From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124]) by inbox.dpdk.org (Postfix) with ESMTP id 2F4AAA0560; Tue, 18 Oct 2022 13:14:38 +0200 (CEST) Received: from [217.70.189.124] (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id 0C975410F2; Tue, 18 Oct 2022 13:14:19 +0200 (CEST) Received: from mga02.intel.com (mga02.intel.com [134.134.136.20]) by mails.dpdk.org (Postfix) with ESMTP id 24DD941133 for ; Tue, 18 Oct 2022 13:14:16 +0200 (CEST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1666091657; x=1697627657; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=vdRHM51G9u8zmCW529s3m+ye/vWCocGkPhhJuktJGJ4=; b=V2kAc/9/0oIX1jFhB85xVKM3VjtJz2L/eypfD8mxUvF8eKFn6NrjiTAA XPRmMjRsPu3qQLrU6TUMij7wpHMxw9j2zXqk4Ic/FaO2UdSBDlNycraUo izP3E4SmAKWbXtYggww7l+uypVTtKaimbcFe97PuXsnoqi1W/C89i3YQj /LAYsmgeJ2DfleFMELz46Lf0PpJIl1yGaTBPTOJptFeHTsA9L4Q4n3Yy4 1qgwHdzY/3wNPKa7ws+hgsXviaMO3qVhBmuZok6b0Fniy4hOViEpZ74E4 GbvzjxP5GbMqUAS2lG06OFt77iqHpmLGskXa2UacyPkGzXoXOgt75ttXg Q==; X-IronPort-AV: E=McAfee;i="6500,9779,10503"; a="293441548" X-IronPort-AV: E=Sophos;i="5.95,193,1661842800"; d="scan'208";a="293441548" Received: from fmsmga003.fm.intel.com ([10.253.24.29]) by orsmga101.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 18 Oct 2022 04:14:16 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=McAfee;i="6500,9779,10503"; a="717884135" X-IronPort-AV: E=Sophos;i="5.95,193,1661842800"; d="scan'208";a="717884135" Received: from dpdk-jf-ntb-one.sh.intel.com ([10.67.111.104]) by FMSMGA003.fm.intel.com with ESMTP; 18 Oct 2022 04:14:13 -0700 From: Junfeng Guo To: andrew.rybchenko@oktetlabs.ru, qi.z.zhang@intel.com, jingjing.wu@intel.com, beilei.xing@intel.com Cc: dev@dpdk.org, junfeng.guo@intel.com, Xiaoyun Li Subject: [PATCH v3 03/15] net/idpf: add queue setup and release in single queue model Date: Tue, 18 Oct 2022 19:12:33 +0800 Message-Id: <20221018111245.890651-4-junfeng.guo@intel.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20221018111245.890651-1-junfeng.guo@intel.com> References: <20220905105828.3190335-1-junfeng.guo@intel.com> <20221018111245.890651-1-junfeng.guo@intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=a Content-Transfer-Encoding: 8bit X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Add support for queue operations in single queue model: - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release In the single queue model, the same descriptor queue is used by SW to post buffer descriptors to HW and by HW to post completed descriptors to SW. Signed-off-by: Beilei Xing Signed-off-by: Xiaoyun Li Signed-off-by: Junfeng Guo --- doc/guides/nics/features/idpf.ini | 2 + doc/guides/nics/idpf.rst | 22 ++ drivers/net/idpf/idpf_ethdev.c | 58 ++++ drivers/net/idpf/idpf_ethdev.h | 9 + drivers/net/idpf/idpf_rxtx.c | 463 ++++++++++++++++++++++++++++++ drivers/net/idpf/idpf_rxtx.h | 186 ++++++++++++ drivers/net/idpf/idpf_vchnl.c | 249 ++++++++++++++++ drivers/net/idpf/meson.build | 1 + 8 files changed, 990 insertions(+) create mode 100644 drivers/net/idpf/idpf_rxtx.c create mode 100644 drivers/net/idpf/idpf_rxtx.h diff --git a/doc/guides/nics/features/idpf.ini b/doc/guides/nics/features/idpf.ini index 9900e23364..7cfcb60bd0 100644 --- a/doc/guides/nics/features/idpf.ini +++ b/doc/guides/nics/features/idpf.ini @@ -7,6 +7,8 @@ ; is selected. ; [Features] +Runtime Rx queue setup = Y +Runtime Tx queue setup = Y Multiprocess aware = Y FreeBSD = Y Linux = Y diff --git a/doc/guides/nics/idpf.rst b/doc/guides/nics/idpf.rst index 417d6b690e..af7810834a 100644 --- a/doc/guides/nics/idpf.rst +++ b/doc/guides/nics/idpf.rst @@ -45,6 +45,28 @@ Runtime Config Options Then idpf PMD will create 3 vports (ethdevs) for device ca:00.0. NOTE: This parameter is MUST, otherwise there'll be no any ethdev created. +- ``rx_single`` (defalut ``0``) + + There're two queue modes supported by Intel® IPU Ethernet ES2000 Series, single queue + mode and split queue mode for Rx queue. User can choose Rx queue mode by the ``devargs`` + parameter ``rx_single``. + + -a ca:00.0,rx_single=1 + + Then idpf PMD will configure Rx queue with single queue mode. Otherwise, split queue + mode is chosen by default. + +- ``tx_single`` (defalut ``0``) + + There're two queue modes supported by Intel® IPU Ethernet ES2000 Series, single queue + mode and split queue mode for Tx queue. User can choose Tx queue mode by the ``devargs`` + parameter ``tx_single``. + + -a ca:00.0,tx_single=1 + + Then idpf PMD will configure Tx queue with single queue mode. Otherwise, split queue + mode is chosen by default. + Driver compilation and testing ------------------------------ diff --git a/drivers/net/idpf/idpf_ethdev.c b/drivers/net/idpf/idpf_ethdev.c index e73a30a00f..c0a6b3e90d 100644 --- a/drivers/net/idpf/idpf_ethdev.c +++ b/drivers/net/idpf/idpf_ethdev.c @@ -10,13 +10,18 @@ #include #include "idpf_ethdev.h" +#include "idpf_rxtx.h" +#define IDPF_TX_SINGLE_Q "tx_single" +#define IDPF_RX_SINGLE_Q "rx_single" #define IDPF_VPORT "vport" struct idpf_adapter_list adapter_list; bool adapter_list_init; static const char * const idpf_valid_args[] = { + IDPF_TX_SINGLE_Q, + IDPF_RX_SINGLE_Q, IDPF_VPORT, NULL }; @@ -32,6 +37,10 @@ static const struct eth_dev_ops idpf_eth_dev_ops = { .dev_start = idpf_dev_start, .dev_stop = idpf_dev_stop, .dev_close = idpf_dev_close, + .rx_queue_setup = idpf_rx_queue_setup, + .rx_queue_release = idpf_dev_rx_queue_release, + .tx_queue_setup = idpf_tx_queue_setup, + .tx_queue_release = idpf_dev_tx_queue_release, }; static int @@ -60,6 +69,18 @@ idpf_init_vport_req_info(struct rte_eth_dev *dev) (struct virtchnl2_create_vport *)adapter->vport_req_info[idx]; vport_info->vport_type = rte_cpu_to_le_16(VIRTCHNL2_VPORT_TYPE_DEFAULT); + if (adapter->txq_model) { + vport_info->txq_model = + rte_cpu_to_le_16(VIRTCHNL2_QUEUE_MODEL_SINGLE); + vport_info->num_tx_q = IDPF_DEFAULT_TXQ_NUM; + vport_info->num_tx_complq = 0; + } + if (adapter->rxq_model) { + vport_info->rxq_model = + rte_cpu_to_le_16(VIRTCHNL2_QUEUE_MODEL_SINGLE); + vport_info->num_rx_q = IDPF_DEFAULT_RXQ_NUM; + vport_info->num_rx_bufq = 0; + } return 0; } @@ -89,6 +110,8 @@ idpf_init_vport(struct rte_eth_dev *dev) int i; vport->vport_id = vport_info->vport_id; + vport->txq_model = vport_info->txq_model; + vport->rxq_model = vport_info->rxq_model; vport->num_tx_q = vport_info->num_tx_q; vport->num_rx_q = vport_info->num_rx_q; vport->max_mtu = vport_info->max_mtu; @@ -128,6 +151,12 @@ idpf_init_vport(struct rte_eth_dev *dev) static int idpf_dev_configure(__rte_unused struct rte_eth_dev *dev) { + if (dev->data->nb_tx_queues > IDPF_DEFAULT_TXQ_NUM || + dev->data->nb_rx_queues > IDPF_DEFAULT_RXQ_NUM) { + PMD_INIT_LOG(ERR, "Invalid queue number."); + return -EINVAL; + } + return 0; } @@ -291,6 +320,25 @@ parse_vport(const char *key, const char *value, void *args) return 0; } +static int +parse_bool(const char *key, const char *value, void *args) +{ + int *i = (int *)args; + char *end; + int num; + + num = strtoul(value, &end, 10); + + if (num != 0 && num != 1) { + PMD_INIT_LOG(ERR, "invalid value:\"%s\" for key:\"%s\", value must be 0 or 1", + value, key); + return -1; + } + + *i = num; + return 0; +} + static int idpf_parse_devargs(struct rte_pci_device *pci_dev, struct idpf_adapter *adapter) { @@ -312,6 +360,16 @@ idpf_parse_devargs(struct rte_pci_device *pci_dev, struct idpf_adapter *adapter) if (ret) goto bail; + ret = rte_kvargs_process(kvlist, IDPF_TX_SINGLE_Q, &parse_bool, + &adapter->txq_model); + if (ret) + goto bail; + + ret = rte_kvargs_process(kvlist, IDPF_RX_SINGLE_Q, &parse_bool, + &adapter->rxq_model); + if (ret) + goto bail; + bail: rte_kvargs_free(kvlist); return ret; diff --git a/drivers/net/idpf/idpf_ethdev.h b/drivers/net/idpf/idpf_ethdev.h index d00ee12364..d90bcfa63a 100644 --- a/drivers/net/idpf/idpf_ethdev.h +++ b/drivers/net/idpf/idpf_ethdev.h @@ -83,6 +83,8 @@ struct idpf_chunks_info { struct idpf_vport { struct idpf_adapter *adapter; /* Backreference to associated adapter */ uint16_t vport_id; + uint32_t txq_model; + uint32_t rxq_model; uint16_t num_tx_q; uint16_t num_rx_q; @@ -114,6 +116,9 @@ struct idpf_adapter { uint32_t cmd_retval; /* return value of the cmd response from ipf */ uint8_t *mbx_resp; /* buffer to store the mailbox response from ipf */ + uint32_t txq_model; + uint32_t rxq_model; + /* Vport info */ uint8_t **vport_req_info; uint8_t **vport_recv_info; @@ -191,6 +196,10 @@ int idpf_vc_check_api_version(struct idpf_adapter *adapter); int idpf_vc_get_caps(struct idpf_adapter *adapter); int idpf_vc_create_vport(struct rte_eth_dev *dev); int idpf_vc_destroy_vport(struct idpf_vport *vport); +int idpf_vc_config_rxqs(struct idpf_vport *vport); +int idpf_vc_config_rxq(struct idpf_vport *vport, uint16_t rxq_id); +int idpf_vc_config_txqs(struct idpf_vport *vport); +int idpf_vc_config_txq(struct idpf_vport *vport, uint16_t txq_id); int idpf_vc_ena_dis_vport(struct