From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id 0F39AA0613 for ; Thu, 26 Sep 2019 08:29:59 +0200 (CEST) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id 455963423; Thu, 26 Sep 2019 08:29:57 +0200 (CEST) Received: from mellanox.co.il (mail-il-dmz.mellanox.com [193.47.165.129]) by dpdk.org (Postfix) with ESMTP id 0A0DB324D for ; Thu, 26 Sep 2019 08:29:54 +0200 (CEST) Received: from Internal Mail-Server by MTLPINE1 (envelope-from orika@mellanox.com) with ESMTPS (AES256-SHA encrypted); 26 Sep 2019 09:29:54 +0300 Received: from pegasus04.mtr.labs.mlnx. (pegasus04.mtr.labs.mlnx [10.210.16.126]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id x8Q6TmlG012493; Thu, 26 Sep 2019 09:29:53 +0300 From: Ori Kam To: Thomas Monjalon , Ferruh Yigit , Andrew Rybchenko Cc: dev@dpdk.org, orika@mellanox.com, jingjing.wu@intel.com, stephen@networkplumber.org Date: Thu, 26 Sep 2019 06:28:57 +0000 Message-Id: <1569479349-36962-2-git-send-email-orika@mellanox.com> X-Mailer: git-send-email 1.8.3.1 In-Reply-To: <1569479349-36962-1-git-send-email-orika@mellanox.com> References: <1569479349-36962-1-git-send-email-orika@mellanox.com> Subject: [dpdk-dev] [PATCH 01/13] ethdev: support setup function for hairpin queue 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" This commit introduce the RX/TX hairpin setup function. Hairpin is RX/TX queue that is used by the nic in order to offload wire to wire traffic. Each hairpin queue is binded to one or more queues from other type. For example TX hairpin queue should be binded to at least 1 RX hairpin queue and vice versa. Signed-off-by: Ori Kam --- lib/librte_ethdev/rte_ethdev.c | 213 +++++++++++++++++++++++++++++++ lib/librte_ethdev/rte_ethdev.h | 145 +++++++++++++++++++++ lib/librte_ethdev/rte_ethdev_core.h | 18 +++ lib/librte_ethdev/rte_ethdev_version.map | 4 + 4 files changed, 380 insertions(+) diff --git a/lib/librte_ethdev/rte_ethdev.c b/lib/librte_ethdev/rte_ethdev.c index 30b0c78..4021f38 100644 --- a/lib/librte_ethdev/rte_ethdev.c +++ b/lib/librte_ethdev/rte_ethdev.c @@ -1701,6 +1701,115 @@ struct rte_eth_dev * } int +rte_eth_rx_hairpin_queue_setup(uint16_t port_id, uint16_t rx_queue_id, + uint16_t nb_rx_desc, unsigned int socket_id, + const struct rte_eth_rxconf *rx_conf, + const struct rte_eth_hairpin_conf *hairpin_conf) +{ + int ret; + struct rte_eth_dev *dev; + struct rte_eth_dev_info dev_info; + struct rte_eth_rxconf local_conf; + void **rxq; + + RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -EINVAL); + + dev = &rte_eth_devices[port_id]; + if (rx_queue_id >= dev->data->nb_rx_queues) { + RTE_ETHDEV_LOG(ERR, "Invalid RX queue_id=%u\n", rx_queue_id); + return -EINVAL; + } + + RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->dev_infos_get, -ENOTSUP); + RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->rx_hairpin_queue_setup, + -ENOTSUP); + + rte_eth_dev_info_get(port_id, &dev_info); + + /* Use default specified by driver, if nb_rx_desc is zero */ + if (nb_rx_desc == 0) { + nb_rx_desc = dev_info.default_rxportconf.ring_size; + /* If driver default is also zero, fall back on EAL default */ + if (nb_rx_desc == 0) + nb_rx_desc = RTE_ETH_DEV_FALLBACK_RX_RINGSIZE; + } + + if (nb_rx_desc > dev_info.rx_desc_lim.nb_max || + nb_rx_desc < dev_info.rx_desc_lim.nb_min || + nb_rx_desc % dev_info.rx_desc_lim.nb_align != 0) { + + RTE_ETHDEV_LOG(ERR, + "Invalid value for nb_rx_desc(=%hu), should be: " + "<= %hu, >= %hu, and a product of %hu\n", + nb_rx_desc, dev_info.rx_desc_lim.nb_max, + dev_info.rx_desc_lim.nb_min, + dev_info.rx_desc_lim.nb_align); + return -EINVAL; + } + + if (dev->data->dev_started && + !