From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-9.7 required=3.0 tests=HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_PATCH,MAILING_LIST_MULTI,SIGNED_OFF_BY,SPF_HELO_NONE,SPF_PASS, UNPARSEABLE_RELAY,USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 5AA16C33CB6 for ; Tue, 21 Jan 2020 16:17:03 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id 3A607217F4 for ; Tue, 21 Jan 2020 16:17:03 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1729459AbgAUQQ7 (ORCPT ); Tue, 21 Jan 2020 11:16:59 -0500 Received: from mail-il-dmz.mellanox.com ([193.47.165.129]:43530 "EHLO mellanox.co.il" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1729360AbgAUQQ5 (ORCPT ); Tue, 21 Jan 2020 11:16:57 -0500 Received: from Internal Mail-Server by MTLPINE1 (envelope-from paulb@mellanox.com) with ESMTPS (AES256-SHA encrypted); 21 Jan 2020 18:16:54 +0200 Received: from reg-r-vrt-019-120.mtr.labs.mlnx (reg-r-vrt-019-120.mtr.labs.mlnx [10.213.19.120]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id 00LGGrX8008966; Tue, 21 Jan 2020 18:16:54 +0200 From: Paul Blakey To: Paul Blakey , Saeed Mahameed , Oz Shlomo , Jakub Kicinski , Vlad Buslov , David Miller , "netdev@vger.kernel.org" , Jiri Pirko Subject: [PATCH net-next-mlx5 13/13] net/mlx5e: Restore tunnel metadata on miss Date: Tue, 21 Jan 2020 18:16:22 +0200 Message-Id: <1579623382-6934-14-git-send-email-paulb@mellanox.com> X-Mailer: git-send-email 1.8.4.3 In-Reply-To: <1579623382-6934-1-git-send-email-paulb@mellanox.com> References: <1579623382-6934-1-git-send-email-paulb@mellanox.com> Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org In tunnel and chains setup, we decapsulate the packets on first chain hop, if we miss on later chains, the packet will comes up without tunnel header, so it won't be taken by the tunnel device automatically, which fills the tunnel metadata, and further tc tunnel matches won't work. To fix that: On miss, we get the tunnel mapping id, which was set on the chain 0 rule that decapsulated the packet. This rule matched the tunnel outer headers. From the tunnel mapping id, we get to this tunnel matches and restore the equivalent tunnel info metadata dst on the skb. We also set the skb->dev to the relevant device (tunnel device). Now further tc processing can be done on the relevant device. Signed-off-by: Paul Blakey Reviewed-by: Roi Dayan Reviewed-by: Oz Shlomo Reviewed-by: Mark Bloch --- drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 10 ++- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 108 ++++++++++++++++++++++-- drivers/net/ethernet/mellanox/mlx5/core/en_tc.h | 9 +- 3 files changed, 115 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 4402a53..59d01a8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -1191,6 +1191,7 @@ void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_eswitch_rep *rep = rpriv->rep; + struct mlx5e_tc_update_priv tc_priv = {}; struct mlx5_wq_cyc *wq = &rq->wqe.wq; struct mlx5e_wqe_frag_info *wi; struct sk_buff *skb; @@ -1223,11 +1224,13 @@ void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) if (rep->vlan && skb_vlan_tag_present(skb)) skb_vlan_pop(skb); - if (!mlx5e_tc_rep_update_skb(cqe, skb)) + if (!mlx5e_tc_rep_update_skb(cqe, skb, &tc_priv)) goto free_wqe; napi_gro_receive(rq->cq.napi, skb); + mlx5_tc_rep_post_napi_receive(&tc_priv); + free_wqe: mlx5e_free_rx_wqe(rq, wi, true); wq_cyc_pop: @@ -1244,6 +1247,7 @@ void mlx5e_handle_rx_cqe_mpwrq_rep(struct mlx5e_rq *rq, u32 wqe_offset = stride_ix << rq->mpwqe.log_stride_sz; u32 head_offset = wqe_offset & (PAGE_SIZE - 1); u32 page_idx = wqe_offset >> PAGE_SHIFT; + struct mlx5e_tc_update_priv tc_priv = {}; struct mlx5e_rx_wqe_ll *wqe; struct mlx5_wq_ll *wq; struct sk_buff *skb; @@ -1276,11 +1280,13 @@ void mlx5e_handle_rx_cqe_mpwrq_rep(struct mlx5e_rq *rq, mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb); - if (!mlx5e_tc_rep_update_skb(cqe, skb)) + if (!mlx5e_tc_rep_update_skb(cqe, skb, &tc_priv)) goto mpwrq_cqe_out; napi_gro_receive(rq->cq.napi, skb); + mlx5_tc_rep_post_napi_receive(&tc_priv); + mpwrq_cqe_out: if (likely(wi->consumed_strides < rq->mpwqe.num_strides)) return; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 9f8ff40..d8d028f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -4587,19 +4587,100 @@ void mlx5e_tc_reoffload_flows_work(struct work_struct *work) mutex_unlock(&rpriv->unready_flows_lock); } +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 flow_dissector_key_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; + } + } + + tun_dst = tun_rx_dst(enc_opts.len); + if (!tun_dst) { + WARN_ON_ONCE(true); + return false; + } + + ip_tunnel_key_init(&tun_dst->u.tun_info.key, + key.enc_ipv4.src, key.enc_ipv4.dst, + key.enc_ip.tos, key.enc_ip.ttl, + 0, /* label */ + key.enc_tp.src, key.enc_tp.dst, + key32_to_tunnel_id(key.enc_key_id.keyid), + TUNNEL_KEY); + + if (enc_opts.len) + ip_tunnel_info_opts_set(&tun_dst->u.tun_info, enc_opts.data, + enc_opts.len, enc_opts.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; +} + bool mlx5e_tc_rep_update_skb(struct mlx5_cqe64 *cqe, - struct sk_buff *skb) + 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; struct tc_skb_ext *tc_skb_ext; struct mlx5_eswitch *esw; struct mlx5e_priv *priv; - u32 chain = 0, reg_c0; + int tunnel_moffset; 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->imm_inval_pkey); if (!reg_c0) return true; @@ -4615,17 +4696,26 @@ bool mlx5e_tc_rep_update_skb(struct mlx5_cqe64 *cqe, return false; } - if (!chain) - return true; + if (chain) { + tc_skb_ext = skb_ext_add(skb, TC_SKB_EXT); + if (!tc_skb_ext) { + WARN_ON(1); + return false; + } - tc_skb_ext = skb_ext_add(skb, TC_SKB_EXT); - if (!tc_skb_ext) { - WARN_ON_ONCE(1); - return false; + tc_skb_ext->chain = chain; } - tc_skb_ext->chain = chain; + tunnel_moffset = mlx5e_tc_attr_to_reg_mappings[TUNNEL_TO_REG].moffset; + tunnel_id = reg_c1 >> (8 * tunnel_moffset); + return mlx5e_restore_tunnel(priv, skb, tc_priv, tunnel_id); #endif /* CONFIG_NET_TC_SKB_EXT */ return true; } + +void mlx5_tc_rep_post_napi_receive(struct mlx5e_tc_update_priv *tc_priv) +{ + if (tc_priv->tun_dev) + dev_put(tc_priv->tun_dev); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h index 2fab76b..21cbde4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h @@ -109,7 +109,14 @@ struct mlx5e_tc_attr_to_reg_mapping { bool mlx5e_is_valid_eswitch_fwd_dev(struct mlx5e_priv *priv, struct net_device *out_dev); -bool mlx5e_tc_rep_update_skb(struct mlx5_cqe64 *cqe, struct sk_buff *skb); +struct mlx5e_tc_update_priv { + struct net_device *tun_dev; +}; + +bool mlx5e_tc_rep_update_skb(struct mlx5_cqe64 *cqe, struct sk_buff *skb, + struct mlx5e_tc_update_priv *tc_priv); + +void mlx5_tc_rep_post_napi_receive(struct mlx5e_tc_update_priv *tc_priv); struct mlx5e_tc_mod_hdr_acts { int num_actions; -- 1.8.3.1