idpf_vport *vport, bool enable); int idpf_read_one_msg(struct idpf_adapter *adapter, uint32_t ops, uint16_t buf_len, uint8_t *buf); diff --git a/drivers/net/idpf/idpf_rxtx.c b/drivers/net/idpf/idpf_rxtx.c new file mode 100644 index 0000000000..9fef467990 --- /dev/null +++ b/drivers/net/idpf/idpf_rxtx.c @@ -0,0 +1,463 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2022 Intel Corporation + */ + +#include +#include + +#include "idpf_ethdev.h" +#include "idpf_rxtx.h" + +static inline int +check_rx_thresh(uint16_t nb_desc, uint16_t thresh) +{ + /* The following constraints must be satisfied: + * thresh < rxq->nb_rx_desc + */ + if (thresh >= nb_desc) { + PMD_INIT_LOG(ERR, "rx_free_thresh (%u) must be less than %u", + thresh, nb_desc); + return -EINVAL; + } + + return 0; +} + +static inline int +check_tx_thresh(uint16_t nb_desc, uint16_t tx_rs_thresh, + uint16_t tx_free_thresh) +{ + /* TX descriptors will have their RS bit set after tx_rs_thresh + * descriptors have been used. The TX descriptor ring will be cleaned + * after tx_free_thresh descriptors are used or if the number of + * descriptors required to transmit a packet is greater than the + * number of free TX descriptors. + * + * The following constraints must be satisfied: + * - tx_rs_thresh must be less than the size of the ring minus 2. + * - tx_free_thresh must be less than the size of the ring minus 3. + * - tx_rs_thresh must be less than or equal to tx_free_thresh. + * - tx_rs_thresh must be a divisor of the ring size. + * + * One descriptor in the TX ring is used as a sentinel to avoid a H/W + * race condition, hence the maximum threshold constraints. When set + * to zero use default values. + */ + if (tx_rs_thresh >= (nb_desc - 2)) { + PMD_INIT_LOG(ERR, "tx_rs_thresh (%u) must be less than the " + "number of TX descriptors (%u) minus 2", + tx_rs_thresh, nb_desc); + return -EINVAL; + } + if (tx_free_thresh >= (nb_desc - 3)) { + PMD_INIT_LOG(ERR, "tx_free_thresh (%u) must be less than the " + "number of TX descriptors (%u) minus 3.", + tx_free_thresh, nb_desc); + return -EINVAL; + } + if (tx_rs_thresh > tx_free_thresh) { + PMD_INIT_LOG(ERR, "tx_rs_thresh (%u) must be less than or " + "equal to tx_free_thresh (%u).", + tx_rs_thresh, tx_free_thresh); + return -EINVAL; + } + if ((nb_desc % tx_rs_thresh) != 0) { + PMD_INIT_LOG(ERR, "tx_rs_thresh (%u) must be a divisor of the " + "number of TX descriptors (%u).", + tx_rs_thresh, nb_desc); + return -EINVAL; + } + + return 0; +} + +static inline void +release_rxq_mbufs(struct idpf_rx_queue *rxq) +{ + uint16_t i; + + if (!rxq->sw_ring) + return; + + for (i = 0; i < rxq->nb_rx_desc; i++) { + if (rxq->sw_ring[i]) { + rte_pktmbuf_free_seg(rxq->sw_ring[i]); + rxq->sw_ring[i] = NULL; + } + } +} + +static inline void +release_txq_mbufs(struct idpf_tx_queue *txq) +{ + uint16_t nb_desc, i; + + if (!txq || !txq->sw_ring) { + PMD_DRV_LOG(DEBUG, "Pointer to rxq or sw_ring is NULL"); + return; + } + + if (!txq->sw_nb_desc) { + /* For single queue model */ + nb_desc = txq->nb_tx_desc; + } + for (i = 0; i < nb_desc; i++) { + if (txq->sw_ring[i].mbuf) { + rte_pktmbuf_free_seg(txq->sw_ring[i].mbuf); + txq->sw_ring[i].mbuf = NULL; + } + } +} + +static const struct idpf_rxq_ops def_rxq_ops = { + .release_mbufs = release_rxq_mbufs, +}; + +static const struct idpf_txq_ops def_txq_ops = { + .release_mbufs = release_txq_mbufs, +}; + +static void +idpf_rx_queue_release(void *rxq) +{ + struct idpf_rx_queue *q = (struct idpf_rx_queue *)rxq; + + if (!q) + return; + + /* Single queue */ + q->ops->release_mbufs(q); + rte_free(q->sw_ring); + rte_memzone_free(q->mz); + rte_free(q); +} + +static void +idpf_tx_queue_release(void *txq) +{ + struct idpf_tx_queue *q = (struct idpf_tx_queue *)txq; + + if (!q) + return; + + rte_free(q->complq); + q->ops->release_mbufs(q); + rte_free(q->sw_ring); + rte_memzone_free(q->mz); + rte_free(q); +} + +static inline void +reset_single_rx_queue(struct idpf_rx_queue *rxq) +{ + uint16_t len; + uint32_t i; + + if (!rxq) + return; + + len = rxq->nb_rx_desc + IDPF_RX_MAX_BURST; + + for (i = 0; i < len * sizeof(struct virtchnl2_singleq_rx_buf_desc); + i++) + ((volatile char *)rxq->rx_ring)[i] = 0; + + memset(&rxq->fake_mbuf, 0x0, sizeof(rxq->fake_mbuf)); + + for (i = 0; i < IDPF_RX_MAX_BURST; i++) + rxq->sw_ring[rxq->nb_rx_desc + i] = &rxq->fake_mbuf; + + rxq->rx_tail = 0; + rxq->nb_rx_hold = 0; + + if (rxq->pkt_first_seg != NULL) + rte_pktmbuf_free(rxq->pkt_first_seg); + + rxq->pkt_first_seg = NULL; + rxq->pkt_last_seg = NULL; + rxq->rxrearm_start = 0; + rxq->rxrearm_nb = 0; +} + +static inline void +reset_single_tx_queue(struct idpf_tx_queue *txq) +{ + struct idpf_tx_entry *txe; + uint32_t i, size; + uint16_t prev; + + if (!txq) { + PMD_DRV_LOG(DEBUG, "Pointer to txq is NULL"); + return; + } + + txe = txq->sw_ring; + size = sizeof(struct idpf_flex_tx_desc) * txq->nb_tx_desc; + for (i = 0; i < size; i++) + ((volatile char *)txq->tx_ring)[i] = 0; + + prev = (uint16_t)(txq->nb_tx_desc - 1); + for (i = 0; i < txq->nb_tx_desc; i++) { + txq->tx_ring[i].qw1.cmd_dtype = + rte_cpu_to_le_16(IDPF_TX_DESC_DTYPE_DESC_DONE); + txe[i].mbuf = NULL; + txe[i].last_id = i; + txe[prev].next_id = i; + prev = i; + } + + txq->tx_tail = 0; + txq->nb_used = 0; + + txq->last_desc_cleaned = txq->nb_tx_desc - 1; + txq->nb_free = txq->nb_tx_desc - 1; + + txq->next_dd = txq->rs_thresh - 1; + txq->next_rs = txq->rs_thresh - 1; +} + +static int +idpf_rx_single_queue_setup(struct rte_eth_dev *dev, uint16_t queue_idx, + uint16_t nb_desc, unsigned int socket_id, + const struct rte_eth_rxconf *rx_conf, + struct rte_mempool *mp) +{ + struct idpf_vport *vport = dev->data->dev_private; + struct idpf_adapter *adapter = vport->adapter; + struct idpf_hw *hw = &adapter->hw; + struct idpf_rx_queue *rxq; + const struct rte_memzone *mz; + uint16_t rx_free_thresh; + uint32_t ring_size; + uint16_t len; + uint64_t offloads; + + PMD_INIT_FUNC_TRACE(); + + if (nb_desc % IDPF_ALIGN_RING_DESC != 0 || + nb_desc > IDPF_MAX_RING_DESC || + nb_desc < IDPF_MIN_RING_DESC) { + PMD_INIT_LOG(ERR, "Number (%u) of receive descriptors is invalid", + nb_desc); + return -EINVAL; + } + + offloads = rx_conf->offloads | dev->data->dev_conf.rxmode.offloads; + + /* Check free threshold */ + rx_free_thresh = (rx_conf->rx_free_thresh == 0) ? + IDPF_DEFAULT_RX_FREE_THRESH : + rx_conf->rx_free_thresh; + if (check_rx_thresh(nb_desc, rx_free_thresh)) + return -EINVAL; + + /* Free memory if needed */ + if (dev->data->rx_queues[queue_idx]) { + idpf_rx_queue_release(dev->data->rx_queues[queue_idx]); + dev->data->rx_queues[queue_idx] = NULL; + } + + /* Setup Rx description queue */ + rxq = rte_zmalloc_socket("idpf rxq", + sizeof(struct idpf_rx_queue), + RTE_CACHE_LINE_SIZE, + socket_id); + if (!rxq) { + PMD_INIT_LOG(ERR, "Failed to allocate memory for rx queue data structure"); + return -ENOMEM; + } + + rxq->mp = mp; + rxq->nb_rx_desc = nb_desc; + rxq->rx_free_thresh = rx_free_thresh; + rxq->queue_id = vport->chunks_info.rx_start_qid + queue_idx; + rxq->port_id = dev->data->port_id; + rxq->rx_deferred_start = rx_conf->rx_deferred_start; + rxq->rx_hdr_len = 0; + rxq->adapter = adapter; + rxq->offloads = offloads; + + len = rte_pktmbuf_data_room_size(rxq->mp) - RTE_PKTMBUF_HEADROOM; + rxq->rx_buf_len = len; + + len = nb_desc + IDPF_RX_MAX_BURST; + rxq->sw_ring = + rte_zmalloc_socket("idpf rxq sw ring", + sizeof(struct rte_mbuf *) * len, + RTE_CACHE_LINE_SIZE, + socket_id); + if (!rxq->sw_ring) { + PMD_INIT_LOG(ERR, "Failed to allocate memory for SW ring"); + rte_free(rxq); + return -ENOMEM; + } + + /* Allocate a liitle more to support bulk allocate. */ + len = nb_desc + IDPF_RX_MAX_BURST; + ring_size = RTE_ALIGN(len * + sizeof(struct virtchnl2_singleq_rx_buf_desc), + IDPF_DMA_MEM_ALIGN); + mz = rte_eth_dma_zone_reserve(dev, "rx ring", queue_idx, + ring_size, IDPF_RING_BASE_ALIGN, + socket_id); + if (!mz) { + PMD_INIT_LOG(ERR, "Failed to reserve DMA memory for RX buffer queue."); + rte_free(rxq->sw_ring); + rte_free(rxq); + return -ENOMEM; + } + + /* Zero all the descriptors in the ring. */ + memset(mz->addr, 0, ring_size); + rxq->rx_ring_phys_addr = mz->iova; + rxq->rx_ring = mz->addr; + + rxq->mz = mz; + reset_single_rx_queue(rxq); + rxq->q_set = true; + dev->data->rx_queues[queue_idx] = rxq; + rxq->qrx_tail = hw->hw_addr + (vport->chunks_info.rx_qtail_start + + queue_idx * vport->chunks_info.rx_qtail_spacing); + rxq->ops = &def_rxq_ops; + + return 0; +} + +int +idpf_rx_queue_setup(struct rte_eth_dev *dev, uint16_t queue_idx, + uint16_t nb_desc, unsigned int socket_id, + const struct rte_eth_rxconf *rx_conf, + struct rte_mempool *mp) +{ + struct idpf_vport *vport = dev->data->dev_private; + + if (vport->rxq_model == VIRTCHNL2_QUEUE_MODEL_SINGLE) + return idpf_rx_single_queue_setup(dev, queue_idx, nb_desc, + socket_id, rx_conf, mp); + else + return -1; +} + +static int +idpf_tx_single_queue_setup(struct rte_eth_dev *dev, uint16_t queue_idx, + uint16_t nb_desc, unsigned int socket_id, + const struct rte_eth_txconf *tx_conf) +{ + struct idpf_vport *vport = dev->data->dev_private; + struct idpf_adapter *adapter = vport->adapter; + struct idpf_hw *hw = &adapter->hw; + struct idpf_tx_queue *txq; + const struct rte_memzone *mz; + uint32_t ring_size; + uint16_t tx_rs_thresh, tx_free_thresh; + uint64_t offloads; + + PMD_INIT_FUNC_TRACE(); + + offloads = tx_conf->offloads | dev->data->dev_conf.txmode.offloads; + + if (nb_desc % IDPF_ALIGN_RING_DESC != 0 || + nb_desc > IDPF_MAX_RING_DESC || + nb_desc < IDPF_MIN_RING_DESC) { + PMD_INIT_LOG(ERR, "Number (%u) of transmit descriptors is invalid", + nb_desc); + return -EINVAL; + } + + tx_rs_thresh = (uint16_t)((tx_conf->tx_rs_thresh) ? + tx_conf->tx_rs_thresh : IDPF_DEFAULT_TX_RS_THRESH); + tx_free_thresh = (uint16_t)((tx_conf->tx_free_thresh) ? + tx_conf->tx_free_thresh : IDPF_DEFAULT_TX_FREE_THRESH); + if (check_tx_thresh(nb_desc, tx_rs_thresh, tx_free_thresh)) + return -EINVAL; + + /* Free memory if needed. */ + if (dev->data->tx_queues[queue_idx]) { + idpf_tx_queue_release(dev->data->tx_queues[queue_idx]); + dev->data->tx_queues[queue_idx] = NULL; + } + + /* Allocate the TX queue data structure. */ + txq = rte_zmalloc_socket("idpf txq", + sizeof(struct idpf_tx_queue), + RTE_CACHE_LINE_SIZE, + socket_id); + if (!txq) { + PMD_INIT_LOG(ERR, "Failed to allocate memory for tx queue structure"); + return -ENOMEM; + } + + /* TODO: vlan offload */ + + txq->nb_tx_desc = nb_desc; + txq->rs_thresh = tx_rs_thresh; + txq->free_thresh = tx_free_thresh; + txq->queue_id = vport->chunks_info.tx_start_qid + queue_idx; + txq->port_id = dev->data->port_id; + txq->offloads = offloads; + txq->tx_deferred_start = tx_conf->tx_deferred_start; + + /* Allocate software ring */ + txq->sw_ring = + rte_zmalloc_socket("idpf tx sw ring", + sizeof(struct idpf_tx_entry) * nb_desc, + RTE_CACHE_LINE_SIZE, + socket_id); + if (!txq->sw_ring) { + PMD_INIT_LOG(ERR, "Failed to allocate memory for SW TX ring"); + rte_free(txq); + return -ENOMEM; + } + + /* Allocate TX hardware ring descriptors. */ + ring_size = sizeof(struct idpf_flex_tx_desc) * nb_desc; + ring_size = RTE_ALIGN(ring_size, IDPF_DMA_MEM_ALIGN); + mz = rte_eth_dma_zone_reserve(dev, "tx_ring", queue_idx, + ring_size, IDPF_RING_BASE_ALIGN, + socket_id); + if (!mz) { + PMD_INIT_LOG(ERR, "Failed to reserve DMA memory for TX"); + rte_free(txq->sw_ring); + rte_free(txq); + return -ENOMEM; + } + + txq->tx_ring_phys_addr = mz->iova; + txq->tx_ring = (struct idpf_flex_tx_desc *)mz->addr; + + txq->mz = mz; + reset_single_tx_queue(txq); + txq->q_set = true; + dev->data->tx_queues[queue_idx] = txq; + txq->qtx_tail = hw->hw_addr + (vport->chunks_info.tx_qtail_start + + queue_idx * vport->chunks_info.tx_qtail_spacing); + txq->ops = &def_txq_ops; + + return 0; +} + +int +idpf_tx_queue_setup(struct rte_eth_dev *dev, uint16_t queue_idx, + uint16_t nb_desc, unsigned int socket_id, + const struct rte_eth_txconf *tx_conf) +{ + struct idpf_vport *vport = dev->data->dev_private; + + if (vport->txq_model == VIRTCHNL2_QUEUE_MODEL_SINGLE) + return idpf_tx_single_queue_setup(dev, queue_idx, nb_desc, + socket_id, tx_conf); + else + return -1; +} + +void +idpf_dev_rx_queue_release(struct rte_eth_dev *dev, uint16_t qid) +{ + idpf_rx_queue_release(dev->data->rx_queues[qid]); +} + +void +idpf_dev_tx_queue_release(struct rte_eth_dev *dev, uint16_t qid) +{ + idpf_tx_queue_release(dev->data->tx_queues[qid]); +} diff --git a/drivers/net/idpf/idpf_rxtx.h b/drivers/net/idpf/idpf_rxtx.h new file mode 100644 index 0000000000..69a1fa6348 --- /dev/null +++ b/drivers/net/idpf/idpf_rxtx.h @@ -0,0 +1,186 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2022 Intel Corporation + */ + +#ifndef _IDPF_RXTX_H_ +#define _IDPF_RXTX_H_ + +#include "idpf_osdep.h" +#include "idpf_type.h" +#include "idpf_devids.h" +#include "idpf_lan_txrx.h" +#include "idpf_lan_pf_regs.h" +#include "virtchnl.h" +#include "virtchnl2.h" +#include "virtchnl2_lan_desc.h" + +#include "idpf_ethdev.h" + +/* In QLEN must be whole number of 32 descriptors. */ +#define IDPF_ALIGN_RING_DESC 32 +#define IDPF_MIN_RING_DESC 32 +#define IDPF_MAX_RING_DESC 4096 +#define IDPF_DMA_MEM_ALIGN 4096 +/* Base address of the HW descriptor ring should be 128B aligned. */ +#define IDPF_RING_BASE_ALIGN 128 + +/* used for Rx Bulk Allocate */ +#define IDPF_RX_MAX_BURST 