From patchwork Tue Jan 19 07:28:07 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Xueming Li X-Patchwork-Id: 86871 X-Patchwork-Delegate: rasland@nvidia.com Return-Path: X-Original-To: patchwork@inbox.dpdk.org Delivered-To: patchwork@inbox.dpdk.org Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124]) by inbox.dpdk.org (Postfix) with ESMTP id 8CD02A0A03; Tue, 19 Jan 2021 08:30:44 +0100 (CET) Received: from [217.70.189.124] (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id 1061A140DA2; Tue, 19 Jan 2021 08:30:04 +0100 (CET) Received: from mellanox.co.il (mail-il-dmz.mellanox.com [193.47.165.129]) by mails.dpdk.org (Postfix) with ESMTP id 09258140D44 for ; Tue, 19 Jan 2021 08:29:53 +0100 (CET) Received: from Internal Mail-Server by MTLPINE1 (envelope-from xuemingl@nvidia.com) with SMTP; 19 Jan 2021 09:29:51 +0200 Received: from nvidia.com (pegasus05.mtr.labs.mlnx [10.210.16.100]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id 10J7Tpqk014531; Tue, 19 Jan 2021 09:29:51 +0200 From: Xueming Li To: Viacheslav Ovsiienko Cc: dev@dpdk.org, xuemingl@nvidia.com, Asaf Penso Date: Tue, 19 Jan 2021 07:28:07 +0000 Message-Id: <1611041295-12797-2-git-send-email-xuemingl@nvidia.com> X-Mailer: git-send-email 1.8.3.1 In-Reply-To: <1611041295-12797-1-git-send-email-xuemingl@nvidia.com> References: <1611041295-12797-1-git-send-email-xuemingl@nvidia.com> In-Reply-To: <1608304614-13908-2-git-send-email-xuemingl@nvidia.com> References: <1608304614-13908-2-git-send-email-xuemingl@nvidia.com> Subject: [dpdk-dev] [PATCH v4 1/8] common/mlx5: update representor name parsing 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 Sender: "dev" This patch updates representor name parsing for SF. In sysfs, representor name stored under "phys_port_name" sysfs key, similar to VF representor, switch port name of SF representor is "pfsf". For netlink message, net SF type is supported. Examples: pf0sf1 pf0sf[0-3] Signed-off-by: Xueming Li Acked-by: Viacheslav Ovsiienko --- drivers/common/mlx5/linux/mlx5_common_os.c | 32 +++++++++++++++------- drivers/common/mlx5/linux/mlx5_nl.c | 2 ++ drivers/common/mlx5/mlx5_common.h | 2 ++ drivers/net/mlx5/linux/mlx5_ethdev_os.c | 3 ++ 4 files changed, 29 insertions(+), 10 deletions(-) diff --git a/drivers/common/mlx5/linux/mlx5_common_os.c b/drivers/common/mlx5/linux/mlx5_common_os.c index 0edd78ea6d..5cf9576921 100644 --- a/drivers/common/mlx5/linux/mlx5_common_os.c +++ b/drivers/common/mlx5/linux/mlx5_common_os.c @@ -97,22 +97,34 @@ void mlx5_translate_port_name(const char *port_name_in, struct mlx5_switch_info *port_info_out) { - char pf_c1, pf_c2, vf_c1, vf_c2, eol; + char ctrl = 0, pf_c1, pf_c2, vf_c1, vf_c2, eol; char *end; int sc_items; - /* - * Check for port-name as a string of the form pf0vf0 - * (support kernel ver >= 5.0 or OFED ver >= 4.6). - */ + sc_items = sscanf(port_name_in, "%c%d", + &ctrl, &port_info_out->ctrl_num); + if (sc_items == 2 && ctrl == 'c') { + port_name_in++; /* 'c' */ + port_name_in += snprintf(NULL, 0, "%d", + port_info_out->ctrl_num); + } + /* Check for port-name as a string of the form pf0vf0 or pf0sf0 */ sc_items = sscanf(port_name_in, "%c%c%d%c%c%d%c", &pf_c1, &pf_c2, &port_info_out->pf_num, &vf_c1, &vf_c2, &port_info_out->port_name, &eol); - if (sc_items == 6 && - pf_c1 == 'p' && pf_c2 == 'f' && - vf_c1 == 'v' && vf_c2 == 'f') { - port_info_out->name_type = MLX5_PHYS_PORT_NAME_TYPE_PFVF; - return; + if (sc_items == 6 && pf_c1 == 'p' && pf_c2 == 'f') { + if (vf_c1 == 'v' && vf_c2 == 'f') { + /* Kernel ver >= 5.0 or OFED ver >= 4.6 */ + port_info_out->name_type = + MLX5_PHYS_PORT_NAME_TYPE_PFVF; + return; + } + if (vf_c1 == 's' && vf_c2 == 'f') { + /* Kernel ver >= 5.11 or OFED ver >= 5.1 */ + port_info_out->name_type = + MLX5_PHYS_PORT_NAME_TYPE_PFSF; + return; + } } /* * Check for port-name as a string of the form p0 diff --git a/drivers/common/mlx5/linux/mlx5_nl.c b/drivers/common/mlx5/linux/mlx5_nl.c index 40d8620300..3d55cc98b4 100644 --- a/drivers/common/mlx5/linux/mlx5_nl.c +++ b/drivers/common/mlx5/linux/mlx5_nl.c @@ -1148,6 +1148,8 @@ mlx5_nl_check_switch_info(bool num_vf_set, case MLX5_PHYS_PORT_NAME_TYPE_PFHPF: /* Fallthrough */ case MLX5_PHYS_PORT_NAME_TYPE_PFVF: + /* Fallthrough */ + case MLX5_PHYS_PORT_NAME_TYPE_PFSF: /* New representors naming schema. */ switch_info->representor = 1; break; diff --git a/drivers/common/mlx5/mlx5_common.h b/drivers/common/mlx5/mlx5_common.h index e35188da4c..a422b74577 100644 --- a/drivers/common/mlx5/mlx5_common.h +++ b/drivers/common/mlx5/mlx5_common.h @@ -153,6 +153,7 @@ enum mlx5_nl_phys_port_name_type { MLX5_PHYS_PORT_NAME_TYPE_UPLINK, /* p0, kernel ver >= 5.0 */ MLX5_PHYS_PORT_NAME_TYPE_PFVF, /* pf0vf0, kernel ver >= 5.0 */ MLX5_PHYS_PORT_NAME_TYPE_PFHPF, /* pf0, kernel ver >= 5.7, HPF rep */ + MLX5_PHYS_PORT_NAME_TYPE_PFSF, /* pf0sf0, kernel ver >= 5.0 */ MLX5_PHYS_PORT_NAME_TYPE_UNKNOWN, /* Unrecognized. */ }; @@ -161,6 +162,7 @@ struct mlx5_switch_info { uint32_t master:1; /**< Master device. */ uint32_t representor:1; /**< Representor device. */ enum mlx5_nl_phys_port_name_type name_type; /** < Port name type. */ + int32_t ctrl_num; /**< Controller number (valid for c#pf#vf# format). */ int32_t pf_num; /**< PF number (valid for pfxvfx format only). */ int32_t port_name; /**< Representor port name. */ uint64_t switch_id; /**< Switch identifier. */ diff --git a/drivers/net/mlx5/linux/mlx5_ethdev_os.c b/drivers/net/mlx5/linux/mlx5_ethdev_os.c index e36a78091c..1b37970c21 100644 --- a/drivers/net/mlx5/linux/mlx5_ethdev_os.c +++ b/drivers/net/mlx5/linux/mlx5_ethdev_os.c @@ -1013,6 +1013,9 @@ mlx5_sysfs_check_switch_info(bool device_dir, /* New representors naming schema. */ switch_info->representor = 1; break; + default: + switch_info->master = device_dir; + break; } } From patchwork Tue Jan 19 07:28:08 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Xueming Li X-Patchwork-Id: 86868 X-Patchwork-Delegate: rasland@nvidia.com Return-Path: X-Original-To: patchwork@inbox.dpdk.org Delivered-To: patchwork@inbox.dpdk.org Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124]) by inbox.dpdk.org (Postfix) with ESMTP id 5D57AA0A03; Tue, 19 Jan 2021 08:30:17 +0100 (CET) Received: from [217.70.189.124] (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id 88A60140D61; Tue, 19 Jan 2021 08:30:00 +0100 (CET) Received: from mellanox.co.il (mail-il-dmz.mellanox.com [193.47.165.129]) by mails.dpdk.org (Postfix) with ESMTP id F3CD8140D00 for ; Tue, 19 Jan 2021 08:29:53 +0100 (CET) Received: from Internal Mail-Server by MTLPINE1 (envelope-from xuemingl@nvidia.com) with SMTP; 19 Jan 2021 09:29:51 +0200 Received: from nvidia.com (pegasus05.mtr.labs.mlnx [10.210.16.100]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id 10J7Tpql014531; Tue, 19 Jan 2021 09:29:51 +0200 From: Xueming Li To: Viacheslav Ovsiienko Cc: dev@dpdk.org, xuemingl@nvidia.com, Asaf Penso , Anatoly Burakov Date: Tue, 19 Jan 2021 07:28:08 +0000 Message-Id: <1611041295-12797-3-git-send-email-xuemingl@nvidia.com> X-Mailer: git-send-email 1.8.3.1 In-Reply-To: <1611041295-12797-1-git-send-email-xuemingl@nvidia.com> References: <1611041295-12797-1-git-send-email-xuemingl@nvidia.com> In-Reply-To: <1608304614-13908-2-git-send-email-xuemingl@nvidia.com> References: <1608304614-13908-2-git-send-email-xuemingl@nvidia.com> Subject: [dpdk-dev] [PATCH v4 2/8] net/mlx5: support representor of sub function 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 Sender: "dev" This patch adds support for SF representor. Similar to VF representor, switch port name of SF representor in phys_port_name sysfs key is "pfsf". Device representor argumnt is "representors=sf[list]", list member could be mix of instance and range. Example: representors=sf[0,2,4,8-12,-1] To probe VF representor and SF representor, need to separate into 2 devices: -a ,representor=vf[list] -a ,representor=sf[list] Signed-off-by: Xueming Li Acked-by: Viacheslav Ovsiienko --- doc/guides/nics/mlx5.rst | 58 +++++++++-- drivers/net/mlx5/linux/mlx5_ethdev_os.c | 2 + drivers/net/mlx5/linux/mlx5_os.c | 123 ++++++++++++++++++++---- drivers/net/mlx5/mlx5_ethdev.c | 2 + 4 files changed, 154 insertions(+), 31 deletions(-) diff --git a/doc/guides/nics/mlx5.rst b/doc/guides/nics/mlx5.rst index db0c8b6c20..c7829007a4 100644 --- a/doc/guides/nics/mlx5.rst +++ b/doc/guides/nics/mlx5.rst @@ -871,14 +871,18 @@ Driver options - ``representor`` parameter [list] This parameter can be used to instantiate DPDK Ethernet devices from - existing port (or VF) representors configured on the device. + existing port (PF, VF or SF) representors configured on the device. It is a standard parameter whose format is described in :ref:`ethernet_device_standard_device_arguments`. - For instance, to probe port representors 0 through 2:: + For instance, to probe VF port representors 0 through 2:: - representor=[0-2] + representor=vf[0-2] + + To probe SF port representors 0 through 2:: + + representor=sf[0-2] - ``max_dump_files_num`` parameter [int] @@ -1287,15 +1291,15 @@ Quick Start Guide on OFED/EN Enable switchdev mode --------------------- -Switchdev mode is a mode in E-Switch, that binds between representor and VF. -Representor is a port in DPDK that is connected to a VF in such a way -that assuming there are no offload flows, each packet that is sent from the VF -will be received by the corresponding representor. While each packet that is -sent to a representor will be received by the VF. +Switchdev mode is a mode in E-Switch, that binds between representor and VF or SF. +Representor is a port in DPDK that is connected to a VF or SF in such a way +that assuming there are no offload flows, each packet that is sent from the VF or SF +will be received by the corresponding representor. While each packet that is or SF +sent to a representor will be received by the VF or SF. This is very useful in case of SRIOV mode, where the first packet that is sent -by the VF will be received by the DPDK application which will decide if this +by the VF or SF will be received by the DPDK application which will decide if this flow should be offloaded to the E-Switch. After offloading the flow packet -that the VF that are matching the flow will not be received any more by +that the VF or SF that are matching the flow will not be received any more by the DPDK application. 