(dev_info.dev_capa & + RTE_ETH_DEV_CAPA_RUNTIME_RX_QUEUE_SETUP)) + return -EBUSY; + + if (dev->data->dev_started && + (dev->data->rx_queue_state[rx_queue_id] != + RTE_ETH_QUEUE_STATE_STOPPED)) + return -EBUSY; + + rxq = dev->data->rx_queues; + if (rxq[rx_queue_id]) { + RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->rx_queue_release, + -ENOTSUP); + (*dev->dev_ops->rx_queue_release)(rxq[rx_queue_id]); + rxq[rx_queue_id] = NULL; + } + + if (rx_conf == NULL) + rx_conf = &dev_info.default_rxconf; + + local_conf = *rx_conf; + + /* + * If an offloading has already been enabled in + * rte_eth_dev_configure(), it has been enabled on all queues, + * so there is no need to enable it in this queue again. + * The local_conf.offloads input to underlying PMD only carries + * those offloadings which are only enabled on this queue and + * not enabled on all queues. + */ + local_conf.offloads &= ~dev->data->dev_conf.rxmode.offloads; + + /* + * New added offloadings for this queue are those not enabled in + * rte_eth_dev_configure() and they must be per-queue type. + * A pure per-port offloading can't be enabled on a queue while + * disabled on another queue. A pure per-port offloading can't + * be enabled for any queue as new added one if it hasn't been + * enabled in rte_eth_dev_configure(). + */ + if ((local_conf.offloads & dev_info.rx_queue_offload_capa) != + local_conf.offloads) { + RTE_ETHDEV_LOG(ERR, + "Ethdev port_id=%d rx_queue_id=%d, " + "new added offloads 0x%"PRIx64" must be " + "within per-queue offload capabilities " + "0x%"PRIx64" in %s()\n", + port_id, rx_queue_id, local_conf.offloads, + dev_info.rx_queue_offload_capa, + __func__); + return -EINVAL; + } + + ret = (*dev->dev_ops->rx_hairpin_queue_setup)(dev, rx_queue_id, + nb_rx_desc, socket_id, + &local_conf, + hairpin_conf); + + return eth_err(port_id, ret); +} + +int rte_eth_tx_queue_setup(uint16_t port_id, uint16_t tx_queue_id, uint16_t nb_tx_desc, unsigned int socket_id, const struct rte_eth_txconf *tx_conf) @@ -1799,6 +1908,110 @@ struct rte_eth_dev * tx_queue_id, nb_tx_desc, socket_id, &local_conf)); } +int +rte_eth_tx_hairpin_queue_setup(uint16_t port_id, uint16_t tx_queue_id, + uint16_t nb_tx_desc, unsigned int socket_id, + const struct rte_eth_txconf *tx_conf, + const struct rte_eth_hairpin_conf *hairpin_conf) +{ + struct rte_eth_dev *dev; + struct rte_eth_dev_info dev_info; + struct rte_eth_txconf local_conf; + void **txq; + + RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -EINVAL); + + dev = &rte_eth_devices[port_id]; + if (tx_queue_id >= dev->data->nb_tx_queues) { + RTE_ETHDEV_LOG(ERR, "Invalid TX queue_id=%u\n", tx_queue_id); + return -EINVAL; + } + + RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->dev_infos_get, -ENOTSUP); + RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->tx_hairpin_queue_setup, + -ENOTSUP); + + rte_eth_dev_info_get(port_id, &dev_info); + + /* Use default specified by driver, if nb_tx_desc is zero */ + if (nb_tx_desc == 0) { + nb_tx_desc = dev_info.default_txportconf.ring_size; + /* If driver default is zero, fall back on EAL default */ + if (nb_tx_desc == 0) + nb_tx_desc = RTE_ETH_DEV_FALLBACK_TX_RINGSIZE; + } + if (nb_tx_desc > dev_info.tx_desc_lim.nb_max || + nb_tx_desc < dev_info.tx_desc_lim.nb_min || + nb_tx_desc % dev_info.tx_desc_lim.nb_align != 0) { + RTE_ETHDEV_LOG(ERR, + "Invalid value for nb_tx_desc(=%hu), " + "should be: <= %hu, >= %hu, and a product of " + " %hu\n", + nb_tx_desc, dev_info.tx_desc_lim.nb_max, + dev_info.tx_desc_lim.nb_min, + dev_info.tx_desc_lim.nb_align); + return -EINVAL; + } + + if (dev->data->dev_started && + !