From 0de345e9a0db54caea2e4c461a1c244d818442d2 Mon Sep 17 00:00:00 2001 From: Jerin Jacob Date: Tue, 8 Feb 2022 14:20:48 +0530 Subject: [PATCH] ethdev: support queue-based priority flow control Based on device support and use-case need, there are two different ways to enable PFC. The first case is the port level PFC configuration, in this case, rte_eth_dev_priority_flow_ctrl_set() API shall be used to configure the PFC, and PFC frames will be generated using based on VLAN TC value. The second case is the queue level PFC configuration, in this case, Any packet field content can be used to steer the packet to the specific queue using rte_flow or RSS and then use rte_eth_dev_priority_flow_ctrl_queue_configure() to configure the TC mapping on each queue. Based on congestion selected on the specific queue, configured TC shall be used to generate PFC frames. Signed-off-by: Jerin Jacob Signed-off-by: Sunil Kumar Kori Reviewed-by: Ferruh Yigit --- doc/guides/nics/features.rst | 7 +- doc/guides/rel_notes/release_22_03.rst | 5 + lib/ethdev/ethdev_driver.h | 11 ++ lib/ethdev/rte_ethdev.c | 143 +++++++++++++++++++++++++ lib/ethdev/rte_ethdev.h | 101 +++++++++++++++++ lib/ethdev/version.map | 4 + 6 files changed, 269 insertions(+), 2 deletions(-) diff --git a/doc/guides/nics/features.rst b/doc/guides/nics/features.rst index 27be2d2576..1cacdc883a 100644 --- a/doc/guides/nics/features.rst +++ b/doc/guides/nics/features.rst @@ -379,9 +379,12 @@ Flow control Supports configuring link flow control. * **[implements] eth_dev_ops**: ``flow_ctrl_get``, ``flow_ctrl_set``, - ``priority_flow_ctrl_set``. + ``priority_flow_ctrl_set``, ``priority_flow_ctrl_queue_info_get``, + ``priority_flow_ctrl_queue_configure`` * **[related] API**: ``rte_eth_dev_flow_ctrl_get()``, ``rte_eth_dev_flow_ctrl_set()``, - ``rte_eth_dev_priority_flow_ctrl_set()``. + ``rte_eth_dev_priority_flow_ctrl_set()``, + ``rte_eth_dev_priority_flow_ctrl_queue_info_get()``, + ``rte_eth_dev_priority_flow_ctrl_queue_configure()``. .. _nic_features_rate_limitation: diff --git a/doc/guides/rel_notes/release_22_03.rst b/doc/guides/rel_notes/release_22_03.rst index f5093f6d5f..25cf659824 100644 --- a/doc/guides/rel_notes/release_22_03.rst +++ b/doc/guides/rel_notes/release_22_03.rst @@ -71,6 +71,11 @@ New Features - ``rte_ipv6_udptcp_cksum_mbuf()`` - ``rte_ipv6_udptcp_cksum_mbuf_verify()`` +* **Added an API to enable queue based priority flow ctrl(PFC).** + + New APIs, ``rte_eth_dev_priority_flow_ctrl_queue_info_get()`` and + ``rte_eth_dev_priority_flow_ctrl_queue_configure()``, was added. + * **Updated AF_XDP PMD** * Added support for libxdp >=v1.2.2. diff --git a/lib/ethdev/ethdev_driver.h b/lib/ethdev/ethdev_driver.h index 0dac55f9c8..1c5b58faa4 100644 --- a/lib/ethdev/ethdev_driver.h +++ b/lib/ethdev/ethdev_driver.h @@ -533,6 +533,13 @@ typedef int (*flow_ctrl_set_t)(struct rte_eth_dev *dev, typedef int (*priority_flow_ctrl_set_t)(struct rte_eth_dev *dev, struct rte_eth_pfc_conf *pfc_conf); +/** @internal Get info for queue based PFC on an Ethernet device. */ +typedef int (*priority_flow_ctrl_queue_info_get_t)(struct rte_eth_dev *dev, + struct rte_eth_pfc_queue_info *pfc_queue_info); +/** @internal