32 +#define IDPF_TX_MAX_BURST 32 + +#define IDPF_DEFAULT_RX_FREE_THRESH 32 + +/* used for Vector PMD */ +#define IDPF_VPMD_RX_MAX_BURST 32 +#define IDPF_VPMD_TX_MAX_BURST 32 +#define IDPF_VPMD_DESCS_PER_LOOP 4 +#define IDPF_RXQ_REARM_THRESH 64 + +#define IDPF_DEFAULT_TX_RS_THRESH 32 +#define IDPF_DEFAULT_TX_FREE_THRESH 32 + +#define IDPF_MIN_TSO_MSS 88 +#define IDPF_MAX_TSO_MSS 9728 +#define IDPF_MAX_TSO_FRAME_SIZE 262143 +#define IDPF_TX_MAX_MTU_SEG 10 + +#define IDPF_TX_OFFLOAD_NOTSUP_MASK \ + (RTE_MBUF_F_TX_OFFLOAD_MASK ^ IDPF_TX_OFFLOAD_MASK) + +struct idpf_rx_queue { + struct idpf_adapter *adapter; /* the adapter this queue belongs to */ + struct rte_mempool *mp; /* mbuf pool to populate Rx ring */ + const struct rte_memzone *mz; /* memzone for Rx ring */ + volatile void *rx_ring; + struct rte_mbuf **sw_ring; /* address of SW ring */ + uint64_t rx_ring_phys_addr; /* Rx ring DMA address */ + + uint16_t nb_rx_desc; /* ring length */ + uint16_t rx_tail; /* current value of tail */ + volatile uint8_t *qrx_tail; /* register address of tail */ + uint16_t rx_free_thresh; /* max free RX desc to hold */ + uint16_t nb_rx_hold; /* number of held free RX desc */ + struct rte_mbuf *pkt_first_seg; /* first segment of current packet */ + struct rte_mbuf *pkt_last_seg; /* last segment of current packet */ + struct rte_mbuf fake_mbuf; /* dummy mbuf */ + + /* used for VPMD */ + uint16_t rxrearm_nb; /* number of remaining to be re-armed */ + uint16_t rxrearm_start; /* the idx we start the re-arming from */ + uint64_t mbuf_initializer; /* value to init mbufs */ + + /* for rx bulk */ + uint16_t rx_nb_avail; /* number of staged packets ready */ + uint16_t rx_next_avail; /* index of next staged packets */ + uint16_t rx_free_trigger; /* triggers rx buffer allocation */ + struct rte_mbuf *rx_stage[IDPF_RX_MAX_BURST * 2]; /* store mbuf */ + + uint16_t port_id; /* device port ID */ + uint16_t queue_id; /* Rx queue index */ + uint16_t rx_buf_len; /* The packet buffer size */ + uint16_t rx_hdr_len; /* The header buffer size */ + uint16_t max_pkt_len; /* Maximum packet length */ + uint8_t rxdid; + + bool q_set; /* if rx queue has been configured */ + bool q_started; /* if rx queue has been started */ + bool rx_deferred_start; /* don't start this queue in dev start */ + const struct idpf_rxq_ops *ops; + + /* only valid for split queue mode */ + uint8_t expected_gen_id; + struct idpf_rx_queue *bufq1; + struct idpf_rx_queue *bufq2; + + uint64_t offloads; + uint32_t hw_register_set; +}; + +struct idpf_tx_entry { + struct rte_mbuf *mbuf; + uint16_t next_id; + uint16_t last_id; +}; + +struct idpf_tx_vec_entry { + struct rte_mbuf *mbuf; +}; + +/* Structure associated with each TX queue. */ +struct idpf_tx_queue { + const struct rte_memzone *mz; /* memzone for Tx ring */ + volatile struct idpf_flex_tx_desc *tx_ring; /* Tx ring virtual address */ + volatile union { + struct idpf_flex_tx_sched_desc *desc_ring; + struct idpf_splitq_tx_compl_desc *compl_ring; + }; + uint64_t tx_ring_phys_addr; /* Tx ring DMA address */ + struct idpf_tx_entry *sw_ring; /* address array of SW ring */ + + uint16_t nb_tx_desc; /* ring length */ + uint16_t tx_tail; /* current value of tail */ + volatile uint8_t *qtx_tail; /* register address of tail */ + /* number of used desc since RS bit set */ + uint16_t nb_used; + uint16_t nb_free; + uint16_t last_desc_cleaned; /* last desc have been cleaned*/ + uint16_t free_thresh; + uint16_t rs_thresh; + + uint16_t port_id; + uint16_t queue_id; + uint64_t offloads; + uint16_t next_dd; /* next to set RS, for VPMD */ + uint16_t next_rs; /* next to check DD, for VPMD */ + + bool q_set; /* if tx queue has been configured */ + bool q_started; /* if tx queue has been started */ + bool tx_deferred_start; /* don't start this queue in dev start */ + const struct idpf_txq_ops *ops; +#define IDPF_TX_FLAGS_VLAN_TAG_LOC_L2TAG1 BIT(0) +#define IDPF_TX_FLAGS_VLAN_TAG_LOC_L2TAG2 BIT(1) + uint8_t vlan_flag; + + /* only valid for split queue mode */ + uint16_t sw_nb_desc; + uint16_t sw_tail; + void **txqs; + uint32_t tx_start_qid; + uint8_t expected_gen_id; + struct idpf_tx_queue *complq; +}; + +/* Offload features */ +union idpf_tx_offload { + uint64_t data; + struct { + uint64_t l2_len:7; /* L2 (MAC) Header Length. */ + uint64_t l3_len:9; /* L3 (IP) Header Length. */ + uint64_t l4_len:8; /* L4 Header Length. */ + uint64_t tso_segsz:16; /* TCP TSO segment size */ + /* uint64_t unused : 