From patchwork Thu Dec 17 11:44:23 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Michael Baum X-Patchwork-Id: 85307 X-Patchwork-Delegate: rasland@nvidia.com Return-Path: X-Original-To: patchwork@inbox.dpdk.org Delivered-To: patchwork@inbox.dpdk.org Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id 36F1BA09F6; Thu, 17 Dec 2020 12:45:00 +0100 (CET) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id 25B50CA0C; Thu, 17 Dec 2020 12:44:58 +0100 (CET) Received: from mellanox.co.il (mail-il-dmz.mellanox.com [193.47.165.129]) by dpdk.org (Postfix) with ESMTP id 3BF5CCA08 for ; Thu, 17 Dec 2020 12:44:55 +0100 (CET) Received: from Internal Mail-Server by MTLPINE1 (envelope-from michaelba@nvidia.com) with SMTP; 17 Dec 2020 13:44:50 +0200 Received: from nvidia.com (pegasus07.mtr.labs.mlnx [10.210.16.112]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id 0BHBio2U004524; Thu, 17 Dec 2020 13:44:50 +0200 From: Michael Baum To: dev@dpdk.org Cc: Matan Azrad , Raslan Darawsheh , Viacheslav Ovsiienko Date: Thu, 17 Dec 2020 11:44:23 +0000 Message-Id: <1608205475-20067-6-git-send-email-michaelba@nvidia.com> X-Mailer: git-send-email 1.8.3.1 In-Reply-To: <1608205475-20067-1-git-send-email-michaelba@nvidia.com> References: <1608205475-20067-1-git-send-email-michaelba@nvidia.com> Subject: [dpdk-dev] [PATCH 05/17] net/mlx5: move rearm and clock queue CQ creation to common X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" Using common function for CQ creation at rearm queue and clock queue. Signed-off-by: Michael Baum Acked-by: Matan Azrad --- drivers/net/mlx5/mlx5.h | 9 +-- drivers/net/mlx5/mlx5_rxtx.c | 2 +- drivers/net/mlx5/mlx5_txpp.c | 147 +++++++++++-------------------------------- 3 files changed, 40 insertions(+), 118 deletions(-) diff --git a/drivers/net/mlx5/mlx5.h b/drivers/net/mlx5/mlx5.h index 121d726..00ccaee 100644 --- a/drivers/net/mlx5/mlx5.h +++ b/drivers/net/mlx5/mlx5.h @@ -26,6 +26,7 @@ #include #include #include +#include #include "mlx5_defs.h" #include "mlx5_utils.h" @@ -612,13 +613,7 @@ struct mlx5_flow_id_pool { /* Tx pacing queue structure - for Clock and Rearm queues. */ struct mlx5_txpp_wq { /* Completion Queue related data.*/ - struct mlx5_devx_obj *cq; - void *cq_umem; - union { - volatile void *cq_buf; - volatile struct mlx5_cqe *cqes; - }; - volatile uint32_t *cq_dbrec; + struct mlx5_devx_cq cq_obj; uint32_t cq_ci:24; uint32_t arm_sn:2; /* Send Queue related data.*/ diff --git a/drivers/net/mlx5/mlx5_rxtx.c b/drivers/net/mlx5/mlx5_rxtx.c index d12d746..dad24a3 100644 --- a/drivers/net/mlx5/mlx5_rxtx.c +++ b/drivers/net/mlx5/mlx5_rxtx.c @@ -2277,7 +2277,7 @@ enum mlx5_txcmp_code { qs = RTE_PTR_ADD(wqe, MLX5_WSEG_SIZE); qs->max_index = rte_cpu_to_be_32(wci); - qs->qpn_cqn = rte_cpu_to_be_32(txq->sh->txpp.clock_queue.cq->id); + qs->qpn_cqn = rte_cpu_to_be_32(txq->sh->txpp.clock_queue.cq_obj.cq->id); qs->reserved0 = RTE_BE32(0); qs->reserved1 = RTE_BE32(0); } diff --git a/drivers/net/mlx5/mlx5_txpp.c