Configure queue based PFC parameter on an Ethernet device. */ +typedef int (*priority_flow_ctrl_queue_config_t)(struct rte_eth_dev *dev, + struct rte_eth_pfc_queue_conf *pfc_queue_conf); + /** @internal Update RSS redirection table on an Ethernet device. */ typedef int (*reta_update_t)(struct rte_eth_dev *dev, struct rte_eth_rss_reta_entry64 *reta_conf, @@ -1080,6 +1087,10 @@ struct eth_dev_ops { flow_ctrl_set_t flow_ctrl_set; /**< Setup flow control */ /** Setup priority flow control */ priority_flow_ctrl_set_t priority_flow_ctrl_set; + /** Priority flow control queue info get */ + priority_flow_ctrl_queue_info_get_t priority_flow_ctrl_queue_info_get; + /** Priority flow control queue configure */ + priority_flow_ctrl_queue_config_t priority_flow_ctrl_queue_config; /** Set Unicast Table Array */ eth_uc_hash_table_set_t uc_hash_table_set; diff --git a/lib/ethdev/rte_ethdev.c b/lib/ethdev/rte_ethdev.c index 917a320afa..90e153c7b1 100644 --- a/lib/ethdev/rte_ethdev.c +++ b/lib/ethdev/rte_ethdev.c @@ -4033,6 +4033,149 @@ rte_eth_dev_priority_flow_ctrl_set(uint16_t port_id, return -ENOTSUP; } +static int +validate_rx_pause_config(struct rte_eth_dev_info *dev_info, uint8_t tc_max, + struct rte_eth_pfc_queue_conf *pfc_queue_conf) +{ + if ((pfc_queue_conf->mode == RTE_ETH_FC_RX_PAUSE) || + (pfc_queue_conf->mode == RTE_ETH_FC_FULL)) { + if (pfc_queue_conf->rx_pause.tx_qid >= dev_info->nb_tx_queues) { + RTE_ETHDEV_LOG(ERR, + "PFC Tx queue not in range for Rx pause requested:%d configured:%d\n", + pfc_queue_conf->rx_pause.tx_qid, + dev_info->nb_tx_queues); + return -EINVAL; + } + + if (pfc_queue_conf->rx_pause.tc >= tc_max) { + RTE_ETHDEV_LOG(ERR, + "PFC TC not in range for Rx pause requested:%d max:%d\n", + pfc_queue_conf->rx_pause.tc, tc_max); + return -EINVAL; + } + } + + return 0; +} + +static int +validate_tx_pause_config(struct rte_eth_dev_info *dev_info, uint8_t tc_max, + struct rte_eth_pfc_queue_conf *pfc_queue_conf) +{ + if ((pfc_queue_conf->mode == RTE_ETH_FC_TX_PAUSE) || + (pfc_queue_conf->mode == RTE_ETH_FC_FULL)) { + if (pfc_queue_conf->tx_pause.rx_qid >= dev_info->nb_rx_queues) { + RTE_ETHDEV_LOG(ERR, + "PFC Rx queue not in range for Tx pause requested:%d configured:%d\n", + pfc_queue_conf->tx_pause.rx_qid, + dev_info->nb_rx_queues); + return -EINVAL; + } + + if (pfc_queue_conf->tx_pause.tc >= tc_max) { + RTE_ETHDEV_LOG(ERR, + "PFC TC not in range for Tx pause requested:%d max:%d\n", + pfc_queue_conf->tx_pause.tc, tc_max); + return -EINVAL; + } + } + + return 0; +} + +int +rte_eth_dev_priority_flow_ctrl_queue_info_get(uint16_t port_id, + struct rte_eth_pfc_queue_info *pfc_queue_info) +{ + struct rte_eth_dev *dev; + + RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV); + dev = &rte_eth_devices[port_id]; + + if (pfc_queue_info == NULL) { + RTE_ETHDEV_LOG(ERR, "PFC info param is NULL for port (%u)\n", + port_id); + return -EINVAL; + } + + if (*dev->dev_ops->priority_flow_ctrl_queue_info_get) + return eth_err(port_id, (*dev->dev_ops->priority_flow_ctrl_queue_info_get) + (dev, pfc_queue_info)); + return -ENOTSUP; +} + +int +rte_eth_dev_priority_flow_ctrl_queue_configure(uint16_t port_id, + struct rte_eth_pfc_queue_conf *pfc_queue_conf) +{ + struct rte_eth_pfc_queue_info pfc_info; + struct rte_eth_dev_info dev_info; + struct rte_eth_dev *dev; + int ret; + + RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV); + dev = &rte_eth_devices[port_id]; + + if (pfc_queue_conf == NULL) { + RTE_ETHDEV_LOG(ERR, "PFC parameters are NULL for port (%u)\n", + port_id); + return -EINVAL; + } + + ret = rte_eth_dev_info_get(port_id, &dev_info); + if (ret != 0) + return ret; + + ret = rte_eth_dev_priority_flow_ctrl_queue_info_get(port_id, &pfc_info); + if (ret != 0) + return ret; + + if (pfc_info.tc_max == 0) { + RTE_ETHDEV_LOG(ERR, "Ethdev port %u does not support PFC TC values\n", + port_id); + return -ENOTSUP; + } + + /* Check requested mode supported or not */ + if (pfc_info.mode_capa == RTE_ETH_FC_RX_PAUSE && + pfc_queue_conf->mode == RTE_ETH_FC_TX_PAUSE) { + RTE_ETHDEV_LOG(ERR, "PFC Tx pause unsupported for port (%d)\n", + port_id); + return -EINVAL; + } + + if (pfc_info.mode_capa == RTE_ETH_FC_TX_PAUSE && + pfc_queue_conf->mode == RTE_ETH_FC_RX_PAUSE) { + RTE_ETHDEV_LOG(ERR, "PFC Rx pause unsupported for port (%d)\n", + port_id); + return -EINVAL; + } + + /* Validate Rx pause parameters */ + if (pfc_info.mode_capa == RTE_ETH_FC_FULL || + pfc_info.mode_capa == RTE_ETH_FC_RX_PAUSE) { + ret = validate_rx_pause_config(&dev_info, pfc_info.tc_max, + pfc_queue_conf); + if (ret != 0) + return ret; + } + + /* Validate Tx pause parameters */ + if (pfc_info.mode_capa == RTE_ETH_FC_FULL || + pfc_info.mode_capa == RTE_ETH_FC_TX_PAUSE) { + ret = validate_tx_pause_config(&dev_info, pfc_info.tc_max, + pfc_queue_conf); + if (ret != 0) + return ret; + } + + if (*dev->dev_ops->priority_flow_ctrl_queue_config) + return eth_err(port_id, + (*dev->dev_ops->priority_flow_ctrl_queue_config)( + dev, pfc_queue_conf)); + return -ENOTSUP; +} + static int eth_check_reta_mask(struct rte_eth_rss_reta_entry64 *reta_conf, uint16_t reta_size) diff --git a/lib/ethdev/rte_ethdev.h b/lib/ethdev/rte_ethdev.h index 147cc1ced3..ce40164a07 100644 --- a/lib/ethdev/rte_ethdev.h +++ b/lib/ethdev/rte_ethdev.h @@ -1408,6 +1408,59 @@ struct rte_eth_pfc_conf { uint8_t priority; /**< VLAN User Priority. */ }; +/** + * @warning + * @b EXPERIMENTAL: this API may change, or be removed, without prior notice + * + * A structure used to retrieve information of queue based PFC. + */ +struct rte_eth_pfc_queue_info { + /** + * Maximum supported traffic class as per PFC (802.1Qbb) specification. + */ + uint8_t tc_max; + /** PFC queue mode capabilities. */ + enum rte_eth_fc_mode mode_capa; +}; + +/** + * @warning + * @b EXPERIMENTAL: this API may change, or be removed, without prior notice + * + * A structure used to configure Ethernet priority flow control parameters for + * ethdev queues. + * + * rte_eth_pfc_queue_conf::rx_pause structure shall be used to configure given + * tx_qid with corresponding tc. When ethdev device receives PFC frame with + * rte_eth_pfc_queue_conf::rx_pause::tc, traffic will be paused on + * rte_eth_pfc_queue_conf::rx_pause::tx_qid for that tc. + * + * rte_eth_pfc_queue_conf::tx_pause structure shall be used to configure given + * rx_qid. When rx_qid is congested, PFC frames are generated