From patchwork Wed Jan 10 06:39:50 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Lijun Ou X-Patchwork-Id: 10154043 X-Patchwork-Delegate: jgg@ziepe.ca Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork.web.codeaurora.org (Postfix) with ESMTP id 7CFEA602D8 for ; Wed, 10 Jan 2018 06:10:49 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 6D40427F9F for ; Wed, 10 Jan 2018 06:10:49 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 616E7280CF; Wed, 10 Jan 2018 06:10:49 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-6.9 required=2.0 tests=BAYES_00,RCVD_IN_DNSWL_HI autolearn=ham version=3.3.1 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 506F327F82 for ; Wed, 10 Jan 2018 06:10:48 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S933493AbeAJGKq (ORCPT ); Wed, 10 Jan 2018 01:10:46 -0500 Received: from szxga04-in.huawei.com ([45.249.212.190]:3712 "EHLO huawei.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S933424AbeAJGKp (ORCPT ); Wed, 10 Jan 2018 01:10:45 -0500 Received: from DGGEMS403-HUB.china.huawei.com (unknown [172.30.72.58]) by Forcepoint Email with ESMTP id C432D35DFDCC0; Wed, 10 Jan 2018 14:10:30 +0800 (CST) Received: from linux-ioko.site (10.71.200.31) by DGGEMS403-HUB.china.huawei.com (10.3.19.203) with Microsoft SMTP Server id 14.3.361.1; Wed, 10 Jan 2018 14:10:28 +0800 From: Lijun Ou To: , CC: , Subject: [PATCH V2 for-next 4/7] RDMA/hns: Fill sq wqe context of ud type in hip08 Date: Wed, 10 Jan 2018 14:39:50 +0800 Message-ID: <1515566393-63888-5-git-send-email-oulijun@huawei.com> X-Mailer: git-send-email 1.9.1 In-Reply-To: <1515566393-63888-1-git-send-email-oulijun@huawei.com> References: <1515566393-63888-1-git-send-email-oulijun@huawei.com> MIME-Version: 1.0 X-Originating-IP: [10.71.200.31] X-CFilter-Loop: Reflected Sender: linux-rdma-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-rdma@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP This patch mainly configure the fileds of sq wqe of ud type when posting wr of gsi qp type. Signed-off-by: Lijun Ou Signed-off-by: Yixian Liu Signed-off-by: Wei Hu (Xavier) --- V1->V2: - return errno code directly and delete unnecessary initialized value of ret from Leon Romanvosky's advice. - Add necessary option for free sq lock when qp is illegal qp type. V1: - The initial submit --- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 446 +++++++++++++++++++---------- drivers/infiniband/hw/hns/hns_roce_hw_v2.h | 84 ++++++ 2 files changed, 385 insertions(+), 145 deletions(-) diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index e53cd7d..cb3ac54 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -51,26 +51,99 @@ static void set_data_seg_v2(struct hns_roce_v2_wqe_data_seg *dseg, dseg->len = cpu_to_le32(sg->length); } +static int set_rwqe_data_seg(struct ib_qp *ibqp, struct ib_send_wr *wr, + struct hns_roce_v2_rc_send_wqe *rc_sq_wqe, + void *wqe, unsigned int *sge_ind, + struct ib_send_wr **bad_wr) +{ + struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device); + struct hns_roce_v2_wqe_data_seg *dseg = wqe; + struct hns_roce_qp *qp = to_hr_qp(ibqp); + int i; + + if (wr->send_flags & IB_SEND_INLINE && wr->num_sge) { + if (rc_sq_wqe->msg_len > hr_dev->caps.max_sq_inline) { + *bad_wr = wr; + dev_err(hr_dev->dev, "inline len(1-%d)=%d, illegal", + rc_sq_wqe->msg_len, hr_dev->caps.max_sq_inline); + return -EINVAL; + } + + for (i = 0; i < wr->num_sge; i++) { + memcpy(wqe, ((void *)wr->sg_list[i].addr), + wr->sg_list[i].length); + wqe += wr->sg_list[i].length; + } + + roce_set_bit(rc_sq_wqe->byte_4, V2_RC_SEND_WQE_BYTE_4_INLINE_S, + 1); + } else { + if (wr->num_sge <= 2) { + for (i = 0; i < wr->num_sge; i++) { + if (likely(wr->sg_list[i].length)) { + set_data_seg_v2(dseg, wr->sg_list + i); + dseg++; + } + } + } else { + roce_set_field(rc_sq_wqe->byte_20, + V2_RC_SEND_WQE_BYTE_20_MSG_START_SGE_IDX_M, + V2_RC_SEND_WQE_BYTE_20_MSG_START_SGE_IDX_S, + (*sge_ind) & (qp->sge.sge_cnt - 1)); + + for (i = 0; i < 2; i++) { + if (likely(wr->sg_list[i].length)) { + set_data_seg_v2(dseg, wr->sg_list + i); + dseg++; + } + } + + dseg = get_send_extend_sge(qp, + (*sge_ind) & (qp->sge.sge_cnt - 1)); + + for (i = 0; i < wr->num_sge - 2; i++) { + if (likely(wr->sg_list[i + 2].length)) { + set_data_seg_v2(dseg, + wr->sg_list + 2 + i); + dseg++; + (*sge_ind)++; + } + } + } + + roce_set_field(rc_sq_wqe->byte_16, + V2_RC_SEND_WQE_BYTE_16_SGE_NUM_M, + V2_RC_SEND_WQE_BYTE_16_SGE_NUM_S, wr->num_sge); + } + + return 0; +} + static int hns_roce_v2_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, struct ib_send_wr **bad_wr) { struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device); + struct hns_roce_ah *ah = to_hr_ah(ud_wr(wr)->ah); + struct hns_roce_v2_ud_send_wqe *ud_sq_wqe; struct hns_roce_v2_rc_send_wqe *rc_sq_wqe; struct hns_roce_qp *qp = to_hr_qp(ibqp); struct hns_roce_v2_wqe_data_seg *dseg; struct device *dev = hr_dev->dev; struct hns_roce_v2_db sq_db; unsigned int sge_ind = 0; - unsigned int wqe_sz = 0; unsigned int owner_bit; unsigned long flags; unsigned int ind; void *wqe = NULL; + bool loopback; int ret = 0; + u8 *smac; int nreq; int i; - if (unlikely(ibqp->qp_type != IB_QPT_RC)) { + if (unlikely(ibqp->qp_type != IB_QPT_RC && + ibqp->qp_type != IB_QPT_GSI && + ibqp->qp_type != IB_QPT_UD)) { dev_err(dev, "Not supported QP(0x%x)type!\n", ibqp->qp_type); *bad_wr = NULL; return -EOPNOTSUPP; @@ -107,172 +180,255 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, wr->wr_id; owner_bit = ~(qp->sq.head >> ilog2(qp->sq.wqe_cnt)) & 0x1; - rc_sq_wqe = wqe; - memset(rc_sq_wqe, 0, sizeof(*rc_sq_wqe)); - for (i = 0; i < wr->num_sge; i++) - rc_sq_wqe->msg_len += wr->sg_list[i].length; - rc_sq_wqe->inv_key_immtdata = send_ieth(wr); + /* Corresponding to the QP type, wqe process separately */ + if (ibqp->qp_type == IB_QPT_GSI) { + ud_sq_wqe = wqe; + memset(ud_sq_wqe, 0, sizeof(*ud_sq_wqe)); + + roce_set_field(ud_sq_wqe->dmac, V2_UD_SEND_WQE_DMAC_0_M, + V2_UD_SEND_WQE_DMAC_0_S, ah->av.mac[0]); + roce_set_field(ud_sq_wqe->dmac, V2_UD_SEND_WQE_DMAC_1_M, + V2_UD_SEND_WQE_DMAC_1_S, ah->av.mac[1]); + roce_set_field(ud_sq_wqe->dmac, V2_UD_SEND_WQE_DMAC_2_M, + V2_UD_SEND_WQE_DMAC_2_S, ah->av.mac[2]); + roce_set_field(ud_sq_wqe->dmac, V2_UD_SEND_WQE_DMAC_3_M, + V2_UD_SEND_WQE_DMAC_3_S, ah->av.mac[3]); + roce_set_field(ud_sq_wqe->byte_48, + V2_UD_SEND_WQE_BYTE_48_DMAC_4_M, + V2_UD_SEND_WQE_BYTE_48_DMAC_4_S, + ah->av.mac[4]); + roce_set_field(ud_sq_wqe->byte_48, + V2_UD_SEND_WQE_BYTE_48_DMAC_5_M, + V2_UD_SEND_WQE_BYTE_48_DMAC_5_S, + ah->av.mac[5]); + + /* MAC loopback */ + smac = (u8 *)hr_dev->dev_addr[qp->port]; + loopback = ether_addr_equal_unaligned(ah->av.mac, + smac) ? 1 : 0; + + roce_set_bit(ud_sq_wqe->byte_40, + V2_UD_SEND_WQE_BYTE_40_LBI_S, loopback); + + roce_set_field(ud_sq_wqe->byte_4, + V2_UD_SEND_WQE_BYTE_4_OPCODE_M, + V2_UD_SEND_WQE_BYTE_4_OPCODE_S, + HNS_ROCE_V2_WQE_OP_SEND); - roce_set_bit(rc_sq_wqe->byte_4, V2_RC_SEND_WQE_BYTE_4_FENCE_S, - (wr->send_flags & IB_SEND_FENCE) ? 1 : 0); + for (i = 0; i < wr->num_sge; i++) + ud_sq_wqe->msg_len += wr->sg_list[i].length; - roce_set_bit(rc_sq_wqe->byte_4, V2_RC_SEND_WQE_BYTE_4_SE_S, - (wr->send_flags & IB_SEND_SOLICITED) ? 1 : 0); + ud_sq_wqe->immtdata = send_ieth(wr); - roce_set_bit(rc_sq_wqe->byte_4, V2_RC_SEND_WQE_BYTE_4_CQE_S, - (wr->send_flags & IB_SEND_SIGNALED) ? 