1. Enable SRIOV mode:: @@ -1322,6 +1326,40 @@ the DPDK application. echo switchdev > /sys/class/net//compat/devlink/mode +SubFunction representor support +------------------------------- +SubFunction is a portion of the PCI device, a SF netdev has its own +dedicated queues(txq, rxq). A SF netdev supports E-Switch representation +offload similar to existing PF and VF representors. A SF shares PCI +level resources with other SFs and/or with its parent PCI function. + +1. Configure SF feature:: + + mlxconfig -d set PF_BAR2_SIZE=<0/1/2/3> PF_BAR2_ENABLE=1 + + Value of PF_BAR2_SIZE: + + 0: 8 SFs + 1: 16 SFs + 2: 32 SFs + 3: 64 SFs + +2. Reset the FW:: + + mlxfwreset -d reset + +3. Enable switchdev mode:: + + echo switchdev > /sys/class/net//compat/devlink/mode + +4. Create SF:: + + mlnx-sf -d -a create + +5. Probe SF representor:: + + testpmd> port attach ,representor=sf0,dv_flow_en=1 + Performance tuning ------------------ diff --git a/drivers/net/mlx5/linux/mlx5_ethdev_os.c b/drivers/net/mlx5/linux/mlx5_ethdev_os.c index 1b37970c21..ac311de46d 100644 --- a/drivers/net/mlx5/linux/mlx5_ethdev_os.c +++ b/drivers/net/mlx5/linux/mlx5_ethdev_os.c @@ -1010,6 +1010,8 @@ mlx5_sysfs_check_switch_info(bool device_dir, case MLX5_PHYS_PORT_NAME_TYPE_PFHPF: /* Fallthrough */ case MLX5_PHYS_PORT_NAME_TYPE_PFVF: + /* Fallthrough */ + case MLX5_PHYS_PORT_NAME_TYPE_PFSF: /* New representors naming schema. */ switch_info->representor = 1; break; diff --git a/drivers/net/mlx5/linux/mlx5_os.c b/drivers/net/mlx5/linux/mlx5_os.c index 4d7940bcca..b2776c080a 100644 --- a/drivers/net/mlx5/linux/mlx5_os.c +++ b/drivers/net/mlx5/linux/mlx5_os.c @@ -654,6 +654,8 @@ mlx5_flow_counter_mode_config(struct rte_eth_dev *dev __rte_unused) * Verbs device parameters (name, port, switch_info) to spawn. * @param config * Device configuration parameters. + * @param config + * Device arguments. * * @return * A valid Ethernet device object on success, NULL otherwise and rte_errno @@ -665,7 +667,8 @@ mlx5_flow_counter_mode_config(struct rte_eth_dev *dev __rte_unused) static struct rte_eth_dev * mlx5_dev_spawn(struct rte_device *dpdk_dev, struct mlx5_dev_spawn_data *spawn, - struct mlx5_dev_config *config) + struct mlx5_dev_config *config, + struct rte_eth_devargs *eth_da) { const struct mlx5_switch_info *switch_info = &spawn->info; struct mlx5_dev_ctx_shared *sh = NULL; @@ -696,34 +699,82 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev, /* Determine if this port representor is supposed to be spawned. */ if (switch_info->representor && dpdk_dev->devargs) { - struct rte_eth_devargs eth_da; - - err = rte_eth_devargs_parse(dpdk_dev->devargs->args, ð_da); - if (err) { - rte_errno = -err; - DRV_LOG(ERR, "failed to process device arguments: %s", - strerror(rte_errno)); - return NULL; - } - if (eth_da.type != RTE_ETH_REPRESENTOR_NONE) { - /* Representor not specified. */ + switch (eth_da->type) { + case RTE_ETH_REPRESENTOR_SF: + if (switch_info->name_type != + MLX5_PHYS_PORT_NAME_TYPE_PFSF) { + rte_errno = EBUSY; + return NULL; + } + break; + case RTE_ETH_REPRESENTOR_VF: + /* Allows HPF representor index -1 as exception. */ + if (!(spawn->info.port_name == -1 && + switch_info->name_type == + MLX5_PHYS_PORT_NAME_TYPE_PFHPF) && + switch_info->name_type != + MLX5_PHYS_PORT_NAME_TYPE_PFVF) { + rte_errno = EBUSY; + return NULL; + } + break; + case RTE_ETH_REPRESENTOR_NONE: rte_errno = EBUSY; return NULL; - } - if (eth_da.type != RTE_ETH_REPRESENTOR_VF) { + break; + default: rte_errno = ENOTSUP; DRV_LOG(ERR, "unsupported representor type: %s", dpdk_dev->devargs->args); return NULL; } - for (i = 0; i < eth_da.nb_representor_ports; ++i) - if (eth_da.representor_ports[i] == + /* Check controller ID: */ + for (i = 0; i < eth_da->nb_mh_controllers; ++i) + if (eth_da->mh_controllers[i] == + (uint16_t)switch_info->ctrl_num) + break; + if (eth_da->nb_mh_controllers && + i == eth_da->nb_mh_controllers) { + rte_errno = EBUSY; + return NULL; + } + /* Check SF/VF ID: */ + for (i = 0; i < eth_da->nb_representor_ports; ++i) + if (eth_da->representor_ports[i] == (uint16_t)switch_info->port_name) break; - if (i == eth_da.nb_representor_ports) { + if (eth_da->type != RTE_ETH_REPRESENTOR_PF && + i == eth_da->nb_representor_ports) { rte_errno = EBUSY; return NULL; } + /* Check PF ID. Check after repr port to avoid warning flood. */ + if (spawn->pf_bond >= 0) { + for (i = 0; i < eth_da->nb_ports; ++i) + if (eth_da->ports[i] == + (uint16_t)switch_info->pf_num) + break; + if (eth_da->nb_ports && i == eth_da->nb_ports) { + /* For backward compatibility, bonding + * representor syntax supported with limitation, + * device iterator won't find it: + * ,representor=# + */ + if (switch_info->pf_num > 0 && + eth_da->ports[0] == 0) { + DRV_LOG(WARNING, "Representor on Bonding PF should use pf#vf# format: %s", + dpdk_dev->devargs->args); + } else { + rte_errno = EBUSY; + return NULL; + } + } + } else if (eth_da->nb_ports > 1 || eth_da->ports[0]) { + rte_errno = EINVAL; + DRV_LOG(ERR, "PF id not supported by non-bond device: %s", + dpdk_dev->devargs->args); + return NULL; + } } /* Build device name. */ if (spawn->pf_bond < 0) { @@ -731,8 +782,11 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev, if (!switch_info->representor) strlcpy(name, dpdk_dev->name, sizeof(name)); else - snprintf(name, sizeof(name), "%s_representor_%u", - dpdk_dev->name, switch_info->port_name); + snprintf(name, sizeof(name), "%s_representor_%s%u", + dpdk_dev->name, + switch_info->name_type == + MLX5_PHYS_PORT_NAME_TYPE_PFSF ? "sf" : "vf", + switch_info->port_name); } else { /* Bonding device. */ if (!switch_info->representor) @@ -740,9 +794,11 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev, dpdk_dev->name, mlx5_os_get_dev_device_name(spawn->phys_dev)); else - snprintf(name, sizeof(name), "%s_%s_representor_%u", + snprintf(name, sizeof(name), "%s_%s_representor_%s%u", dpdk_dev->name, mlx5_os_get_dev_device_name(spawn->phys_dev), + switch_info->name_type == + MLX5_PHYS_PORT_NAME_TYPE_PFSF ? "sf" : "vf", switch_info->port_name); } /* check if the device is already spawned */ @@ -1790,6 +1846,7 @@ mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, struct mlx5_dev_spawn_data *list = NULL; struct mlx5_dev_config dev_config; unsigned int dev_config_vf; + struct rte_eth_devargs eth_da = { .type = RTE_ETH_REPRESENTOR_NONE }; int ret; if (rte_eal_process_type() == RTE_PROC_PRIMARY) @@ -1800,6 +1857,27 @@ mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, strerror(rte_errno)); return -rte_errno; } + if (pci_dev->device.devargs) { + /* Parse representor information from device argument. */ + if (pci_dev->device.devargs->cls_str) + ret = rte_eth_devargs_parse( + pci_dev->device.devargs->cls_str, ð_da); + if (ret) { + DRV_LOG(ERR, "failed to parse device arguments: %s", + pci_dev->device.devargs->cls_str); + return -rte_errno; + } + if (eth_da.type == RTE_ETH_REPRESENTOR_NONE) { + /* Support legacy device argument */ + ret = rte_eth_devargs_parse( + pci_dev->device.devargs->args, ð_da); + if (ret) { + DRV_LOG(ERR, "failed to parse device arguments: %s", + pci_dev->device.devargs->args); + return -rte_errno; + } + } + } errno = 0; ibv_list = mlx5_glue->get_device_list(&ret); if (!ibv_list) { @@ -1972,6 +2050,8 @@ mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, case MLX5_PHYS_PORT_NAME_TYPE_PFHPF: /* Fallthrough */ case MLX5_PHYS_PORT_NAME_TYPE_PFVF: + /* Fallthrough */ + case MLX5_PHYS_PORT_NAME_TYPE_PFSF: if (list[ns].info.pf_num == bd) ns++; break; @@ -2149,7 +2229,8 @@ mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, dev_config.log_hp_size = MLX5_ARG_UNSET; list[i].eth_dev = mlx5_dev_spawn(&pci_dev->device, &list[i], - &dev_config); + &dev_config, + ð_da); if (!list[i].eth_dev) { if (rte_errno != EBUSY && rte_errno != EEXIST) break; diff --git a/drivers/net/mlx5/mlx5_ethdev.c b/drivers/net/mlx5/mlx5_ethdev.c index 45ee7e4488..ad6aacc329 100644 --- a/drivers/net/mlx5/mlx5_ethdev.c +++ b/drivers/net/mlx5/mlx5_ethdev.c @@ -374,6 +374,8 @@ mlx5_dev_infos_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *info) break; } } + if (priv->master) + info->dev_capa = RTE_ETH_DEV_CAPA_REPRESENTOR_SF; return 0; } From patchwork Tue Jan 19 07:28:10 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Xueming Li X-Patchwork-Id: 86870 X-Patchwork-Delegate: rasland@nvidia.com Return-Path: X-Original-To: patchwork@inbox.dpdk.org Delivered-To: patchwork@inbox.dpdk.org Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124]) by inbox.dpdk.org (Postfix) with ESMTP id DDF81A0A03; Tue, 19 Jan 2021 08:30:34 +0100 (CET) Received: from [217.70.189.124] (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id B3CD8140D9D; Tue, 19 Jan 2021 08:30:02 +0100 (CET) Received: from mellanox.co.il (mail-il-dmz.mellanox.com [193.47.165.129]) by mails.dpdk.org (Postfix) with ESMTP id EB3A1140CF8 for ; Tue, 19 Jan 2021 08:29:53 +0100 (CET) Received: from Internal Mail-Server by MTLPINE1 (envelope-from xuemingl@nvidia.com) with SMTP; 19 Jan 2021 09:29:52 +0200 Received: from nvidia.com (pegasus05.mtr.labs.mlnx [10.210.16.100]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id 10J7Tpqn014531; Tue, 19 Jan 2021 09:29:52 +0200 From: Xueming Li To: Viacheslav Ovsiienko Cc: dev@dpdk.org, xuemingl@nvidia.com, Asaf Penso , Anatoly Burakov Date: Tue, 19 Jan 2021 07:28:10 +0000 Message-Id: <1611041295-12797-5-git-send-email-xuemingl@nvidia.com> X-Mailer: git-send-email 1.8.3.1 In-Reply-To: <1611041295-12797-1-git-send-email-xuemingl@nvidia.com> References: <1611041295-12797-1-git-send-email-xuemingl@nvidia.com> In-Reply-To: <1608304614-13908-2-git-send-email-xuemingl@nvidia.com> References: <1608304614-13908-2-git-send-email-xuemingl@nvidia.com> Subject: [dpdk-dev] [PATCH v4 4/8] net/mlx5: refactor bonding representor probe 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 Sender: "dev" To probe representor on 2nd PF of kernel bonding device, had to specify PF1 BDF in devarg: ,representor=0 When closing bonding device, all representors had to be closed together and this implies all representors have to use primary PF of bonding device. So after probing representor port on 2nd PF, when locating new probed device using device argument, the filter used 2nd PF as PCI address and failed to locate new device. Conflict happened by using current representor devargs: - Use PCI BDF to specify representor owner PF - Use PCI BDF to locate probed representor device. - PMD uses primary PCI BDF as PCI device. To resolve such conflicts, new representor syntax is introduced here: ,representor=pfXvfY All representors must use primary PF as owner PCI device, PMD internally locate owner PCI address by checking representor "pfX" part. To EAL, all representors are registered to primary PCI device, the 2nd PF is hidden to EAL, thus all search should be consistent. Same to VF representor, HPF (host PF on BlueField) uses same syntax to probe, example: representor=pf1vf[0-3,-1] This patch also adds pf index into kernel bonding representor port name: __representor_pfvf Signed-off-by: Xueming Li Acked-by: Viacheslav Ovsiienko --- doc/guides/nics/mlx5.rst | 4 +- drivers/net/mlx5/linux/mlx5_os.c | 263 +++++++++++++++++-------------- drivers/net/mlx5/mlx5.c | 22 +++ drivers/net/mlx5/mlx5.h | 3 +- drivers/net/mlx5/mlx5_defs.h | 4 - drivers/net/mlx5/mlx5_ethdev.c | 27 ---- drivers/net/mlx5/mlx5_mac.c | 8 +- 7 files changed, 177 insertions(+), 154 deletions(-) diff --git a/doc/guides/nics/mlx5.rst b/doc/guides/nics/mlx5.rst index c7829007a4..eaca4fc058 100644 --- a/doc/guides/nics/mlx5.rst +++ b/doc/guides/nics/mlx5.rst @@ -878,11 +878,11 @@ Driver options For instance, to probe VF port representors 0 through 2:: - representor=vf[0-2] + ,representor=vf[0-2] To