From patchwork Mon Jan 15 01:57:29 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Qi Zhang X-Patchwork-Id: 33708 X-Patchwork-Delegate: ferruh.yigit@amd.com Return-Path: X-Original-To: patchwork@dpdk.org Delivered-To: patchwork@dpdk.org Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id E36D72BF5; Mon, 15 Jan 2018 02:57:47 +0100 (CET) Received: from mga14.intel.com (mga14.intel.com [192.55.52.115]) by dpdk.org (Postfix) with ESMTP id F26942BE1 for ; Mon, 15 Jan 2018 02:57:46 +0100 (CET) X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from fmsmga001.fm.intel.com ([10.253.24.23]) by fmsmga103.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 14 Jan 2018 17:57:46 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.46,361,1511856000"; d="scan'208";a="22028376" Received: from dpdk51.sh.intel.com ([10.67.110.184]) by fmsmga001.fm.intel.com with ESMTP; 14 Jan 2018 17:57:44 -0800 From: Qi Zhang To: thomas@monjalon.net Cc: dev@dpdk.org, jinging.wu@intel.com, konstantin.ananyev@intel.com, Qi Zhang Date: Mon, 15 Jan 2018 09:57:29 +0800 Message-Id: <20180115015729.10181-1-qi.z.zhang@intel.com> X-Mailer: git-send-email 2.13.6 Subject: [dpdk-dev] [RFC] ether: support deferred queue setup 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" According to exist implementation, rte_eth_[rx|tx]_queue_setup will always return fail if device is already started(rte_eth_dev_start). This can't satisfied the usage when application want to deferred setup part of the queues while keep traffic running on those queues already be setup. example: rte_eth_dev_config(nb_rxq = 2, nb_txq =2) rte_eth_rx_queue_setup(idx = 0 ...) rte_eth_rx_queue_setup(idx = 0 ...) rte_eth_dev_start(...) /* [rx|tx]_burst is ready to start on queue 0 */ rte_eth_rx_queue_setup(idx=1 ...) /* fail*/ Basically this is not a general hardware limitation, because for NIC like i40e, ixgbe, it is not necessary to stop the whole device before configure a fresh queue or reconfigure an exist queue with traffic on it. The patch add new eth_dev_ops: [rx|tx]_queue_hot_[setup|release] and internal logic of rte_eth_[rx|tx]_queue_setup is changed, so application is allowed to setup queue after device start if the driver is implemented properly. The typical implementation of [rx|tx]_queue_hot_setup could be: 1. do the same thing in [rx|tx]_queue_setup. 2. perform per queue start logic from [rx|tx]_queue_start. The typical implementation of [rx|tx]_queue_hot_release could be: 1. perform per queue stop logic from [rx|tx]_queue_stop. 2. do the same thing in [rx|tx]_queue_release. Signed-off-by: Qi Zhang --- lib/librte_ether/rte_ethdev.c | 54 ++++++++++++++++++++++++------------------- lib/librte_ether/rte_ethdev.h | 8 +++++++ 2 files changed, 38 insertions(+), 24 deletions(-) diff --git a/lib/librte_ether/rte_ethdev.c b/lib/librte_ether/rte_ethdev.c index a524af740..b4f534dbb 100644 --- a/lib/librte_ether/rte_ethdev.c +++ b/lib/librte_ether/rte_ethdev.c @@ -1100,6 +1100,8 @@ rte_eth_rx_queue_setup(uint16_t port_id, uint16_t rx_queue_id, struct rte_eth_dev_info dev_info; struct rte_eth_rxconf local_conf; void **rxq; + eth_rx_queue_setup_t rxq_setup; + eth_queue_release_t rxq_release; RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -EINVAL); @@ -1109,14 +1111,7 @@ rte_eth_rx_queue_setup(uint16_t port_id, uint16_t rx_queue_id, return -EINVAL; } - if (dev->data->dev_started) { - RTE_PMD_DEBUG_TRACE( - "port %d must be stopped to allow configuration\n", port_id); - return -EBUSY; - } - RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->dev_infos_get, -ENOTSUP); - RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->rx_queue_setup, -ENOTSUP); /* * Check the size of the