24; */ + }; +}; + +struct idpf_rxq_ops { + void (*release_mbufs)(struct idpf_rx_queue *rxq); +}; + +struct idpf_txq_ops { + void (*release_mbufs)(struct idpf_tx_queue *txq); +}; + +int idpf_rx_queue_setup(struct rte_eth_dev *dev, uint16_t queue_idx, + uint16_t nb_desc, unsigned int socket_id, + const struct rte_eth_rxconf *rx_conf, + struct rte_mempool *mp); +int idpf_rx_queue_init(struct rte_eth_dev *dev, uint16_t rx_queue_id); +void idpf_dev_rx_queue_release(struct rte_eth_dev *dev, uint16_t qid); + +int idpf_tx_queue_setup(struct rte_eth_dev *dev, uint16_t queue_idx, + uint16_t nb_desc, unsigned int socket_id, + const struct rte_eth_txconf *tx_conf); +int idpf_tx_queue_init(struct rte_eth_dev *dev, uint16_t tx_queue_id); +void idpf_dev_tx_queue_release(struct rte_eth_dev *dev, uint16_t qid); + +#endif /* _IDPF_RXTX_H_ */ diff --git a/drivers/net/idpf/idpf_vchnl.c b/drivers/net/idpf/idpf_vchnl.c index ef0288ff45..02a55e0658 100644 --- a/drivers/net/idpf/idpf_vchnl.c +++ b/drivers/net/idpf/idpf_vchnl.c @@ -21,6 +21,7 @@ #include #include "idpf_ethdev.h" +#include "idpf_rxtx.h" #include "idpf_prototype.h" @@ -469,6 +470,254 @@ idpf_vc_destroy_vport(struct idpf_vport *vport) return err; } +#define IDPF_RX_BUF_STRIDE 64 +int +idpf_vc_config_rxqs(struct idpf_vport *vport) +{ + struct idpf_adapter *adapter = vport->adapter; + struct idpf_rx_queue **rxq = + (struct idpf_rx_queue **)vport->dev_data->rx_queues; + struct virtchnl2_config_rx_queues *vc_rxqs = NULL; + struct virtchnl2_rxq_info *rxq_info; + struct idpf_cmd_info args; + uint16_t total_qs, num_qs; + int size, err, i; + int k = 0; + + total_qs = vport->num_rx_q; + while (total_qs) { + if (total_qs > adapter->max_rxq_per_msg) { + num_qs = adapter->max_rxq_per_msg; + total_qs -= adapter->max_rxq_per_msg; + } else { + num_qs = total_qs; + total_qs = 0; + } + + size = sizeof(*vc_rxqs) + (num_qs - 1) * + sizeof(struct virtchnl2_rxq_info); + vc_rxqs = rte_zmalloc("cfg_rxqs", size, 0); + if (vc_rxqs == NULL) { + PMD_DRV_LOG(ERR, "Failed to allocate virtchnl2_config_rx_queues"); + err = -ENOMEM; + break; + } + vc_rxqs->vport_id = vport->vport_id; + vc_rxqs->num_qinfo = num_qs; + if (vport->rxq_model == VIRTCHNL2_QUEUE_MODEL_SINGLE) { + for (i = 0; i < num_qs; i++, k++) { + rxq_info = &vc_rxqs->qinfo[i]; + rxq_info->dma_ring_addr = rxq[k]->rx_ring_phys_addr; + rxq_info->type = VIRTCHNL2_QUEUE_TYPE_RX; + rxq_info->queue_id = rxq[k]->queue_id; + rxq_info->model = VIRTCHNL2_QUEUE_MODEL_SINGLE; + rxq_info->data_buffer_size = rxq[k]->rx_buf_len; + rxq_info->max_pkt_size = vport->max_pkt_len; + + rxq_info->desc_ids = VIRTCHNL2_RXDID_2_FLEX_SQ_NIC_M; + rxq_info->qflags |= VIRTCHNL2_RX_DESC_SIZE_32BYTE; + + rxq_info->ring_len = rxq[k]->nb_rx_desc; + } + } else { + return -1; + } + memset(&args, 0, sizeof(args)); + args.ops = VIRTCHNL2_OP_CONFIG_RX_QUEUES; + args.in_args = (uint8_t *)vc_rxqs; + args.in_args_size = size; + args.out_buffer = adapter->mbx_resp; + args.out_size = IDPF_DFLT_MBX_BUF_SIZE; + + err = idpf_execute_vc_cmd(adapter, &args); + rte_free(vc_rxqs); + if (err) { + PMD_DRV_LOG(ERR, "Failed to execute command of VIRTCHNL2_OP_CONFIG_RX_QUEUES"); + break; + } + } + + return err; +} + +int +idpf_vc_config_rxq(struct idpf_vport *vport, uint16_t rxq_id) +{ + struct idpf_adapter *adapter = vport->adapter; + struct idpf_rx_queue **rxq = + (struct idpf_rx_queue **)vport->dev_data->rx_queues; + struct virtchnl2_config_rx_queues *vc_rxqs = NULL; + struct virtchnl2_rxq_info *rxq_info; + struct idpf_cmd_info args; + uint16_t num_qs; + int size, err; + + if (vport->rxq_model == VIRTCHNL2_QUEUE_MODEL_SINGLE) + num_qs = IDPF_RXQ_PER_GRP; + else + num_qs = IDPF_RXQ_PER_GRP + IDPF_RX_BUFQ_PER_GRP; + + size = sizeof(*vc_rxqs) + (num_qs - 1) * + sizeof(struct virtchnl2_rxq_info); + vc_rxqs = rte_zmalloc("cfg_rxqs", size, 0); + if (vc_rxqs == NULL) { + PMD_DRV_LOG(ERR, "Failed to allocate virtchnl2_config_rx_queues"); + err = -ENOMEM; + return err; + } + vc_rxqs->vport_id = vport->vport_id; + vc_rxqs->num_qinfo = num_qs; + if (vport->rxq_model == VIRTCHNL2_QUEUE_MODEL_SINGLE) { + rxq_info = &vc_rxqs->qinfo[0]; + rxq_info->dma_ring_addr = rxq[rxq_id]->rx_ring_phys_addr; + rxq_info->type = VIRTCHNL2_QUEUE_TYPE_RX; + rxq_info->queue_id = rxq[rxq_id]->queue_id; + rxq_info->model = VIRTCHNL2_QUEUE_MODEL_SINGLE; + rxq_info->data_buffer_size = rxq[rxq_id]->rx_buf_len; + rxq_info->max_pkt_size = vport->max_pkt_len; + + rxq_info->desc_ids = VIRTCHNL2_RXDID_2_FLEX_SQ_NIC_M; + rxq_info->qflags |= VIRTCHNL2_RX_DESC_SIZE_32BYTE; + + rxq_info->ring_len = rxq[rxq_id]->nb_rx_desc; + } else { + return -1; + } + + memset(&args, 0, sizeof(args)); + args.ops = VIRTCHNL2_OP_CONFIG_RX_QUEUES; + args.in_args = (uint8_t *)vc_rxqs; + args.in_args_size = size; + args.out_buffer = adapter->mbx_resp; + args.out_size = IDPF_DFLT_MBX_BUF_SIZE; + + err = idpf_execute_vc_cmd(adapter, &args); + rte_free(vc_rxqs); + if (err) + PMD_DRV_LOG(ERR, "Failed to execute command of VIRTCHNL2_OP_CONFIG_RX_QUEUES"); + + return err; +} + +int +idpf_vc_config_txqs(struct idpf_vport *vport) +{ + struct idpf_adapter *adapter = vport->adapter; + struct idpf_tx_queue **txq = + (struct idpf_tx_queue **)vport->dev_data->tx_queues; + struct virtchnl2_config_tx_queues *vc_txqs = NULL; + struct virtchnl2_txq_info *txq_info; + struct idpf_cmd_info args; + uint16_t total_qs, num_qs; + int size, err, i; + int k = 0; + + total_qs = vport->num_tx_q; + while (total_qs) { + if (total_qs > adapter->max_txq_per_msg) { + num_qs = adapter->max_txq_per_msg; + total_qs -= adapter->max_txq_per_msg; + } else { + num_qs = total_qs; + total_qs = 0; + } + size = sizeof(*vc_txqs) + (num_qs - 1) * + sizeof(struct virtchnl2_txq_info); + vc_txqs = rte_zmalloc("cfg_txqs", size, 0); + if (vc_txqs == NULL) { + PMD_DRV_LOG(ERR, "Failed to allocate virtchnl2_config_tx_queues"); + err = -ENOMEM; + break; + } + vc_txqs->vport_id = vport->vport_id; + vc_txqs->num_qinfo = num_qs; + if (vport->txq_model == VIRTCHNL2_QUEUE_MODEL_SINGLE) { + for (i = 0; i < num_qs; i++, k++) { + txq_info = &vc_txqs->qinfo[i]; + txq_info->dma_ring_addr = txq[k]->tx_ring_phys_addr; + txq_info->type = VIRTCHNL2_QUEUE_TYPE_TX; + txq_info->queue_id = txq[k]->queue_id; + txq_info->model = VIRTCHNL2_QUEUE_MODEL_SINGLE; + txq_info->sched_mode = VIRTCHNL2_TXQ_SCHED_MODE_QUEUE; + txq_info->ring_len = txq[k]->nb_tx_desc; + } + } else { + return -1; + } + + memset(&args, 0, sizeof(args)); + args.ops = VIRTCHNL2_OP_CONFIG_TX_QUEUES; + args.in_args = (uint8_t *)vc_txqs; + args.in_args_size = size; + args.out_buffer = adapter->mbx_resp; + args.out_size = IDPF_DFLT_MBX_BUF_SIZE; + + err = idpf_execute_vc_cmd(adapter, &args); + rte_free(vc_txqs); + if (err) { + PMD_DRV_LOG(ERR, "Failed to execute command of VIRTCHNL2_OP_CONFIG_TX_QUEUES"); + break; + } + } + + return err; +} + +int +idpf_vc_config_txq(struct idpf_vport *vport, uint16_t txq_id) +{ + struct idpf_adapter *adapter = vport->adapter; + struct idpf_tx_queue **txq = + (struct idpf_tx_queue **)vport->dev_data->tx_queues; + struct virtchnl2_config_tx_queues *vc_txqs = NULL; + struct virtchnl2_txq_info *txq_info; + struct idpf_cmd_info args; + uint16_t num_qs; + int size, err; + + if (vport->txq_model == VIRTCHNL2_QUEUE_MODEL_SINGLE) + num_qs = IDPF_TXQ_PER_GRP; + else + num_qs = IDPF_TXQ_PER_GRP + IDPF_TX_COMPLQ_PER_GRP; + + size = sizeof(*vc_txqs) + (num_qs - 1) * + sizeof(struct virtchnl2_txq_info); + vc_txqs = rte_zmalloc("cfg_txqs", size, 0); + if (vc_txqs == NULL) { + PMD_DRV_LOG(ERR, "Failed to allocate virtchnl2_config_tx_queues"); + err = -ENOMEM; + return err; + } + vc_txqs->vport_id = vport->vport_id; + vc_txqs->num_qinfo = num_qs; + + if (vport->txq_model == VIRTCHNL2_QUEUE_MODEL_SINGLE) { + txq_info = &vc_txqs->qinfo[0]; + txq_info->dma_ring_addr = txq[txq_id]->tx_ring_phys_addr; + txq_info->type = VIRTCHNL2_QUEUE_TYPE_TX; + txq_info->queue_id = txq[txq_id]->queue_id; + txq_info->model = VIRTCHNL2_QUEUE_MODEL_SINGLE; + txq_info->sched_mode = VIRTCHNL2_TXQ_SCHED_MODE_QUEUE; + txq_info->ring_len = txq[txq_id]->nb_tx_desc; + } else { + return -1; + } + + memset(&args, 0, sizeof(args)); + args.ops = VIRTCHNL2_OP_CONFIG_TX_QUEUES; + args.in_args = (uint8_t *)vc_txqs; + args.in_args_size = size; + args.out_buffer = adapter->mbx_resp; + args.out_size = IDPF_DFLT_MBX_BUF_SIZE; + + err = idpf_execute_vc_cmd(adapter, &args); + rte_free(vc_txqs); + if (err) + PMD_DRV_LOG(ERR, "Failed to execute command of VIRTCHNL2_OP_CONFIG_TX_QUEUES"); + + return err; +} + int idpf_vc_ena_dis_vport(struct idpf_vport *vport, bool enable) { diff --git a/drivers/net/idpf/meson.build b/drivers/net/idpf/meson.build index bf8bf58ef5..832f887296 100644 --- a/drivers/net/idpf/meson.build +++ b/drivers/net/idpf/meson.build @@ -12,5 +12,6 @@ deps += ['common_idpf', 'security', 'cryptodev'] sources = files( 'idpf_ethdev.c', + 'idpf_rxtx.c', 'idpf_vchnl.c', ) -- 2.34.1