1 : 0); + /* Set sig attr */ + roce_set_bit(ud_sq_wqe->byte_4, + V2_UD_SEND_WQE_BYTE_4_CQE_S, + (wr->send_flags & IB_SEND_SIGNALED) ? 1 : 0); - roce_set_bit(rc_sq_wqe->byte_4, V2_RC_SEND_WQE_BYTE_4_OWNER_S, - owner_bit); + /* Set se attr */ + roce_set_bit(ud_sq_wqe->byte_4, + V2_UD_SEND_WQE_BYTE_4_SE_S, + (wr->send_flags & IB_SEND_SOLICITED) ? 1 : 0); - switch (wr->opcode) { - case IB_WR_RDMA_READ: - roce_set_field(rc_sq_wqe->byte_4, - V2_RC_SEND_WQE_BYTE_4_OPCODE_M, - V2_RC_SEND_WQE_BYTE_4_OPCODE_S, - HNS_ROCE_V2_WQE_OP_RDMA_READ); - rc_sq_wqe->rkey = cpu_to_le32(rdma_wr(wr)->rkey); - rc_sq_wqe->va = cpu_to_le64(rdma_wr(wr)->remote_addr); - break; - case IB_WR_RDMA_WRITE: - roce_set_field(rc_sq_wqe->byte_4, - V2_RC_SEND_WQE_BYTE_4_OPCODE_M, - V2_RC_SEND_WQE_BYTE_4_OPCODE_S, - HNS_ROCE_V2_WQE_OP_RDMA_WRITE); - rc_sq_wqe->rkey = cpu_to_le32(rdma_wr(wr)->rkey); - rc_sq_wqe->va = cpu_to_le64(rdma_wr(wr)->remote_addr); - break; - case IB_WR_RDMA_WRITE_WITH_IMM: - roce_set_field(rc_sq_wqe->byte_4, + roce_set_bit(ud_sq_wqe->byte_4, + V2_UD_SEND_WQE_BYTE_4_OWNER_S, owner_bit); + + roce_set_field(ud_sq_wqe->byte_16, + V2_UD_SEND_WQE_BYTE_16_PD_M, + V2_UD_SEND_WQE_BYTE_16_PD_S, + to_hr_pd(ibqp->pd)->pdn); + + roce_set_field(ud_sq_wqe->byte_16, + V2_UD_SEND_WQE_BYTE_16_SGE_NUM_M, + V2_UD_SEND_WQE_BYTE_16_SGE_NUM_S, + wr->num_sge); + + roce_set_field(ud_sq_wqe->byte_20, + V2_UD_SEND_WQE_BYTE_20_MSG_START_SGE_IDX_M, + V2_UD_SEND_WQE_BYTE_20_MSG_START_SGE_IDX_S, + sge_ind & (qp->sge.sge_cnt - 1)); + + roce_set_field(ud_sq_wqe->byte_24, + V2_UD_SEND_WQE_BYTE_24_UDPSPN_M, + V2_UD_SEND_WQE_BYTE_24_UDPSPN_S, 0); + ud_sq_wqe->qkey = + cpu_to_be32(ud_wr(wr)->remote_qkey & 0x80000000) ? + qp->qkey : ud_wr(wr)->remote_qkey; + roce_set_field(ud_sq_wqe->byte_32, + V2_UD_SEND_WQE_BYTE_32_DQPN_M, + V2_UD_SEND_WQE_BYTE_32_DQPN_S, + ud_wr(wr)->remote_qpn); + + roce_set_field(ud_sq_wqe->byte_36, + V2_UD_SEND_WQE_BYTE_36_VLAN_M, + V2_UD_SEND_WQE_BYTE_36_VLAN_S, + ah->av.vlan); + roce_set_field(ud_sq_wqe->byte_36, + V2_UD_SEND_WQE_BYTE_36_HOPLIMIT_M, + V2_UD_SEND_WQE_BYTE_36_HOPLIMIT_S, + ah->av.hop_limit); + roce_set_field(ud_sq_wqe->byte_36, + V2_UD_SEND_WQE_BYTE_36_TCLASS_M, + V2_UD_SEND_WQE_BYTE_36_TCLASS_S, + 0); + roce_set_field(ud_sq_wqe->byte_36, + V2_UD_SEND_WQE_BYTE_36_TCLASS_M, + V2_UD_SEND_WQE_BYTE_36_TCLASS_S, + 0); + roce_set_field(ud_sq_wqe->byte_40, + V2_UD_SEND_WQE_BYTE_40_FLOW_LABEL_M, + V2_UD_SEND_WQE_BYTE_40_FLOW_LABEL_S, 