probe SF port representors 0 through 2:: - representor=sf[0-2] + ,representor=sf[0-2] - ``max_dump_files_num`` parameter [int] diff --git a/drivers/net/mlx5/linux/mlx5_os.c b/drivers/net/mlx5/linux/mlx5_os.c index 7b320e8b72..9ae5910f46 100644 --- a/drivers/net/mlx5/linux/mlx5_os.c +++ b/drivers/net/mlx5/linux/mlx5_os.c @@ -645,6 +645,72 @@ mlx5_flow_counter_mode_config(struct rte_eth_dev *dev __rte_unused) #endif } +/** + * Check if representor spawn info match devargs. + * + * @param spawn + * Verbs device parameters (name, port, switch_info) to spawn. + * @param eth_da + * Device devargs to probe. + * @param repr_id + * Encoded representor ID. + * + * @return + * Match result. + */ +static bool +mlx5_representor_match(struct mlx5_dev_spawn_data *spawn, + struct rte_eth_devargs *eth_da, + uint16_t repr_id) +{ + const struct mlx5_switch_info *switch_info = &spawn->info; + unsigned int c, p, f; + uint16_t repr; + + switch (eth_da->type) { + case RTE_ETH_REPRESENTOR_SF: + if (switch_info->name_type != MLX5_PHYS_PORT_NAME_TYPE_PFSF) { + rte_errno = EBUSY; + return false; + } + break; + case RTE_ETH_REPRESENTOR_VF: + /* Allows HPF representor index -1 as exception. */ + if (!(spawn->info.port_name == -1 && + switch_info->name_type == + MLX5_PHYS_PORT_NAME_TYPE_PFHPF) && + switch_info->name_type != MLX5_PHYS_PORT_NAME_TYPE_PFVF) { + rte_errno = EBUSY; + return false; + } + break; + case RTE_ETH_REPRESENTOR_NONE: + rte_errno = EBUSY; + return false; + default: + rte_errno = ENOTSUP; + DRV_LOG(ERR, "unsupported representor type"); + return false; + } + /* Check representor ID: */ + for (c = 0; c < eth_da->nb_mh_controllers; ++c) { + for (p = 0; p < eth_da->nb_ports; ++p) { + for (f = 0; f < eth_da->nb_representor_ports; ++f) { + repr = rte_eth_representor_id_encode( + eth_da->mh_controllers[c], + eth_da->ports[p], + eth_da->type, + eth_da->representor_ports[f]); + if (repr_id == repr) + return true; + } + } + } + rte_errno = EBUSY; + return false; +} + + /** * Spawn an Ethernet device from Verbs information. * @@ -676,6 +742,7 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev, struct mlx5dv_context dv_attr = { .comp_mask = 0 }; struct rte_eth_dev *eth_dev = NULL; struct mlx5_priv *priv = NULL; + uint16_t repr_id = RTE_NO_REPRESENTOR_ID; int err = 0; unsigned int hw_padding = 0; unsigned int mps; @@ -692,115 +759,52 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev, char name[RTE_ETH_NAME_MAX_LEN]; int own_domain_id = 0; uint16_t port_id; - unsigned int i; #ifdef HAVE_MLX5DV_DR_DEVX_PORT struct mlx5dv_devx_port devx_port = { .comp_mask = 0 }; #endif + if (switch_info->representor) + repr_id = rte_eth_representor_id_encode( + switch_info->ctrl_num, + spawn->pf_bond >= 0 ? switch_info->pf_num : 0, + switch_info->name_type == + MLX5_PHYS_PORT_NAME_TYPE_PFSF ? + RTE_ETH_REPRESENTOR_SF : RTE_ETH_REPRESENTOR_VF, + switch_info->port_name); /* Determine if this port representor is supposed to be spawned. */ - if (switch_info->representor && dpdk_dev->devargs) { - switch (eth_da->type) { - case RTE_ETH_REPRESENTOR_SF: - if (switch_info->name_type != - MLX5_PHYS_PORT_NAME_TYPE_PFSF) { - rte_errno = EBUSY; - return NULL; - } - break; - case RTE_ETH_REPRESENTOR_VF: - /* Allows HPF representor index -1 as exception. */ - if (!(spawn->info.port_name == -1 && - switch_info->name_type == - MLX5_PHYS_PORT_NAME_TYPE_PFHPF) && - switch_info->name_type != - MLX5_PHYS_PORT_NAME_TYPE_PFVF) { - rte_errno = EBUSY; - return NULL; - } - break; - case RTE_ETH_REPRESENTOR_NONE: - rte_errno = EBUSY; - return NULL; - break; - default: - rte_errno = ENOTSUP; - DRV_LOG(ERR, "unsupported representor type: %s", - dpdk_dev->devargs->args); - return NULL; - } - /* Check controller ID: */ - for (i = 0; i < eth_da->nb_mh_controllers; ++i) - if (eth_da->mh_controllers[i] == - (uint16_t)switch_info->ctrl_num) - break; - if (eth_da->nb_mh_controllers && - i == eth_da->nb_mh_controllers) { - rte_errno = EBUSY; - return NULL; - } - /* Check SF/VF ID: */ - for (i = 0; i < eth_da->nb_representor_ports; ++i) - if (eth_da->representor_ports[i] == - (uint16_t)switch_info->port_name) - break; - if (eth_da->type != RTE_ETH_REPRESENTOR_PF && - i == eth_da->nb_representor_ports) { - rte_errno = EBUSY; - return NULL; - } - /* Check PF ID. Check after repr port to avoid warning flood. */ - if (spawn->pf_bond >= 0) { - for (i = 0; i < eth_da->nb_ports; ++i) - if (eth_da->ports[i] == - (uint16_t)switch_info->pf_num) - break; - if (eth_da->nb_ports && i == eth_da->nb_ports) { - /* For backward compatibility, bonding - * representor syntax supported with limitation, - * device iterator won't find it: - * ,representor=# - */ - if (switch_info->pf_num > 0 && - eth_da->ports[0] == 0) { - DRV_LOG(WARNING, "Representor on Bonding PF should use pf#vf# format: %s", - dpdk_dev->devargs->args); - } else { - rte_errno = EBUSY; - return NULL; - } - } - } else if (eth_da->nb_ports > 1 || eth_da->ports[0]) { - rte_errno = EINVAL; - DRV_LOG(ERR, "PF id not supported by non-bond device: %s", - dpdk_dev->devargs->args); - return NULL; - } - } + if (switch_info->representor && dpdk_dev->devargs && + !mlx5_representor_match(spawn, eth_da, repr_id)) + return NULL; /* Build device name. */ if (spawn->pf_bond < 0) { /* Single device. */ if (!switch_info->representor) strlcpy(name, dpdk_dev->name, sizeof(name)); else - snprintf(name, sizeof(name), "%s_representor_%s%u", + err = snprintf(name, sizeof(name), "%s_representor_%s%u", dpdk_dev->name, switch_info->name_type == MLX5_PHYS_PORT_NAME_TYPE_PFSF ? "sf" : "vf", switch_info->port_name); } else { /* Bonding device. */ - if (!switch_info->representor) - snprintf(name, sizeof(name), "%s_%s", + if (!switch_info->representor) { + err = snprintf(name, sizeof(name), "%s_%s", dpdk_dev->name, mlx5_os_get_dev_device_name(spawn->phys_dev)); - else - snprintf(name, sizeof(name), "%s_%s_representor_%s%u", - dpdk_dev->name, - mlx5_os_get_dev_device_name(spawn->phys_dev), - switch_info->name_type == - MLX5_PHYS_PORT_NAME_TYPE_PFSF ? "sf" : "vf", - switch_info->port_name); + } else { + err = snprintf(name, sizeof(name), "%s_%s_representor_c%dpf%d%s%u", + dpdk_dev->name, + mlx5_os_get_dev_device_name(spawn->phys_dev), + switch_info->ctrl_num, + switch_info->pf_num, + switch_info->name_type == + MLX5_PHYS_PORT_NAME_TYPE_PFSF ? "sf" : "vf", + switch_info->port_name); + } } + if (err >= (int)sizeof(name)) + DRV_LOG(WARNING, "device name overflow %s", name); /* check if the device is already spawned */ if (rte_eth_dev_get_port_by_name(name, &port_id) == 0) { rte_errno = EEXIST; @@ -1073,11 +1077,7 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev, priv->vport_id = switch_info->representor ? switch_info->port_name + 1 : -1; #endif - /* representor_id field keeps the unmodified VF index. */ - priv->representor_id = switch_info->representor ? - rte_eth_representor_id_encode(0, 0, RTE_ETH_REPRESENTOR_VF, - switch_info->port_name) : - -1; + priv->representor_id = repr_id; /* * Look for sibling devices in order to reuse their switch domain * if any, otherwise allocate one. @@ -1692,9 +1692,11 @@ mlx5_dev_spawn_data_cmp(const void *a, const void *b) * @param[in] ibv_dev * Pointer to Infiniband device structure. * @param[in] pci_dev - * Pointer to PCI device structure to match PCI address. + * Pointer to primary PCI address structure to match. * @param[in] nl_rdma * Netlink RDMA group socket handle. + * @param[in] owner + * Rerepsentor owner PF index. * * @return * negative value if no bonding device found, otherwise @@ -1702,8 +1704,8 @@ mlx5_dev_spawn_data_cmp(const void *a, const void *b) */ static int mlx5_device_bond_pci_match(const struct ibv_device *ibv_dev, - const struct rte_pci_device *pci_dev, - int nl_rdma) + const struct rte_pci_addr *pci_dev, + int nl_rdma, uint16_t owner) { char ifname[IF_NAMESIZE + 1]; unsigned int ifindex; @@ -1760,10 +1762,10 @@ mlx5_device_bond_pci_match(const struct ibv_device *ibv_dev, " for netdev \"%s\"", ifname); continue; } - if (pci_dev->addr.domain != pci_addr.domain || - pci_dev->addr.bus != pci_addr.bus || - pci_dev->addr.devid != pci_addr.devid || - pci_dev->addr.function != pci_addr.function) + if (pci_dev->domain != pci_addr.domain || + pci_dev->bus != pci_addr.bus || + pci_dev->devid != pci_addr.devid || + pci_dev->function + owner != pci_addr.function) continue; /* Slave interface PCI address match found. */ fclose(file); @@ -1831,7 +1833,8 @@ mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, struct mlx5_dev_config dev_config; unsigned int dev_config_vf; struct rte_eth_devargs eth_da = { .type = RTE_ETH_REPRESENTOR_NONE }; - int ret; + struct rte_pci_addr owner_pci = pci_dev->addr; /* Owner PF. */ + int ret = -1; if (rte_eal_process_type() == RTE_PROC_PRIMARY) mlx5_pmd_socket_init(); @@ -1883,7 +1886,8 @@ mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, DRV_LOG(DEBUG, "checking device \"%s\"", ibv_list[ret]->name); bd = mlx5_device_bond_pci_match - (ibv_list[ret], pci_dev, nl_rdma); + (ibv_list[ret], &owner_pci, nl_rdma, + eth_da.ports[0]); if (bd >= 0) { /* * Bonding device detected. Only one match is allowed, @@ -1900,23 +1904,28 @@ mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, ret = -rte_errno; goto exit; } + /* Amend owner pci address if owner PF ID specified. */ + if (eth_da.nb_representor_ports) + owner_pci.function += eth_da.ports[0]; DRV_LOG(INFO, "PCI information matches for" " slave %d bonding device \"%s\"", bd, ibv_list[ret]->name); ibv_match[nd++] = ibv_list[ret]; break; + } else { + /* Bonding device not found. */ + if (mlx5_dev_to_pci_addr + (ibv_list[ret]->ibdev_path, &pci_addr)) + continue; + if (owner_pci.domain != pci_addr.domain || + owner_pci.bus != pci_addr.bus || + owner_pci.devid != pci_addr.devid || + owner_pci.function != pci_addr.function) + continue; + DRV_LOG(INFO, "PCI information matches for device \"%s\"", + ibv_list[ret]->name); + ibv_match[nd++] = ibv_list[ret]; } - if (mlx5_dev_to_pci_addr - (ibv_list[ret]->ibdev_path, &pci_addr)) - continue; - if (pci_dev->addr.domain != pci_addr.domain || - pci_dev->addr.bus != pci_addr.bus || - pci_dev->addr.devid != pci_addr.devid || - pci_dev->addr.function != pci_addr.function) - continue; - DRV_LOG(INFO, "PCI information matches for device \"%s\"", - ibv_list[ret]->name); - ibv_match[nd++] = ibv_list[ret]; } ibv_match[nd] = NULL; if (!nd) { @@ -1924,8 +1933,8 @@ mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, DRV_LOG(WARNING, "no Verbs device matches PCI device " PCI_PRI_FMT "," " are kernel drivers loaded?", - pci_dev->addr.domain, pci_dev->addr.bus, - pci_dev->addr.devid, pci_dev->addr.function); + owner_pci.domain, owner_pci.bus, + owner_pci.devid, owner_pci.function); rte_errno = ENOENT; ret = -rte_errno; goto exit; @@ -2190,6 +2199,24 @@ mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, dev_config_vf = 0; break; } + if (eth_da.type != RTE_ETH_REPRESENTOR_NONE) { + /* Set devargs default values. */ + if (eth_da.nb_mh_controllers == 0) { + eth_da.nb_mh_controllers = 