(dev_info.dev_capa & + RTE_ETH_DEV_CAPA_RUNTIME_TX_QUEUE_SETUP)) + return -EBUSY; + + if (dev->data->dev_started && + (dev->data->tx_queue_state[tx_queue_id] != + RTE_ETH_QUEUE_STATE_STOPPED)) + return -EBUSY; + + txq = dev->data->tx_queues; + if (txq[tx_queue_id]) { + RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->tx_queue_release, + -ENOTSUP); + (*dev->dev_ops->tx_queue_release)(txq[tx_queue_id]); + txq[tx_queue_id] = NULL; + } + + if (tx_conf == NULL) + tx_conf = &dev_info.default_txconf; + + local_conf = *tx_conf; + + /* + * If an offloading has already been enabled in + * rte_eth_dev_configure(), it has been enabled on all queues, + * so there is no need to enable it in this queue again. + * The local_conf.offloads input to underlying PMD only carries + * those offloadings which are only enabled on this queue and + * not enabled on all queues. + */ + local_conf.offloads &= ~dev->data->dev_conf.txmode.offloads; + + /* + * New added offloadings for this queue are those not enabled in + * rte_eth_dev_configure() and they must be per-queue type. + * A pure per-port offloading can't be enabled on a queue while + * disabled on another queue. A pure per-port offloading can't + * be enabled for any queue as new added one if it hasn't been + * enabled in rte_eth_dev_configure(). + */ + if ((local_conf.offloads & dev_info.tx_queue_offload_capa) != + local_conf.offloads) { + RTE_ETHDEV_LOG(ERR, + "Ethdev port_id=%d tx_queue_id=%d, new added " + "offloads 0x%"PRIx64" must be within " + "per-queue offload capabilities 0x%"PRIx64" " + "in %s()\n", + port_id, tx_queue_id, local_conf.offloads, + dev_info.tx_queue_offload_capa, + __func__); + return -EINVAL; + } + + return eth_err(port_id, (*dev->dev_ops->tx_hairpin_queue_setup) + (dev, tx_queue_id, nb_tx_desc, socket_id, &local_conf, + hairpin_conf)); +} + void rte_eth_tx_buffer_drop_callback(struct rte_mbuf **pkts, uint16_t unsent, void *userdata __rte_unused) diff --git a/lib/librte_ethdev/rte_ethdev.h b/lib/librte_ethdev/rte_ethdev.h index 475dbda..b3b1597 100644 --- a/lib/librte_ethdev/rte_ethdev.h +++ b/lib/librte_ethdev/rte_ethdev.h @@ -803,6 +803,30 @@ struct rte_eth_txconf { uint64_t offloads; }; +#define RTE_ETH_MAX_HAIRPIN_PEERS 32 + +/** + * @warning + * @b EXPERIMENTAL: this API may change, or be removed, without prior notice + * + * A structure used to hold hairpin peer data. + */ +struct rte_eth_hairpin_peer { + uint16_t port; /**< Peer port. */ + uint16_t queue; /**< Peer queue. */ +}; + +/** + * @warning + * @b EXPERIMENTAL: this API may change, or be removed, without prior notice + * + * A structure used to configure hairpin binding. + */ +struct rte_eth_hairpin_conf { + uint16_t peer_n; /**< The number of peers. */ + struct rte_eth_hairpin_peer peers[RTE_ETH_MAX_HAIRPIN_PEERS]; +}; + /** * A structure contains information about HW descriptor ring limitations. */ @@ -1769,6 +1793,60 @@ int rte_eth_rx_queue_setup(uint16_t port_id, uint16_t rx_queue_id, struct rte_mempool *mb_pool); /** + * @warning + * @b EXPERIMENTAL: this API may change, or be removed, without prior notice + * + * Allocate and set up a hairpin receive queue for an Ethernet device. + * + * The function set up the selected queue to be used in hairpin. + * + * @param port_id + * The port identifier of the Ethernet device. + * @param rx_queue_id + * The index of the receive queue to set up. + * The value must be in the range [0, nb_rx_queue - 1] previously supplied + * to rte_eth_dev_configure(). + * @param nb_rx_desc + * The number of receive descriptors to allocate for the receive ring. + * @param socket_id + * The *socket_id* argument is the socket identifier in case of NUMA. + * The value can be *SOCKET_ID_ANY* if there is no NUMA constraint for + * the DMA memory allocated for the receive descriptors of the ring. + * @param rx_conf + * The pointer to the configuration data to be used for the receive queue. + * NULL value is allowed, in which case default RX configuration + * will be used. + * The *rx_conf* structure contains an *rx_thresh* structure with the values + * of the Prefetch, Host, and Write-Back threshold registers of the receive + * ring. + * In