with + * rte_eth_pfc_queue_conf::rx_pause::tc and + * rte_eth_pfc_queue_conf::rx_pause::pause_time to the peer. + */ +struct rte_eth_pfc_queue_conf { + enum rte_eth_fc_mode mode; /**< Link flow control mode */ + + struct { + uint16_t tx_qid; /**< Tx queue ID */ + /** Traffic class as per PFC (802.1Qbb) spec. The value must be + * in the range [0, rte_eth_pfc_queue_info::tx_max - 1] + */ + uint8_t tc; + } rx_pause; /* Valid when (mode == FC_RX_PAUSE || mode == FC_FULL) */ + + struct { + uint16_t pause_time; /**< Pause quota in the Pause frame */ + uint16_t rx_qid; /**< Rx queue ID */ + /** Traffic class as per PFC (802.1Qbb) spec. The value must be + * in the range [0, rte_eth_pfc_queue_info::tx_max - 1] + */ + uint8_t tc; + } tx_pause; /* Valid when (mode == FC_TX_PAUSE || mode == FC_FULL) */ +}; + /** * Tunnel type for device-specific classifier configuration. * @see rte_eth_udp_tunnel @@ -4158,6 +4211,54 @@ int rte_eth_dev_priority_flow_ctrl_set(uint16_t port_id, int rte_eth_dev_mac_addr_add(uint16_t port_id, struct rte_ether_addr *mac_addr, uint32_t pool); +/** + * @warning + * @b EXPERIMENTAL: this API may change without prior notice. + * + * Retrieve the information for queue based PFC. + * + * @param port_id + * The port identifier of the Ethernet device. + * @param pfc_queue_info + * A pointer to a structure of type *rte_eth_pfc_queue_info* to be filled with + * the information about queue based PFC. + * @return + * - (0) if successful. + * - (-ENOTSUP) if support for priority_flow_ctrl_queue_info_get does not exist. + * - (-ENODEV) if *port_id* invalid. + * - (-EINVAL) if bad parameter. + */ +__rte_experimental +int rte_eth_dev_priority_flow_ctrl_queue_info_get(uint16_t port_id, + struct rte_eth_pfc_queue_info *pfc_queue_info); + +/** + * @warning + * @b EXPERIMENTAL: this API may change without prior notice. + * + * Configure the queue based priority flow control for a given queue + * for Ethernet device. + * + * @note When an ethdev port switches to queue based PFC mode, the + * unconfigured queues shall be configured by the driver with + * default values such as lower priority value for TC etc. + * + * @param port_id + * The port identifier of the Ethernet device. + * @param pfc_queue_conf + * The pointer to the structure of the priority flow control parameters + * for the queue. + * @return + * - (0) if successful. + * - (-ENOTSUP) if hardware doesn't support queue based PFC mode. + * - (-ENODEV) if *port_id* invalid. + * - (-EINVAL) if bad parameter + * - (-EIO) if flow control setup queue failure + */ +__rte_experimental +int rte_eth_dev_priority_flow_ctrl_queue_configure(uint16_t port_id, + struct rte_eth_pfc_queue_conf *pfc_queue_conf); + /** * Remove a MAC address from the internal array of addresses. * diff --git a/lib/ethdev/version.map b/lib/ethdev/version.map index 1f7359c846..cd0c4c428d 100644 --- a/lib/ethdev/version.map +++ b/lib/ethdev/version.map @@ -256,6 +256,10 @@ EXPERIMENTAL { rte_flow_flex_item_create; rte_flow_flex_item_release; rte_flow_pick_transfer_proxy; + + # added in 22.03 + rte_eth_dev_priority_flow_ctrl_queue_configure; + rte_eth_dev_priority_flow_ctrl_queue_info_get; }; INTERNAL { -- 2.39.5