_list); int mlx5e_rep_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data) { struct mlx5e_priv *priv = netdev_priv(dev); struct flow_block_offload *f = type_data; f->unlocked_driver_cb = true; switch (type) { case TC_SETUP_BLOCK: return flow_block_cb_setup_simple(type_data, &mlx5e_rep_block_tc_cb_list, mlx5e_rep_setup_tc_cb, priv, priv, true); case TC_SETUP_FT: return flow_block_cb_setup_simple(type_data, &mlx5e_rep_block_ft_cb_list, mlx5e_rep_setup_ft_cb, priv, priv, true); default: return -EOPNOTSUPP; } } int mlx5e_rep_tc_init(struct mlx5e_rep_priv *rpriv) { struct mlx5_rep_uplink_priv *uplink_priv = &rpriv->uplink_priv; int err; mutex_init(&uplink_priv->unready_flows_lock); INIT_LIST_HEAD(&uplink_priv->unready_flows); /* init shared tc flow table */ err = mlx5e_tc_esw_init(&uplink_priv->tc_ht); return err; } void mlx5e_rep_tc_cleanup(struct mlx5e_rep_priv *rpriv) { /* delete shared tc flow table */ mlx5e_tc_esw_cleanup(&rpriv->uplink_priv.tc_ht); mutex_destroy(&rpriv->uplink_priv.unready_flows_lock); } void mlx5e_rep_tc_enable(struct mlx5e_priv *priv) { struct mlx5e_rep_priv *rpriv = priv->ppriv; INIT_WORK(&rpriv->uplink_priv.reoffload_flows_work, mlx5e_tc_reoffload_flows_work); } void mlx5e_rep_tc_disable(struct mlx5e_priv *priv) { struct mlx5e_rep_priv *rpriv = priv->ppriv; cancel_work_sync(&rpriv->uplink_priv.reoffload_flows_work); } int mlx5e_rep_tc_event_port_affinity(struct mlx5e_priv *priv) { struct mlx5e_rep_priv *rpriv = priv->ppriv; queue_work(priv->wq, &rpriv->uplink_priv.reoffload_flows_work); return NOTIFY_OK; } static struct mlx5e_rep_indr_block_priv * mlx5e_rep_indr_block_priv_lookup(struct mlx5e_rep_priv *rpriv, struct net_device *netdev) { struct mlx5e_rep_indr_block_priv *cb_priv; /* All callback list access should be protected by RTNL. */ ASSERT_RTNL(); list_for_each_entry(cb_priv, &rpriv->uplink_priv.tc_indr_block_priv_list, list) if (cb_priv->netdev == netdev) return cb_priv; return NULL; } static int mlx5e_rep_indr_offload(struct net_device *netdev, struct flow_cls_offload *flower, struct mlx5e_rep_indr_block_priv *indr_priv, unsigned long flags) { struct mlx5e_priv *priv = netdev_priv(indr_priv->rpriv->netdev); int err = 0; switch (flower->command) { case FLOW_CLS_REPLACE: err = mlx5e_configure_flower(netdev, priv, flower, flags); break; case FLOW_CLS_DESTROY: err = mlx5e_delete_flower(netdev, priv, flower, flags); break; case FLOW_CLS_STATS: err = mlx5e_stats_flower(netdev, priv, flower, flags); break; default: err = -EOPNOTSUPP; } return err; } static int mlx5e_rep_indr_setup_tc_cb(enum tc_setup_type type, void *type_data, void *indr_priv) { unsigned long flags = MLX5_TC_FLAG(EGRESS) | MLX5_TC_FLAG(ESW_OFFLOAD); struct mlx5e_rep_indr_block_priv *priv = indr_priv; switch (type) { case TC_SETUP_CLSFLOWER: return mlx5e_rep_indr_offload(priv->netdev, type_data, priv, flags); default: return -EOPNOTSUPP; } } static int mlx5e_rep_indr_setup_ft_cb(enum tc_setup_type type, void *type_data, void *indr_priv) { struct mlx5e_rep_indr_block_priv *priv = indr_priv; struct flow_cls_offload *f = type_data; struct flow_cls_offload tmp; struct mlx5e_priv *mpriv; struct mlx5_eswitch *esw; unsigned long flags; int err; mpriv = netdev_priv(priv->rpriv->netdev); esw = mpriv->mdev->priv.eswitch; flags = MLX5_TC_FLAG(EGRESS) | MLX5_TC_FLAG(ESW_OFFLOAD) | MLX5_TC_FLAG(FT_OFFLOAD); switch (type) { case TC_SETUP_CLSFLOWER: memcpy(&tmp, f, sizeof(*f)); /* Re-use tc offload path by moving the ft flow to the * reserved ft chain. * * FT offload can use prio range [0, INT_MAX], so we normalize * it to range [1, mlx5_esw_chains_get_prio_range(esw)] * as with tc, where prio 0 isn't supported. * * We only support chain 0 of FT offload. */ if (!mlx5_chains_prios_supported(esw_chains(esw)) || tmp.common.prio >= mlx5_chains_get_prio_range(esw_chains(esw)) || tmp.common.chain_index) return -EOPNOTSUPP; tmp.common.chain_index = mlx5_chains_get_nf_ft_chain(esw_chains(esw)); tmp.common.prio++; err = mlx5e_rep_indr_offload(priv->netdev, &tmp, priv, flags); memcpy(&f->stats, &tmp.stats, sizeof(f->stats)); return err; default: return -EOPNOTSUPP; } } static void mlx5e_rep_indr_block_unbind(void *cb_priv) { struct mlx5e_rep_indr_block_priv *indr_priv = cb_priv; list_del(&indr_priv->list); kfree(indr_priv); } static LIST_HEAD(mlx5e_block_cb_list); static int mlx5e_rep_indr_setup_block(struct net_device *netdev, struct Qdisc *sch, struct mlx5e_rep_priv *rpriv, struct flow_block_offload *f, flow_setup_cb_t *setup_cb, void *data, void (*cleanup)(struct flow_block_cb *block_cb)) { struct mlx5e_priv *priv = netdev_priv(rpriv->netdev); struct mlx5e_rep_indr_block_priv *indr_priv; struct flow_block_cb *block_cb; if (!mlx5e_tc_tun_device_to_offload(priv, netdev) && !