addition it contains the hardware offloads features to activate using + * the DEV_RX_OFFLOAD_* flags. + * If an offloading set in rx_conf->offloads + * hasn't been set in the input argument eth_conf->rxmode.offloads + * to rte_eth_dev_configure(), it is a new added offloading, it must be + * per-queue type and it is enabled for the queue. + * No need to repeat any bit in rx_conf->offloads which has already been + * enabled in rte_eth_dev_configure() at port level. An offloading enabled + * at port level can't be disabled at queue level. + * @param hairpin_conf + * The pointer to the hairpin binding configuration. + * @return + * - 0: Success, receive queue correctly set up. + * - -EINVAL: The size of network buffers which can be allocated from the + * memory pool does not fit the various buffer sizes allowed by the + * device controller. + * - -ENOMEM: Unable to allocate the receive ring descriptors or to + * allocate network memory buffers from the memory pool when + * initializing receive descriptors. + */ +__rte_experimental +int rte_eth_rx_hairpin_queue_setup + (uint16_t port_id, uint16_t rx_queue_id, + uint16_t nb_rx_desc, unsigned int socket_id, + const struct rte_eth_rxconf *rx_conf, + const struct rte_eth_hairpin_conf *hairpin_conf); + +/** * Allocate and set up a transmit queue for an Ethernet device. * * @param port_id @@ -1821,6 +1899,73 @@ int rte_eth_tx_queue_setup(uint16_t port_id, uint16_t tx_queue_id, const struct rte_eth_txconf *tx_conf); /** + * @warning + * @b EXPERIMENTAL: this API may change, or be removed, without prior notice + * + * Allocate and set up a transmit hairpin queue for an Ethernet device. + * + * @param port_id + * The port identifier of the Ethernet device. + * @param tx_queue_id + * The index of the transmit queue to set up. + * The value must be in the range [0, nb_tx_queue - 1] previously supplied + * to rte_eth_dev_configure(). + * @param nb_tx_desc + * The number of transmit descriptors to allocate for the transmit ring. + * @param socket_id + * The *socket_id* argument is the socket identifier in case of NUMA. + * Its value can be *SOCKET_ID_ANY* if there is no NUMA constraint for + * the DMA memory allocated for the transmit descriptors of the ring. + * @param tx_conf + * The pointer to the configuration data to be used for the transmit queue. + * NULL value is allowed, in which case default RX configuration + * will be used. + * The *tx_conf* structure contains the following data: + * - The *tx_thresh* structure with the values of the Prefetch, Host, and + * Write-Back threshold registers of the transmit ring. + * When setting Write-Back threshold to the value greater then zero, + * *tx_rs_thresh* value should be explicitly set to one. + * - The *tx_free_thresh* value indicates the [minimum] number of network + * buffers that must be pending in the transmit ring to trigger their + * [implicit] freeing by the driver transmit function. + * - The *tx_rs_thresh* value indicates the [minimum] number of transmit + * descriptors that must be pending in the transmit ring before setting the + * RS bit on a descriptor by the driver transmit function. + * The *tx_rs_thresh* value should be less or equal then + * *tx_free_thresh* value, and both of them should be less then + * *nb_tx_desc* - 3. + * - The *txq_flags* member contains flags to pass to the TX queue setup + * function to configure the behavior of the TX queue. This should be set + * to 0 if no special configuration is required. + * This API is obsolete and will be deprecated. Applications + * should set it to ETH_TXQ_FLAGS_IGNORE and use + * the offloads field below. + * - The *offloads* member contains Tx offloads to be enabled. + * If an offloading set in tx_conf->offloads + * hasn't been set in the input argument eth_conf->txmode.offloads + * to rte_eth_dev_configure(), it is a new added offloading, it must be + * per-queue type and it is enabled for the queue. + * No need to repeat any bit in tx_conf->offloads which has already been + * enabled in rte_eth_dev_configure() at port level. An offloading enabled + * at port level can't be disabled at queue level. + * + * Note that setting *tx_free_thresh* or *tx_rs_thresh* value to 0 forces + * the transmit function to use default values. + * @param hairpin_conf + * The hairpin binding configuration. + * + * @return + * - 0: Success, the transmit queue is correctly set up. + * - -ENOMEM: Unable to allocate the transmit ring descriptors. + */ +__rte_experimental +int rte_eth_tx_hairpin_queue_setup + (uint16_t port_id, uint16_t tx_queue_id, + uint16_t nb_tx_desc, unsigned int socket_id, + const struct rte_eth_txconf *tx_conf, + const struct rte_eth_hairpin_conf *hairpin_conf); + +/** * Return the NUMA socket to which an Ethernet device is connected * * @param port_id diff --git a/lib/librte_ethdev/rte_ethdev_core.h b/lib/librte_ethdev/rte_ethdev_core.h index 2394b32..bc40708 100644 --- a/lib/librte_ethdev/rte_ethdev_core.h +++ b/lib/librte_ethdev/rte_ethdev_core.h @@ -126,6 +126,13 @@ typedef int (*eth_rx_queue_setup_t)(struct rte_eth_dev *dev, struct rte_mempool *mb_pool); /**< @internal Set up a receive queue of an Ethernet device. */ +typedef int (*eth_rx_hairpin_queue_setup_t) + (struct rte_eth_dev *dev, uint16_t rx_queue_id, + uint16_t nb_rx_desc, unsigned int socket_id, + const struct rte_eth_rxconf *rx_conf, + const struct rte_eth_hairpin_conf *hairpin_conf); +/**< @internal Set up a receive hairpin queue of an Ethernet device. */ + typedef int (*eth_tx_queue_setup_t)(struct rte_eth_dev *dev, uint16_t tx_queue_id, uint16_t nb_tx_desc, @@ -133,6 +140,13 @@ typedef int (*eth_tx_queue_setup_t)(struct rte_eth_dev *dev, const struct rte_eth_txconf *tx_conf); /**< @internal Setup a transmit queue of an Ethernet device. */ +typedef int (*eth_tx_hairpin_queue_setup_t) + (struct rte_eth_dev *dev, uint16_t tx_queue_id, + uint16_t nb_tx_desc, unsigned int socket_id, + const struct rte_eth_txconf *tx_conf, + const struct rte_eth_hairpin_conf *hairpin_conf); +/**< @internal Setup a transmit hairpin queue of an Ethernet device. */ + typedef int (*eth_rx_enable_intr_t)(struct rte_eth_dev *dev, uint16_t rx_queue_id); /**< @internal Enable interrupt of a receive queue of an Ethernet device. */ @@ -433,6 +447,8 @@ struct eth_dev_ops { eth_queue_start_t tx_queue_start;/**< Start TX for a queue. */ eth_queue_stop_t tx_queue_stop; /**< Stop TX for a queue. */ eth_rx_queue_setup_t rx_queue_setup;/**< Set up device RX queue. */ + eth_rx_hairpin_queue_setup_t rx_hairpin_queue_setup; + /**< Set up device RX hairpin queue. */ eth_queue_release_t rx_queue_release; /**< Release RX queue. */ eth_rx_queue_count_t rx_queue_count; /**< Get the number of used RX descriptors. */ @@ -444,6 +460,8 @@ struct eth_dev_ops { eth_rx_enable_intr_t rx_queue_intr_enable; /**< Enable Rx queue interrupt. */ eth_rx_disable_intr_t rx_queue_intr_disable; /**< Disable Rx queue interrupt. */ eth_tx_queue_setup_t tx_queue_setup;/**< Set up device TX queue. */ + eth_tx_hairpin_queue_setup_t tx_hairpin_queue_setup; + /**< Set up device TX hairpin queue. */ eth_queue_release_t tx_queue_release; /**< Release TX queue. */ eth_tx_done_cleanup_t tx_done_cleanup;/**< Free tx ring mbufs */ diff --git a/lib/librte_ethdev/rte_ethdev_version.map b/lib/librte_ethdev/rte_ethdev_version.map index 6df42a4..99e05fe 100644 --- a/lib/librte_ethdev/rte_ethdev_version.map +++ b/lib/librte_ethdev/rte_ethdev_version.map @@ -283,4 +283,8 @@ EXPERIMENTAL { # added in 19.08 rte_eth_read_clock; + + # added in 19.11 + rte_eth_rx_hairpin_queue_setup; + rte_eth_tx_hairpin_queue_setup; }; -- 1.8.3.1