0); + roce_set_field(ud_sq_wqe->byte_40, + V2_UD_SEND_WQE_BYTE_40_SL_M, + V2_UD_SEND_WQE_BYTE_40_SL_S, + ah->av.sl_tclass_flowlabel >> + HNS_ROCE_SL_SHIFT); + roce_set_field(ud_sq_wqe->byte_40, + V2_UD_SEND_WQE_BYTE_40_PORTN_M, + V2_UD_SEND_WQE_BYTE_40_PORTN_S, + qp->port); + + roce_set_field(ud_sq_wqe->byte_48, + V2_UD_SEND_WQE_BYTE_48_SGID_INDX_M, + V2_UD_SEND_WQE_BYTE_48_SGID_INDX_S, + hns_get_gid_index(hr_dev, qp->phy_port, + ah->av.gid_index)); + + memcpy(&ud_sq_wqe->dgid[0], &ah->av.dgid[0], + GID_LEN_V2); + + dseg = get_send_extend_sge(qp, + sge_ind & (qp->sge.sge_cnt - 1)); + for (i = 0; i < wr->num_sge; i++) { + set_data_seg_v2(dseg + i, wr->sg_list + i); + sge_ind++; + } + + ind++; + } else if (ibqp->qp_type == IB_QPT_RC) { + rc_sq_wqe = wqe; + memset(rc_sq_wqe, 0, sizeof(*rc_sq_wqe)); + for (i = 0; i < wr->num_sge; i++) + rc_sq_wqe->msg_len += wr->sg_list[i].length; + + rc_sq_wqe->inv_key_immtdata = send_ieth(wr); + + roce_set_bit(rc_sq_wqe->byte_4, + V2_RC_SEND_WQE_BYTE_4_FENCE_S, + (wr->send_flags & IB_SEND_FENCE) ? 1 : 0); + + roce_set_bit(rc_sq_wqe->byte_4, + V2_RC_SEND_WQE_BYTE_4_SE_S, + (wr->send_flags & IB_SEND_SOLICITED) ? 1 : 0); + + roce_set_bit(rc_sq_wqe->byte_4, + V2_RC_SEND_WQE_BYTE_4_CQE_S, + (wr->send_flags & IB_SEND_SIGNALED) ? 1 : 0); + + roce_set_bit(rc_sq_wqe->byte_4, + V2_RC_SEND_WQE_BYTE_4_OWNER_S, owner_bit); + + switch (wr->opcode) { + case IB_WR_RDMA_READ: + roce_set_field(rc_sq_wqe->byte_4, + V2_RC_SEND_WQE_BYTE_4_OPCODE_M, + V2_RC_SEND_WQE_BYTE_4_OPCODE_S, + HNS_ROCE_V2_WQE_OP_RDMA_READ); + rc_sq_wqe->rkey = + cpu_to_le32(rdma_wr(wr)->rkey); + rc_sq_wqe->va = + cpu_to_le64(rdma_wr(wr)->remote_addr); + break; + case IB_WR_RDMA_WRITE: + roce_set_field(rc_sq_wqe->byte_4, + V2_RC_SEND_WQE_BYTE_4_OPCODE_M, + V2_RC_SEND_WQE_BYTE_4_OPCODE_S, + HNS_ROCE_V2_WQE_OP_RDMA_WRITE); + rc_sq_wqe->rkey = + cpu_to_le32(rdma_wr(wr)->rkey); + rc_sq_wqe->va = + cpu_to_le64(rdma_wr(wr)->remote_addr); + break; + case IB_WR_RDMA_WRITE_WITH_IMM: + roce_set_field(rc_sq_wqe->byte_4, V2_RC_SEND_WQE_BYTE_4_OPCODE_M, V2_RC_SEND_WQE_BYTE_4_OPCODE_S, HNS_ROCE_V2_WQE_OP_RDMA_WRITE_WITH_IMM); - rc_sq_wqe->rkey = cpu_to_le32(rdma_wr(wr)->rkey); - rc_sq_wqe->va = cpu_to_le64(rdma_wr(wr)->remote_addr); - break; - case IB_WR_SEND: - roce_set_field(rc_sq_wqe->byte_4, - V2_RC_SEND_WQE_BYTE_4_OPCODE_M, - V2_RC_SEND_WQE_BYTE_4_OPCODE_S, - HNS_ROCE_V2_WQE_OP_SEND); - break; - case