From patchwork Tue Dec 29 13:24:05 2015 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Matan Barak X-Patchwork-Id: 7929981 Return-Path: X-Original-To: patchwork-linux-rdma@patchwork.kernel.org Delivered-To: patchwork-parsemail@patchwork1.web.kernel.org Received: from mail.kernel.org (mail.kernel.org [198.145.29.136]) by patchwork1.web.kernel.org (Postfix) with ESMTP id 0E6549F32E for ; Tue, 29 Dec 2015 13:27:29 +0000 (UTC) Received: from mail.kernel.org (localhost [127.0.0.1]) by mail.kernel.org (Postfix) with ESMTP id E9ED020221 for ; Tue, 29 Dec 2015 13:27:27 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id D4CA020225 for ; Tue, 29 Dec 2015 13:27:26 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752982AbbL2N10 (ORCPT ); Tue, 29 Dec 2015 08:27:26 -0500 Received: from [193.47.165.129] ([193.47.165.129]:40963 "EHLO mellanox.co.il" rhost-flags-FAIL-FAIL-OK-FAIL) by vger.kernel.org with ESMTP id S1752655AbbL2N1Z (ORCPT ); Tue, 29 Dec 2015 08:27:25 -0500 Received: from Internal Mail-Server by MTLPINE1 (envelope-from matanb@mellanox.com) with ESMTPS (AES256-SHA encrypted); 29 Dec 2015 15:26:43 +0200 Received: from rsws33.mtr.labs.mlnx (dev-r-vrt-064.mtr.labs.mlnx [10.212.64.1]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id tBTDQf4O008100; Tue, 29 Dec 2015 15:26:42 +0200 From: Matan Barak To: Doug Ledford Cc: linux-rdma@vger.kernel.org, Yishai Hadas , Moni Shoua , Majd Dibbiny , Or Gerlitz Subject: [PATCH for-next 5/7] IB/mlx4: Enable send of RoCE QP1 packets with IP/UDP headers Date: Tue, 29 Dec 2015 15:24:05 +0200 Message-Id: <1451395447-5198-6-git-send-email-matanb@mellanox.com> X-Mailer: git-send-email 2.1.0 In-Reply-To: <1451395447-5198-1-git-send-email-matanb@mellanox.com> References: <1451395447-5198-1-git-send-email-matanb@mellanox.com> Sender: linux-rdma-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-rdma@vger.kernel.org X-Spam-Status: No, score=-6.9 required=5.0 tests=BAYES_00, RCVD_IN_DNSWL_HI, RP_MATCHES_RCVD, UNPARSEABLE_RELAY autolearn=ham version=3.3.1 X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on mail.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP From: Moni Shoua RoCEv2 packets are sent over IP/UDP protocols. The mlx4 driver uses a type of RAW QP to send packets for QP1 and therefore needs to build the network headers below BTH in software. This patche adds option to build QP1 packets with IP and UDP headers if RoCEv2 is requested. Signed-off-by: Moni Shoua --- drivers/infiniband/hw/mlx4/qp.c | 86 ++++++++++++++++++++++++++--------------- 1 file changed, 54 insertions(+), 32 deletions(-) diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index c0dee79..8485602 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -32,6 +32,8 @@ */ #include +#include +#include #include #include #include @@ -2282,16 +2284,7 @@ static int build_sriov_qp0_header(struct mlx4_ib_sqp *sqp, return 0; } -static void mlx4_u64_to_smac(u8 *dst_mac, u64 src_mac) -{ - int i; - - for (i = ETH_ALEN; i; i--) { - dst_mac[i - 1] = src_mac & 0xff; - src_mac >>= 8; - } -} - +#define MLX4_ROCEV2_QP1_SPORT 0xC000 static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_ud_wr *wr, void *wqe, unsigned *mlx_seg_len) { @@ -2311,6 +2304,8 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_ud_wr *wr, bool is_eth; bool is_vlan = false; bool is_grh; + bool is_udp = false; + int ip_version = 0; send_size = 0; for (i = 0; i < wr->wr.num_sge; ++i) @@ -2319,6 +2314,8 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_ud_wr *wr, is_eth = rdma_port_get_link_layer(sqp->qp.ibqp.device, sqp->qp.port) == IB_LINK_LAYER_ETHERNET; is_grh = mlx4_ib_ah_grh_present(ah); if (is_eth) { + struct ib_gid_attr