(is_vlan_dev(netdev) && vlan_dev_real_dev(netdev) == rpriv->netdev)) return -EOPNOTSUPP; if (f->binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS) return -EOPNOTSUPP; f->unlocked_driver_cb = true; f->driver_block_list = &mlx5e_block_cb_list; switch (f->command) { case FLOW_BLOCK_BIND: indr_priv = mlx5e_rep_indr_block_priv_lookup(rpriv, netdev); if (indr_priv) return -EEXIST; indr_priv = kmalloc(sizeof(*indr_priv), GFP_KERNEL); if (!indr_priv) return -ENOMEM; indr_priv->netdev = netdev; indr_priv->rpriv = rpriv; list_add(&indr_priv->list, &rpriv->uplink_priv.tc_indr_block_priv_list); block_cb = flow_indr_block_cb_alloc(setup_cb, indr_priv, indr_priv, mlx5e_rep_indr_block_unbind, f, netdev, sch, data, rpriv, cleanup); if (IS_ERR(block_cb)) { list_del(&indr_priv->list); kfree(indr_priv); return PTR_ERR(block_cb); } flow_block_cb_add(block_cb, f); list_add_tail(&block_cb->driver_list, &mlx5e_block_cb_list); return 0; case FLOW_BLOCK_UNBIND: indr_priv = mlx5e_rep_indr_block_priv_lookup(rpriv, netdev); if (!indr_priv) return -ENOENT; block_cb = flow_block_cb_lookup(f->block, setup_cb, indr_priv); if (!block_cb) return -ENOENT; flow_indr_block_cb_remove(block_cb, f); list_del(&block_cb->driver_list); return 0; default: return -EOPNOTSUPP; } return 0; } static int mlx5e_rep_indr_setup_cb(struct net_device *netdev, struct Qdisc *sch, void *cb_priv, enum tc_setup_type type, void *type_data, void *data, void (*cleanup)(struct flow_block_cb *block_cb)) { switch (type) { case TC_SETUP_BLOCK: return mlx5e_rep_indr_setup_block(netdev, sch, cb_priv, type_data, mlx5e_rep_indr_setup_tc_cb, data, cleanup); case TC_SETUP_FT: return mlx5e_rep_indr_setup_block(netdev, sch, cb_priv, type_data, mlx5e_rep_indr_setup_ft_cb, data, cleanup); default: return -EOPNOTSUPP; } } int mlx5e_rep_tc_netdevice_event_register(struct mlx5e_rep_priv *rpriv) { struct mlx5_rep_uplink_priv *uplink_priv = &rpriv->uplink_priv; /* init indirect block notifications */ INIT_LIST_HEAD(&uplink_priv->tc_indr_block_priv_list); return flow_indr_dev_register(mlx5e_rep_indr_setup_cb, rpriv); } void mlx5e_rep_tc_netdevice_event_unregister(struct mlx5e_rep_priv *rpriv) { flow_indr_dev_unregister(mlx5e_rep_indr_setup_cb, rpriv, mlx5e_rep_indr_block_unbind); } #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) 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) { WARN_ON_ONCE(true); 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 tun_dev so we do dev_put() after datapath */ tc_priv->tun_dev = dev; skb->dev = dev; return true; } #endif /* CONFIG_NET_TC_SKB_EXT */ bool mlx5e_rep_tc_update_skb(struct mlx5_cqe64 *cqe, struct sk_buff *skb, struct mlx5e_tc_update_priv *tc_priv) { #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) u32 chain = 0, reg_c0, reg_c1, tunnel_id, zone_restore_id; struct mlx5_rep_uplink_priv *uplink_priv; struct mlx5e_rep_priv *uplink_rpriv; struct tc_skb_ext *tc_skb_ext; struct mlx5_eswitch *esw; struct mlx5e_priv *priv; int err; reg_c0 = (be32_to_cpu(cqe->sop_drop_qpn) & MLX5E_TC_FLOW_ID_MASK); if (reg_c0 == MLX5_FS_DEFAULT_FLOW_TAG) reg_c0 = 0; reg_c1 = be32_to_cpu(cqe->ft_metadata); if (!reg_c0) return true; /* If reg_c0 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 = mlx5_get_chain_for_tag(esw_chains(esw), reg_c0, &chain); if (err) { netdev_dbg(priv->netdev, "Couldn't find chain for chain tag: %d, err: %d\n", reg_c0, err); return false; } if (chain) { tc_skb_ext = skb_ext_add(skb, TC_SKB_EXT); if (!tc_skb_ext) { WARN_ON(1); return false; } tc_skb_ext->chain = chain; zone_restore_id = reg_c1 & ZONE_RESTORE_MAX; 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; } tunnel_id = reg_c1 >> REG_MAPPING_SHIFT(TUNNEL_TO_REG); return mlx5e_restore_tunnel(priv, skb, tc_priv, tunnel_id); #endif /* CONFIG_NET_TC_SKB_EXT */ return true; } void mlx5_rep_tc_post_napi_receive(struct mlx5e_tc_update_priv *tc_priv) { if (tc_priv->tun_dev) dev_put(tc_priv->tun_dev); }