IB_WR_SEND_WITH_INV: - roce_set_field(rc_sq_wqe->byte_4, + rc_sq_wqe->rkey = + cpu_to_le32(rdma_wr(wr)->rkey); + rc_sq_wqe->va = + cpu_to_le64(rdma_wr(wr)->remote_addr); + break; + case IB_WR_SEND: + roce_set_field(rc_sq_wqe->byte_4, + V2_RC_SEND_WQE_BYTE_4_OPCODE_M, + V2_RC_SEND_WQE_BYTE_4_OPCODE_S, + HNS_ROCE_V2_WQE_OP_SEND); + break; + case IB_WR_SEND_WITH_INV: + roce_set_field(rc_sq_wqe->byte_4, V2_RC_SEND_WQE_BYTE_4_OPCODE_M, V2_RC_SEND_WQE_BYTE_4_OPCODE_S, HNS_ROCE_V2_WQE_OP_SEND_WITH_INV); - break; - case IB_WR_SEND_WITH_IMM: - roce_set_field(rc_sq_wqe->byte_4, - V2_RC_SEND_WQE_BYTE_4_OPCODE_M, - V2_RC_SEND_WQE_BYTE_4_OPCODE_S, - HNS_ROCE_V2_WQE_OP_SEND_WITH_IMM); - break; - case IB_WR_LOCAL_INV: - roce_set_field(rc_sq_wqe->byte_4, - V2_RC_SEND_WQE_BYTE_4_OPCODE_M, - V2_RC_SEND_WQE_BYTE_4_OPCODE_S, - HNS_ROCE_V2_WQE_OP_LOCAL_INV); - break; - case IB_WR_ATOMIC_CMP_AND_SWP: - roce_set_field(rc_sq_wqe->byte_4, - V2_RC_SEND_WQE_BYTE_4_OPCODE_M, - V2_RC_SEND_WQE_BYTE_4_OPCODE_S, - HNS_ROCE_V2_WQE_OP_ATOM_CMP_AND_SWAP); - break; - case IB_WR_ATOMIC_FETCH_AND_ADD: - roce_set_field(rc_sq_wqe->byte_4, - V2_RC_SEND_WQE_BYTE_4_OPCODE_M, - V2_RC_SEND_WQE_BYTE_4_OPCODE_S, - HNS_ROCE_V2_WQE_OP_ATOM_FETCH_AND_ADD); - break; - case IB_WR_MASKED_ATOMIC_CMP_AND_SWP: - roce_set_field(rc_sq_wqe->byte_4, + break; + case IB_WR_SEND_WITH_IMM: + roce_set_field(rc_sq_wqe->byte_4, + V2_RC_SEND_WQE_BYTE_4_OPCODE_M, + V2_RC_SEND_WQE_BYTE_4_OPCODE_S, + HNS_ROCE_V2_WQE_OP_SEND_WITH_IMM); + break; + case IB_WR_LOCAL_INV: + roce_set_field(rc_sq_wqe->byte_4, + V2_RC_SEND_WQE_BYTE_4_OPCODE_M, + V2_RC_SEND_WQE_BYTE_4_OPCODE_S, + HNS_ROCE_V2_WQE_OP_LOCAL_INV); + break; + case IB_WR_ATOMIC_CMP_AND_SWP: + roce_set_field(rc_sq_wqe->byte_4, + V2_RC_SEND_WQE_BYTE_4_OPCODE_M, + V2_RC_SEND_WQE_BYTE_4_OPCODE_S, + HNS_ROCE_V2_WQE_OP_ATOM_CMP_AND_SWAP); + break; + case IB_WR_ATOMIC_FETCH_AND_ADD: + roce_set_field(rc_sq_wqe->byte_4, + V2_RC_SEND_WQE_BYTE_4_OPCODE_M, + V2_RC_SEND_WQE_BYTE_4_OPCODE_S, + HNS_ROCE_V2_WQE_OP_ATOM_FETCH_AND_ADD); + break; + case IB_WR_MASKED_ATOMIC_CMP_AND_SWP: + roce_set_field(rc_sq_wqe->byte_4, V2_RC_SEND_WQE_BYTE_4_OPCODE_M, V2_RC_SEND_WQE_BYTE_4_OPCODE_S, HNS_ROCE_V2_WQE_OP_ATOM_MSK_CMP_AND_SWAP); - break; - case IB_WR_MASKED_ATOMIC_FETCH_AND_ADD: - roce_set_field(rc_sq_wqe->byte_4, + break; + case IB_WR_MASKED_ATOMIC_FETCH_AND_ADD: + roce_set_field(rc_sq_wqe->byte_4, V2_RC_SEND_WQE_BYTE_4_OPCODE_M, V2_RC_SEND_WQE_BYTE_4_OPCODE_S, HNS_ROCE_V2_WQE_OP_ATOM_MSK_FETCH_AND_ADD); - break; - default: - roce_set_field(rc_sq_wqe->byte_4, - V2_RC_SEND_WQE_BYTE_4_OPCODE_M, - V2_RC_SEND_WQE_BYTE_4_OPCODE_S, - HNS_ROCE_V2_WQE_OP_MASK); - break; - } - - wqe += sizeof(struct hns_roce_v2_rc_send_wqe); - dseg = wqe; - if (wr->send_flags & IB_SEND_INLINE && wr->num_sge) { - if (rc_sq_wqe->msg_len > - hr_dev->caps.max_sq_inline) { - ret = -EINVAL; - *bad_wr = wr; - dev_err(dev, "inline len(1-%d)=%d, illegal", - rc_sq_wqe->msg_len, - hr_dev->caps.max_sq_inline); - goto out; + break; + default: + roce_set_field(rc_sq_wqe->byte_4, + V2_RC_SEND_WQE_BYTE_4_OPCODE_M, + V2_RC_SEND_WQE_BYTE_4_OPCODE_S, + HNS_ROCE_V2_WQE_OP_MASK); + break; } - for (i = 0; i < wr->num_sge; i++) { - memcpy(wqe, ((void *)wr->sg_list[i].addr), - wr->sg_list[i].length); - wqe += wr->sg_list[i].length; - wqe_sz += wr->sg_list[i].length; - } + wqe += sizeof(struct hns_roce_v2_rc_send_wqe); + dseg = wqe; - roce_set_bit(rc_sq_wqe->byte_4, - V2_RC_SEND_WQE_BYTE_4_INLINE_S, 1); + ret = set_rwqe_data_seg(ibqp, wr, rc_sq_wqe, wqe, + &sge_ind, bad_wr); + if (ret) + goto out; + ind++; } else { - if (wr->num_sge <= 2) { - for (i = 0; i < wr->num_sge; i++) { - if (likely(wr->sg_list[i].length)) { - set_data_seg_v2(dseg, - wr->sg_list + i); - dseg++; - } - } - } else { - roce_set_field(rc_sq_wqe->byte_20, - V2_RC_SEND_WQE_BYTE_20_MSG_START_SGE_IDX_M, - V2_RC_SEND_WQE_BYTE_20_MSG_START_SGE_IDX_S, - sge_ind & (qp->sge.sge_cnt - 1)); - - for (i = 0; i < 2; i++) { - if (likely(wr->sg_list[i].length)) { - set_data_seg_v2(dseg, - wr->sg_list + i); - dseg++; - } - } - - dseg = get_send_extend_sge(qp, - sge_ind & (qp->sge.sge_cnt - 1)); - - for (i = 0; i < wr->num_sge - 2; i++) { - if (likely(wr->sg_list[i + 2].length)) { - set_data_seg_v2(dseg, - wr->sg_list + 2 + i); - dseg++; - sge_ind++; - } - } - } - - roce_set_field(rc_sq_wqe->byte_16, - V2_RC_SEND_WQE_BYTE_16_SGE_NUM_M, - V2_RC_SEND_WQE_BYTE_16_SGE_NUM_S, - wr->num_sge); - wqe_sz += wr->num_sge * - sizeof(struct hns_roce_v2_wqe_data_seg); + dev_err(dev, "Illegal qp_type(0x%x)\n", ibqp->qp_type); + spin_unlock_irqrestore(&qp->sq.lock, flags); + return -EOPNOTSUPP; } - ind++; } out: diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h index 463edab..c11b253 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h @@ -916,6 +916,90 @@ struct hns_roce_v2_cq_db { #define V2_CQ_DB_PARAMETER_NOTIFY_S 24 +struct