b/drivers/net/mlx5/mlx5_txpp.c index 2438bf1..54ea572 100644 --- a/drivers/net/mlx5/mlx5_txpp.c +++ b/drivers/net/mlx5/mlx5_txpp.c @@ -13,6 +13,7 @@ #include #include +#include #include "mlx5.h" #include "mlx5_rxtx.h" @@ -126,12 +127,7 @@ claim_zero(mlx5_glue->devx_umem_dereg(wq->sq_umem)); if (wq->sq_buf) mlx5_free((void *)(uintptr_t)wq->sq_buf); - if (wq->cq) - claim_zero(mlx5_devx_cmd_destroy(wq->cq)); - if (wq->cq_umem) - claim_zero(mlx5_glue->devx_umem_dereg(wq->cq_umem)); - if (wq->cq_buf) - mlx5_free((void *)(uintptr_t)wq->cq_buf); + mlx5_devx_cq_destroy(&wq->cq_obj); memset(wq, 0, sizeof(*wq)); } @@ -181,19 +177,6 @@ } static void -mlx5_txpp_fill_cqe_rearm_queue(struct mlx5_dev_ctx_shared *sh) -{ - struct mlx5_txpp_wq *wq = &sh->txpp.rearm_queue; - struct mlx5_cqe *cqe = (struct mlx5_cqe *)(uintptr_t)wq->cqes; - uint32_t i; - - for (i = 0; i < MLX5_TXPP_REARM_CQ_SIZE; i++) { - cqe->op_own = (MLX5_CQE_INVALID << 4) | MLX5_CQE_OWNER_MASK; - ++cqe; - } -} - -static void mlx5_txpp_fill_wqe_rearm_queue(struct mlx5_dev_ctx_shared *sh) { struct mlx5_txpp_wq *wq = &sh->txpp.rearm_queue; @@ -228,7 +211,8 @@ index = (i * MLX5_TXPP_REARM / 2 + MLX5_TXPP_REARM / 2) & ((1 << MLX5_CQ_INDEX_WIDTH) - 1); qs->max_index = rte_cpu_to_be_32(index); - qs->qpn_cqn = rte_cpu_to_be_32(sh->txpp.clock_queue.cq->id); + qs->qpn_cqn = + rte_cpu_to_be_32(sh->txpp.clock_queue.cq_obj.cq->id); } } @@ -238,7 +222,11 @@ { struct mlx5_devx_create_sq_attr sq_attr = { 0 }; struct mlx5_devx_modify_sq_attr msq_attr = { 0 }; - struct mlx5_devx_cq_attr cq_attr = { 0 }; + struct mlx5_devx_cq_attr cq_attr = { + .cqe_size = (sizeof(struct mlx5_cqe) == 128) ? + MLX5_CQE_SIZE_128B : MLX5_CQE_SIZE_64B, + .uar_page_id = mlx5_os_get_devx_uar_page_id(sh->tx_uar), + }; struct mlx5_txpp_wq *wq = &sh->txpp.rearm_queue; size_t page_size; uint32_t umem_size, umem_dbrec; @@ -249,50 +237,16 @@ DRV_LOG(ERR, "Failed to get mem page size"); return -ENOMEM; } - /* Allocate memory buffer for CQEs and doorbell record. */ - umem_size = sizeof(struct mlx5_cqe) * MLX5_TXPP_REARM_CQ_SIZE; - umem_dbrec = RTE_ALIGN(umem_size, MLX5_DBR_SIZE); - umem_size += MLX5_DBR_SIZE; - wq->cq_buf = mlx5_malloc(MLX5_MEM_RTE | MLX5_MEM_ZERO, umem_size, - page_size, sh->numa_node); - if (!wq->cq_buf) { - DRV_LOG(ERR, "Failed to allocate memory for Rearm Queue."); - return -ENOMEM; - } - /* Register allocated buffer in user space with DevX. */ - wq->cq_umem = mlx5_glue->devx_umem_reg(sh->ctx, - (void *)(uintptr_t)wq->cq_buf, - umem_size, - IBV_ACCESS_LOCAL_WRITE); - if (!wq->cq_umem) { - rte_errno = errno; - DRV_LOG(ERR, "Failed to register umem for Rearm Queue."); - goto error; - } /* Create completion queue object for Rearm Queue. */ - cq_attr.cqe_size = (sizeof(struct mlx5_cqe) == 128) ? - MLX5_CQE_SIZE_128B : MLX5_CQE_SIZE_64B; - cq_attr.uar_page_id = mlx5_os_get_devx_uar_page_id(sh->tx_uar); - cq_attr.eqn = sh->eqn; - cq_attr.q_umem_valid = 1; - cq_attr.q_umem_offset = 0; - cq_attr.q_umem_id = mlx5_os_get_umem_id(wq->cq_umem); - cq_attr.db_umem_valid = 1; - cq_attr.db_umem_offset = umem_dbrec; - cq_attr.db_umem_id = mlx5_os_get_umem_id(wq->cq_umem); - cq_attr.log_cq_size = rte_log2_u32(MLX5_TXPP_REARM_CQ_SIZE); - cq_attr.log_page_size = rte_log2_u32(page_size); - wq->cq = mlx5_devx_cmd_create_cq(sh->ctx, &cq_attr); - if (!wq->cq) { - rte_errno = errno; + ret = mlx5_devx_cq_create(sh->ctx, &wq->cq_obj, + log2above(MLX5_TXPP_REARM_CQ_SIZE), &cq_attr, + sh->numa_node); + if (ret) { DRV_LOG(ERR, "Failed to create CQ for Rearm Queue."); - goto error; + return ret; } - wq->cq_dbrec = RTE_PTR_ADD(wq->cq_buf, umem_dbrec); wq->cq_ci = 0; wq->arm_sn = 0; - /* Mark all CQEs initially as invalid. */ - mlx5_txpp_fill_cqe_rearm_queue(sh); /* * Allocate memory buffer for Send Queue WQEs. * There should be no WQE leftovers in the cyclic queue. @@ -323,7 +277,7 @@ sq_attr.state = MLX5_SQC_STATE_RST; sq_attr.tis_lst_sz = 1; sq_attr.tis_num = sh->tis->id; - sq_attr.cqn = wq->cq->id; + sq_attr.cqn = wq->cq_obj.cq->id; sq_attr.cd_master = 1; sq_attr.wq_attr.uar_page = mlx5_os_get_devx_uar_page_id(sh->tx_uar); sq_attr.wq_attr.wq_type = MLX5_WQ_TYPE_CYCLIC; @@ -466,7 +420,13 @@ { struct mlx5_devx_create_sq_attr sq_attr = { 0 }; struct mlx5_devx_modify_sq_attr msq_attr = { 0 }; - struct mlx5_devx_cq_attr cq_attr = { 0 }; + struct mlx5_devx_cq_attr cq_attr = { + .cqe_size = (sizeof(struct mlx5_cqe) == 128) ? + MLX5_CQE_SIZE_128B : MLX5_CQE_SIZE_64B, + .use_first_only = 1, + .overrun_ignore = 1, + .uar_page_id = mlx5_os_get_devx_uar_page_id(sh->tx_uar), + }; struct mlx5_txpp_wq *wq = &sh->txpp.clock_queue; size_t page_size; uint32_t umem_size, umem_dbrec; @@ -487,48 +447,14 @@ } sh->txpp.ts_p = 0; sh->txpp.ts_n = 0; - /* Allocate memory buffer for CQEs and doorbell record. */ - umem_size = sizeof(struct mlx5_cqe) * MLX5_TXPP_CLKQ_SIZE; - umem_dbrec = RTE_ALIGN(umem_size, MLX5_DBR_SIZE); - umem_size += MLX5_DBR_SIZE; - wq->cq_buf = mlx5_malloc(MLX5_MEM_RTE | MLX5_MEM_ZERO, umem_size, - page_size, sh->numa_node); - if (!wq->cq_buf) { - DRV_LOG(ERR, "Failed to allocate memory for Clock Queue."); - return -ENOMEM; - } - /* Register allocated buffer in user space with DevX. */ - wq->cq_umem = mlx5_glue->devx_umem_reg(sh->ctx, - (void *)(uintptr_t)wq->cq_buf, - umem_size, - IBV_ACCESS_LOCAL_WRITE); - if (!wq->cq_umem) { - rte_errno = errno; - DRV_LOG(ERR, "Failed to register umem for Clock Queue."); - goto error; - } /* Create completion queue object for Clock Queue. */ - cq_attr.cqe_size = (sizeof(struct mlx5_cqe) == 128) ? - MLX5_CQE_SIZE_128B : MLX5_CQE_SIZE_64B; - cq_attr.use_first_only = 1; - cq_attr.overrun_ignore = 1; - cq_attr.uar_page_id = mlx5_os_get_devx_uar_page_id(sh->tx_uar); - cq_attr.eqn = sh->eqn; - cq_attr.q_umem_valid = 1; - cq_attr.q_umem_offset = 0; - cq_attr.q_umem_id = mlx5_os_get_umem_id(wq->cq_umem); - cq_attr.db_umem_valid = 1; - cq_attr.db_umem_offset = umem_dbrec; - cq_attr.db_umem_id = mlx5_os_get_umem_id(wq->cq_umem); - cq_attr.log_cq_size = rte_log2_u32(MLX5_TXPP_CLKQ_SIZE); - cq_attr.log_page_size = rte_log2_u32(page_size); - wq->cq = mlx5_devx_cmd_create_cq(sh->ctx, &cq_attr); - if (!wq->cq) { - rte_errno = errno; + ret = mlx5_devx_cq_create(sh->ctx, &wq->cq_obj, + log2above(MLX5_TXPP_CLKQ_SIZE), &cq_attr, + sh->numa_node); + if (ret) { DRV_LOG(ERR, "Failed to create CQ for Clock Queue."); goto error; } - wq->cq_dbrec = RTE_PTR_ADD(wq->cq_buf, umem_dbrec); wq->cq_ci = 0; /* Allocate memory buffer for Send Queue WQEs. */ if (sh->txpp.test) { @@ -574,7 +500,7 @@ sq_attr.static_sq_wq = 1; } sq_attr.state = MLX5_SQC_STATE_RST; - sq_attr.cqn = wq->cq->id; + sq_attr.cqn = wq->cq_obj.cq->id; sq_attr.packet_pacing_rate_limit_index = sh->txpp.pp_id; sq_attr.wq_attr.cd_slave = 1; sq_attr.wq_attr.uar_page = mlx5_os_get_devx_uar_page_id(sh->tx_uar); @@ -625,12 +551,13 @@ struct mlx5_txpp_wq *aq = &sh->txpp.rearm_queue; uint32_t arm_sn = aq->arm_sn << MLX5_CQ_SQN_OFFSET; uint32_t db_hi = arm_sn | MLX5_CQ_DBR_CMD_ALL | aq->cq_ci; - uint64_t db_be = rte_cpu_to_be_64(((uint64_t)db_hi << 32) | aq->cq->id); + uint64_t db_be = + rte_cpu_to_be_64(((uint64_t)db_hi << 32) | aq->cq_obj.cq->id); base_addr = mlx5_os_get_devx_uar_base_addr(sh->tx_uar); uint32_t *addr = RTE_PTR_ADD(base_addr, MLX5_CQ_DOORBELL); rte_compiler_barrier(); - aq->cq_dbrec[MLX5_CQ_ARM_DB] = rte_cpu_to_be_32(db_hi); + aq->cq_obj.db_rec[MLX5_CQ_ARM_DB] = rte_cpu_to_be_32(db_hi); rte_wmb(); #ifdef RTE_ARCH_64 *(uint64_t *)addr = db_be; @@ -728,7 +655,7 @@ mlx5_txpp_update_timestamp(struct mlx5_dev_ctx_shared *sh) { struct mlx5_txpp_wq *wq = &sh->txpp.clock_queue; - struct mlx5_cqe *cqe = (struct mlx5_cqe *)(uintptr_t)wq->cqes; + struct mlx5_cqe *cqe = (struct mlx5_cqe *)(uintptr_t)wq->cq_obj.cqes; union { rte_int128_t u128; struct mlx5_cqe_ts cts; @@ -809,7 +736,7 @@ do { volatile struct mlx5_cqe *cqe; - cqe = &wq->cqes[cq_ci & (MLX5_TXPP_REARM_CQ_SIZE - 1)]; + cqe = &wq->cq_obj.cqes[cq_ci & (MLX5_TXPP_REARM_CQ_SIZE - 1)]; ret = check_cqe(cqe, MLX5_TXPP_REARM_CQ_SIZE, cq_ci); switch (ret) { case MLX5_CQE_STATUS_ERR: @@ -841,7 +768,7 @@ } /* Update doorbell record to notify hardware. */ rte_compiler_barrier(); - *wq->cq_dbrec = rte_cpu_to_be_32(cq_ci); + *wq->cq_obj.db_rec = rte_cpu_to_be_32(cq_ci); rte_wmb(); wq->cq_ci = cq_ci; /* Fire new requests to Rearm Queue. */ @@ -936,9 +863,8 @@ } /* Subscribe CQ event to the event channel controlled by the driver. */ ret = mlx5_glue->devx_subscribe_devx_event(sh->txpp.echan, - sh->txpp.rearm_queue.cq->obj, - sizeof(event_nums), - event_nums, 0); + sh->txpp.rearm_queue.cq_obj.cq->obj, + sizeof(event_nums), event_nums, 0); if (ret) { DRV_LOG(ERR, "Failed to subscribe CQE event."); rte_errno = errno; @@ -1140,7 +1066,8 @@ if (sh->txpp.refcnt) { struct mlx5_txpp_wq *wq = &sh->txpp.clock_queue; - struct mlx5_cqe *cqe = (struct mlx5_cqe *)(uintptr_t)wq->cqes; + struct mlx5_cqe *cqe = + (struct mlx5_cqe *)(uintptr_t)wq->cq_obj.cqes; union { rte_int128_t u128; struct mlx5_cqe_ts cts;