gid_attr; + if (mlx4_is_mfunc(to_mdev(ib_dev)->dev)) { /* When multi-function is enabled, the ib_core gid * indexes don't necessarily match the hw ones, so @@ -2329,23 +2326,36 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_ud_wr *wr, if (err) return err; } else { - err = ib_get_cached_gid(ib_dev, + err = ib_get_cached_gid(sqp->qp.ibqp.device, be32_to_cpu(ah->av.ib.port_pd) >> 24, ah->av.ib.gid_index, &sgid, - NULL); - if (!err && !memcmp(&sgid, &zgid, sizeof(sgid))) - err = -ENOENT; - if (err) + &gid_attr); + if (!err) { + if (gid_attr.ndev) + dev_put(gid_attr.ndev); + if (!memcmp(&sgid, &zgid, sizeof(sgid))) + err = -ENOENT; + } + if (!err) { + is_udp = gid_attr.gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP; + if (is_udp) { + if (ipv6_addr_v4mapped((struct in6_addr *)&sgid)) + ip_version = 4; + else + ip_version = 6; + is_grh = false; + } + } else { return err; + } } - if (ah->av.eth.vlan != cpu_to_be16(0xffff)) { vlan = be16_to_cpu(ah->av.eth.vlan) & 0x0fff; is_vlan = 1; } } err = ib_ud_header_init(send_size, !is_eth, is_eth, is_vlan, is_grh, - 0, 0, 0, &sqp->ud_header); + ip_version, is_udp, 0, &sqp->ud_header); if (err) return err; @@ -2356,7 +2366,7 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_ud_wr *wr, sqp->ud_header.lrh.source_lid = cpu_to_be16(ah->av.ib.g_slid & 0x7f); } - if (is_grh) { + if (is_grh || (ip_version == 6)) { sqp->ud_header.grh.traffic_class = (be32_to_cpu(ah->av.ib.sl_tclass_flowlabel) >> 20) & 0xff; sqp->ud_header.grh.flow_label = @@ -2385,6 +2395,25 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_ud_wr *wr, ah->av.ib.dgid, 16); } + if (ip_version == 4) { + sqp->ud_header.ip4.tos = + (be32_to_cpu(ah->av.ib.sl_tclass_flowlabel) >> 20) & 0xff; + sqp->ud_header.ip4.id = 0; + sqp->ud_header.ip4.frag_off = htons(IP_DF); + sqp->ud_header.ip4.ttl = ah->av.eth.hop_limit; + + memcpy(&sqp->ud_header.ip4.saddr, + sgid.raw + 12, 4); + memcpy(&sqp->ud_header.ip4.daddr, ah->av.ib.dgid + 12, 4); + sqp->ud_header.ip4.check = ib_ud_ip4_csum(&sqp->ud_header); + } + + if (is_udp) { + sqp->ud_header.udp.dport = htons(ROCE_V2_UDP_DPORT); + sqp->ud_header.udp.sport = htons(MLX4_ROCEV2_QP1_SPORT); + sqp->ud_header.udp.csum = 0; + } + mlx->flags &= cpu_to_be32(MLX4_WQE_CTRL_CQ_UPDATE); if (!is_eth) { @@ -2413,34 +2442,27 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_ud_wr *wr, if (is_eth) { struct in6_addr in6; - + u16 ether_type; u16 pcp = (be32_to_cpu(ah->av.ib.sl_tclass_flowlabel) >> 29) << 13; + ether_type = (!is_udp) ? MLX4_IB_IBOE_ETHERTYPE : + (ip_version == 4 ? ETH_P_IP : ETH_P_IPV6); + mlx->sched_prio = cpu_to_be16(pcp); + ether_addr_copy(sqp->ud_header.eth.smac_h, ah->av.eth.s_mac); memcpy(sqp->ud_header.eth.dmac_h, ah->av.eth.mac, 6); - /* FIXME: cache smac value? */ memcpy(&ctrl->srcrb_flags16[0], ah->av.eth.mac, 2); memcpy(&ctrl->imm, ah->av.eth.mac + 2, 4); memcpy(&in6, sgid.raw, sizeof(in6)); - if (!mlx4_is_mfunc(to_mdev(ib_dev)->dev)) { - u64 mac = atomic64_read(&to_mdev(ib_dev)->iboe.mac[sqp->qp.port - 1]); - u8 smac[ETH_ALEN]; - - mlx4_u64_to_smac(smac, mac); - memcpy(sqp->ud_header.eth.smac_h, smac, ETH_ALEN); - } else { - /* use the src mac of the tunnel */ - memcpy(sqp->ud_header.eth.smac_h, ah->av.eth.s_mac, ETH_ALEN); - } if (!memcmp(sqp->ud_header.eth.smac_h, sqp->ud_header.eth.dmac_h, 6)) mlx->flags |= cpu_to_be32(MLX4_WQE_CTRL_FORCE_LOOPBACK); if (!is_vlan) { - sqp->ud_header.eth.type = cpu_to_be16(MLX4_IB_IBOE_ETHERTYPE); + sqp->ud_header.eth.type = cpu_to_be16(ether_type); } else { - sqp->ud_header.vlan.type = cpu_to_be16(MLX4_IB_IBOE_ETHERTYPE); + sqp->ud_header.vlan.type = cpu_to_be16(ether_type); sqp->ud_header.vlan.tag = cpu_to_be16(vlan | pcp); } } else {