hns_roce_v2_ud_send_wqe { + u32 byte_4; + u32 msg_len; + u32 immtdata; + u32 byte_16; + u32 byte_20; + u32 byte_24; + u32 qkey; + u32 byte_32; + u32 byte_36; + u32 byte_40; + u32 dmac; + u32 byte_48; + u8 dgid[GID_LEN_V2]; + +}; +#define V2_UD_SEND_WQE_BYTE_4_OPCODE_S 0 +#define V2_UD_SEND_WQE_BYTE_4_OPCODE_M GENMASK(4, 0) + +#define V2_UD_SEND_WQE_BYTE_4_OWNER_S 7 + +#define V2_UD_SEND_WQE_BYTE_4_CQE_S 8 + +#define V2_UD_SEND_WQE_BYTE_4_SE_S 11 + +#define V2_UD_SEND_WQE_BYTE_16_PD_S 0 +#define V2_UD_SEND_WQE_BYTE_16_PD_M GENMASK(23, 0) + +#define V2_UD_SEND_WQE_BYTE_16_SGE_NUM_S 24 +#define V2_UD_SEND_WQE_BYTE_16_SGE_NUM_M GENMASK(31, 24) + +#define V2_UD_SEND_WQE_BYTE_20_MSG_START_SGE_IDX_S 0 +#define V2_UD_SEND_WQE_BYTE_20_MSG_START_SGE_IDX_M GENMASK(23, 0) + +#define V2_UD_SEND_WQE_BYTE_24_UDPSPN_S 16 +#define V2_UD_SEND_WQE_BYTE_24_UDPSPN_M GENMASK(31, 16) + +#define V2_UD_SEND_WQE_BYTE_32_DQPN_S 0 +#define V2_UD_SEND_WQE_BYTE_32_DQPN_M GENMASK(23, 0) + +#define V2_UD_SEND_WQE_BYTE_36_VLAN_S 0 +#define V2_UD_SEND_WQE_BYTE_36_VLAN_M GENMASK(15, 0) + +#define V2_UD_SEND_WQE_BYTE_36_HOPLIMIT_S 16 +#define V2_UD_SEND_WQE_BYTE_36_HOPLIMIT_M GENMASK(23, 16) + +#define V2_UD_SEND_WQE_BYTE_36_TCLASS_S 24 +#define V2_UD_SEND_WQE_BYTE_36_TCLASS_M GENMASK(31, 24) + +#define V2_UD_SEND_WQE_BYTE_40_FLOW_LABEL_S 0 +#define V2_UD_SEND_WQE_BYTE_40_FLOW_LABEL_M GENMASK(19, 0) + +#define V2_UD_SEND_WQE_BYTE_40_SL_S 20 +#define V2_UD_SEND_WQE_BYTE_40_SL_M GENMASK(23, 20) + +#define V2_UD_SEND_WQE_BYTE_40_PORTN_S 24 +#define V2_UD_SEND_WQE_BYTE_40_PORTN_M GENMASK(26, 24) + +#define V2_UD_SEND_WQE_BYTE_40_LBI_S 31 + +#define V2_UD_SEND_WQE_DMAC_0_S 0 +#define V2_UD_SEND_WQE_DMAC_0_M GENMASK(7, 0) + +#define V2_UD_SEND_WQE_DMAC_1_S 8 +#define V2_UD_SEND_WQE_DMAC_1_M GENMASK(15, 8) + +#define V2_UD_SEND_WQE_DMAC_2_S 16 +#define V2_UD_SEND_WQE_DMAC_2_M GENMASK(23, 16) + +#define V2_UD_SEND_WQE_DMAC_3_S 24 +#define V2_UD_SEND_WQE_DMAC_3_M GENMASK(31, 24) + +#define V2_UD_SEND_WQE_BYTE_48_DMAC_4_S 0 +#define V2_UD_SEND_WQE_BYTE_48_DMAC_4_M GENMASK(7, 0) + +#define V2_UD_SEND_WQE_BYTE_48_DMAC_5_S 8 +#define V2_UD_SEND_WQE_BYTE_48_DMAC_5_M GENMASK(15, 8) + +#define V2_UD_SEND_WQE_BYTE_48_SGID_INDX_S 16 +#define V2_UD_SEND_WQE_BYTE_48_SGID_INDX_M GENMASK(23, 16) + +#define V2_UD_SEND_WQE_BYTE_48_SMAC_INDX_S 24 +#define V2_UD_SEND_WQE_BYTE_48_SMAC_INDX_M GENMASK(31, 24) + struct hns_roce_v2_rc_send_wqe { u32 byte_4; u32 msg_len;