mbuf data buffer. @@ -1158,11 +1153,19 @@ rte_eth_rx_queue_setup(uint16_t port_id, uint16_t rx_queue_id, return -EINVAL; } + if (dev->data->dev_started) { + rxq_setup = dev->dev_ops->rx_queue_hot_setup; + rxq_release = dev->dev_ops->rx_queue_hot_release; + } else { + rxq_setup = dev->dev_ops->rx_queue_setup; + rxq_release = dev->dev_ops->rx_queue_release; + } + + RTE_FUNC_PTR_OR_ERR_RET(*rxq_setup, -ENOTSUP); 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]); + RTE_FUNC_PTR_OR_ERR_RET(*rxq_release, -ENOTSUP); + (*rxq_release)(rxq[rx_queue_id]); rxq[rx_queue_id] = NULL; } @@ -1179,8 +1182,8 @@ rte_eth_rx_queue_setup(uint16_t port_id, uint16_t rx_queue_id, &local_conf.offloads); } - ret = (*dev->dev_ops->rx_queue_setup)(dev, rx_queue_id, nb_rx_desc, - socket_id, &local_conf, mp); + ret = (*rxq_setup)(dev, rx_queue_id, nb_rx_desc, + socket_id, &local_conf, mp); if (!ret) { if (!dev->data->min_rx_buf_size || dev->data->min_rx_buf_size > mbp_buf_size) @@ -1248,6 +1251,8 @@ rte_eth_tx_queue_setup(uint16_t port_id, uint16_t tx_queue_id, struct rte_eth_dev_info dev_info; struct rte_eth_txconf local_conf; void **txq; + eth_tx_queue_setup_t txq_setup; + eth_queue_release_t txq_release; RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -EINVAL); @@ -1257,14 +1262,7 @@ rte_eth_tx_queue_setup(uint16_t port_id, uint16_t tx_queue_id, return -EINVAL; } - if (dev->data->dev_started) { - RTE_PMD_DEBUG_TRACE( - "port %d must be stopped to allow configuration\n", port_id); - return -EBUSY; - } - RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->dev_infos_get, -ENOTSUP); - RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->tx_queue_setup, -ENOTSUP); rte_eth_dev_info_get(port_id, &dev_info); @@ -1280,11 +1278,19 @@ rte_eth_tx_queue_setup(uint16_t port_id, uint16_t tx_queue_id, return -EINVAL; } + if (dev->data->dev_started) { + txq_setup = dev->dev_ops->tx_queue_hot_setup; + txq_release = dev->dev_ops->tx_queue_hot_release; + } else { + txq_setup = dev->dev_ops->tx_queue_setup; + txq_release = dev->dev_ops->tx_queue_release; + } + + RTE_FUNC_PTR_OR_ERR_RET(*txq_setup, -ENOTSUP); 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]); + RTE_FUNC_PTR_OR_ERR_RET(*txq_release, -ENOTSUP); + (*txq_release)(txq[tx_queue_id]); txq[tx_queue_id] = NULL; } @@ -1306,8 +1312,8 @@ rte_eth_tx_queue_setup(uint16_t port_id, uint16_t tx_queue_id, &local_conf.offloads); } - return (*dev->dev_ops->tx_queue_setup)(dev, tx_queue_id, nb_tx_desc, - socket_id, &local_conf); + return (*txq_setup)(dev, tx_queue_id, nb_tx_desc, socket_id, + &local_conf); } void diff --git a/lib/librte_ether/rte_ethdev.h b/lib/librte_ether/rte_ethdev.h index b10e2a92d..e78883e19 100644 --- a/lib/librte_ether/rte_ethdev.h +++ b/lib/librte_ether/rte_ethdev.h @@ -1534,7 +1534,11 @@ 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_queue_setup_t rx_queue_hot_setup; + /**< Set up RX queue when device already started. */ eth_queue_release_t rx_queue_release; /**< Release RX queue. */ + eth_queue_release_t rx_queue_hot_release; + /**< Release RX queue when device alrelady started. */ eth_rx_queue_count_t rx_queue_count; /**< Get the number of used RX descriptors. */ eth_rx_descriptor_done_t rx_descriptor_done; /**< Check rxd DD bit. */ @@ -1545,7 +1549,11 @@ 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_queue_setup_t tx_queue_hot_setup; + /**< Set up TX queue when device already started. */ eth_queue_release_t tx_queue_release; /**< Release TX queue. */ + eth_queue_release_t tx_queue_hot_release; + /**< Release TX queue when device already started. */ eth_tx_done_cleanup_t tx_done_cleanup;/**< Free tx ring mbufs */ eth_dev_led_on_t dev_led_on; /**< Turn on LED. */