1; + eth_da.mh_controllers[0] = 0; + } + if (eth_da.nb_ports == 0 && ns > 0) { + if (list[0].pf_bond >= 0 && list[0].info.representor) + DRV_LOG(WARNING, "Representor on Bonding device should use pf#vf# syntax: %s", + pci_dev->device.devargs->args); + eth_da.nb_ports = 1; + eth_da.ports[0] = list[0].info.pf_num; + } + if (eth_da.nb_representor_ports == 0) { + eth_da.nb_representor_ports = 1; + eth_da.representor_ports[0] = 0; + } + } for (i = 0; i != ns; ++i) { uint32_t restore; @@ -2231,8 +2258,8 @@ mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, DRV_LOG(ERR, "probe of PCI device " PCI_PRI_FMT " aborted after" " encountering an error: %s", - pci_dev->addr.domain, pci_dev->addr.bus, - pci_dev->addr.devid, pci_dev->addr.function, + owner_pci.domain, owner_pci.bus, + owner_pci.devid, owner_pci.function, strerror(rte_errno)); ret = -rte_errno; /* Roll back. */ diff --git a/drivers/net/mlx5/mlx5.c b/drivers/net/mlx5/mlx5.c index 5e8cd6a3df..d613ffd655 100644 --- a/drivers/net/mlx5/mlx5.c +++ b/drivers/net/mlx5/mlx5.c @@ -355,6 +355,28 @@ static const struct mlx5_indexed_pool_config mlx5_ipool_cfg[] = { #define MLX5_FLOW_TABLE_HLIST_ARRAY_SIZE 4096 +/** + * Decide whether representor ID is a HPF(host PF) port on BF2. + * + * @param dev + * Pointer to Ethernet device structure. + * + * @return + * Non-zero if HPF, otherwise 0. + */ +int +mlx5_is_hpf(struct rte_eth_dev *dev) +{ + struct mlx5_priv *priv = dev->data->dev_private; + enum rte_eth_representor_type type; + uint16_t port; + + port = rte_eth_representor_id_parse(priv->representor_id, + NULL, NULL, &type); + return priv->representor && type == RTE_ETH_REPRESENTOR_VF && + port == rte_eth_representor_id_parse(-1, NULL, NULL, NULL); +} + /** * Initialize the ASO aging management structure. * diff --git a/drivers/net/mlx5/mlx5.h b/drivers/net/mlx5/mlx5.h index e06e0ff3bb..e7afa438ce 100644 --- a/drivers/net/mlx5/mlx5.h +++ b/drivers/net/mlx5/mlx5.h @@ -915,7 +915,7 @@ struct mlx5_priv { uint16_t vport_id; /* Associated VF vport index (if any). */ uint32_t vport_meta_tag; /* Used for vport index match ove VF LAG. */ uint32_t vport_meta_mask; /* Used for vport index field match mask. */ - int32_t representor_id; /* Port representor identifier. */ + int32_t representor_id; /* RTE_ETH_REPR(), -1 if not a representor. */ int32_t pf_bond; /* >=0 means PF index in bonding configuration. */ unsigned int if_index; /* Associated kernel network device index. */ uint32_t bond_ifindex; /**< Bond interface index. */ @@ -988,6 +988,7 @@ int mlx5_udp_tunnel_port_add(struct rte_eth_dev *dev, struct rte_eth_udp_tunnel *udp_tunnel); uint16_t mlx5_eth_find_next(uint16_t port_id, struct rte_pci_device *pci_dev); int mlx5_dev_close(struct rte_eth_dev *dev); +int mlx5_is_hpf(struct rte_eth_dev *dev); void mlx5_age_event_prepare(struct mlx5_dev_ctx_shared *sh); /* Macro to iterate over all valid ports for mlx5 driver. */ diff --git a/drivers/net/mlx5/mlx5_defs.h b/drivers/net/mlx5/mlx5_defs.h index 85a0979653..4648196550 100644 --- a/drivers/net/mlx5/mlx5_defs.h +++ b/drivers/net/mlx5/mlx5_defs.h @@ -48,10 +48,6 @@ #define MLX5_PMD_SOFT_COUNTERS 1 #endif -/* Switch port ID parameters for bonding configurations. */ -#define MLX5_PORT_ID_BONDING_PF_MASK 0xf -#define MLX5_PORT_ID_BONDING_PF_SHIFT 12 - /* Alarm timeout. */ #define MLX5_ALARM_TIMEOUT_US 100000 diff --git a/drivers/net/mlx5/mlx5_ethdev.c b/drivers/net/mlx5/mlx5_ethdev.c index ad6aacc329..5341eb16c9 100644 --- a/drivers/net/mlx5/mlx5_ethdev.c +++ b/drivers/net/mlx5/mlx5_ethdev.c @@ -330,33 +330,6 @@ mlx5_dev_infos_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *info) if (priv->representor) { uint16_t port_id; - if (priv->pf_bond >= 0) { - /* - * Switch port ID is opaque value with driver defined - * format. Push the PF index in bonding configurations - * in upper four bits of port ID. If we get too many - * representors (more than 4K) or PFs (more than 15) - * this approach must be reconsidered. - */ - /* Switch port ID for VF representors: 0 - 0xFFE */ - if ((info->switch_info.port_id != 0xffff && - info->switch_info.port_id >= - ((1 << MLX5_PORT_ID_BONDING_PF_SHIFT) - 1)) || - priv->pf_bond > MLX5_PORT_ID_BONDING_PF_MASK) { - DRV_LOG(ERR, "can't update switch port ID" - " for bonding device"); - MLX5_ASSERT(false); - return -ENODEV; - } - /* - * Switch port ID for Host PF representor - * (representor_id is -1) , set to 0xFFF - */ - if (info->switch_info.port_id == 0xffff) - info->switch_info.port_id = 0xfff; - info->switch_info.port_id |= - priv->pf_bond << MLX5_PORT_ID_BONDING_PF_SHIFT; - } MLX5_ETH_FOREACH_DEV(port_id, priv->pci_dev) { struct mlx5_priv *opriv = rte_eth_devices[port_id].data->dev_private; diff --git a/drivers/net/mlx5/mlx5_mac.c b/drivers/net/mlx5/mlx5_mac.c index bd786fd638..b5b810b508 100644 --- a/drivers/net/mlx5/mlx5_mac.c +++ b/drivers/net/mlx5/mlx5_mac.c @@ -159,7 +159,7 @@ mlx5_mac_addr_set(struct rte_eth_dev *dev, struct rte_ether_addr *mac_addr) * Configuring the VF instead of its representor, * need to skip the special case of HPF on Bluefield. */ - if (priv->representor && priv->representor_id >= 0) { + if (priv->representor && !mlx5_is_hpf(dev)) { DRV_LOG(DEBUG, "VF represented by port %u setting primary MAC address", dev->data->port_id); RTE_ETH_FOREACH_DEV_SIBLING(port_id, dev->data->port_id) { @@ -169,7 +169,11 @@ mlx5_mac_addr_set(struct rte_eth_dev *dev, struct rte_ether_addr *mac_addr) return mlx5_os_vf_mac_addr_modify (priv, mlx5_ifindex(&rte_eth_devices[port_id]), - mac_addr, priv->representor_id); + mac_addr, + rte_eth_representor_id_parse( + priv->representor_id, + NULL, NULL, NULL) + ); } } rte_errno = -ENOTSUP; From patchwork Tue Jan 19 07:28:11 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Xueming Li X-Patchwork-Id: 86872 X-Patchwork-Delegate: rasland@nvidia.com Return-Path: X-Original-To: patchwork@inbox.dpdk.org Delivered-To: patchwork@inbox.dpdk.org Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124]) by inbox.dpdk.org (Postfix) with ESMTP id 35F6EA0A03; Tue, 19 Jan 2021 08:30:53 +0100 (CET) Received: from [217.70.189.124] (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id 2DE1F140DBA; Tue, 19 Jan 2021 08:30:05 +0100 (CET) Received: from mellanox.co.il (mail-il-dmz.mellanox.com [193.47.165.129]) by mails.dpdk.org (Postfix) with ESMTP id 0DB5A140D45 for ; Tue, 19 Jan 2021 08:29:53 +0100 (CET) Received: from Internal Mail-Server by MTLPINE1 (envelope-from xuemingl@nvidia.com) with SMTP; 19 Jan 2021 09:29:52 +0200 Received: from nvidia.com (pegasus05.mtr.labs.mlnx [10.210.16.100]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id 10J7Tpqo014531; Tue, 19 Jan 2021 09:29:52 +0200 From: Xueming Li To: Viacheslav Ovsiienko Cc: dev@dpdk.org, xuemingl@nvidia.com, Asaf Penso Date: Tue, 19 Jan 2021 07:28:11 +0000 Message-Id: <1611041295-12797-6-git-send-email-xuemingl@nvidia.com> X-Mailer: git-send-email 1.8.3.1 In-Reply-To: <1611041295-12797-1-git-send-email-xuemingl@nvidia.com> References: <1611041295-12797-1-git-send-email-xuemingl@nvidia.com> In-Reply-To: <1608304614-13908-2-git-send-email-xuemingl@nvidia.com> References: <1608304614-13908-2-git-send-email-xuemingl@nvidia.com> Subject: [dpdk-dev] [PATCH v4 5/8] net/mlx5: support representor from multiple PFs 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 Sender: "dev" To probe representors from different kernel bonding PFs, had to specify 2 separate devargs like this: -a 03:00.0,representor=pf0vf[0-3] -a 03:00.0,representor=pf1vf[0-3] This patch supports range or list of PF section in devargs, so the alternative short devargs of above is: -a 03:00.0,representor=pf[0-1]vf[0-3] Signed-off-by: Xueming Li Acked-by: Viacheslav Ovsiienko --- doc/guides/nics/mlx5.rst | 4 ++ drivers/net/mlx5/linux/mlx5_os.c | 100 +++++++++++++++++++++---------- 2 files changed, 72 insertions(+), 32 deletions(-) diff --git a/doc/guides/nics/mlx5.rst b/doc/guides/nics/mlx5.rst index eaca4fc058..480c9d3fc1 100644 --- a/doc/guides/nics/mlx5.rst +++ b/doc/guides/nics/mlx5.rst @@ -884,6 +884,10 @@ Driver options ,representor=sf[0-2] + To probe VF port representors 0 through 2 on both PFs of bonding device:: + + ,representor=pf[0,1]vf[0-2] + - ``max_dump_files_num`` parameter [int] The maximum number of files per PMD entity that may be created for debug information. diff --git a/drivers/net/mlx5/linux/mlx5_os.c b/drivers/net/mlx5/linux/mlx5_os.c index 9ae5910f46..521a0a5789 100644 --- a/drivers/net/mlx5/linux/mlx5_os.c +++ b/drivers/net/mlx5/linux/mlx5_os.c @@ -1788,21 +1788,25 @@ mlx5_device_bond_pci_match(const struct ibv_device *ibv_dev, } /** - * DPDK callback to register a PCI device. + * Register a PCI device within bonding. * - * This function spawns Ethernet devices out of a given PCI device. + * This function spawns Ethernet devices out of a given PCI device and + * bonding owner PF index. * - * @param[in] pci_drv - * PCI driver structure (mlx5_driver). * @param[in] pci_dev * PCI device information. + * @param[in] req_eth_da + * Requested ethdev device argument. + * @param[in] owner_id + * Requested owner PF port ID within bonding device, default to 0. * * @return * 0 on success, a negative errno value otherwise and rte_errno is set. */ -int -mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, - struct rte_pci_device *pci_dev) +static int +mlx5_os_pci_probe_pf(struct rte_pci_device *pci_dev, + struct rte_eth_devargs *req_eth_da, + uint16_t owner_id) { struct ibv_device **ibv_list; /* @@ -1832,7 +1836,7 @@ mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, struct mlx5_dev_spawn_data *list = NULL; struct mlx5_dev_config dev_config; unsigned int dev_config_vf; - struct rte_eth_devargs eth_da = { .type = RTE_ETH_REPRESENTOR_NONE }; + struct rte_eth_devargs eth_da = *req_eth_da; struct rte_pci_addr owner_pci = pci_dev->addr; /* Owner PF. */ int ret = -1; @@ -1844,27 +1848,6 @@ mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, strerror(rte_errno)); return -rte_errno; } - if (pci_dev->device.devargs) { - /* Parse representor information from device argument. */ - if (pci_dev->device.devargs->cls_str) - ret = rte_eth_devargs_parse( - pci_dev->device.devargs->cls_str, ð_da); - if (ret) { - DRV_LOG(ERR, "failed to parse device arguments: %s", - pci_dev->device.devargs->cls_str); - return -rte_errno; - } - if (eth_da.type == RTE_ETH_REPRESENTOR_NONE) { - /* Support legacy device argument */ - ret = rte_eth_devargs_parse( - pci_dev->device.devargs->args, ð_da); - if (ret) { - DRV_LOG(ERR, "failed to parse device arguments: %s", - pci_dev->device.devargs->args); - return -rte_errno; - } - } - } errno = 0; ibv_list = mlx5_glue->get_device_list(&ret); if (!ibv_list) { @@ -1886,8 +1869,7 @@ mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, DRV_LOG(DEBUG, "checking device \"%s\"", ibv_list[ret]->name); bd = mlx5_device_bond_pci_match - (ibv_list[ret], &owner_pci, nl_rdma, - eth_da.ports[0]); + (ibv_list[ret], &owner_pci, nl_rdma, owner_id); if (bd >= 0) { /* * Bonding device detected. Only one match is allowed, @@ -1906,7 +1888,7 @@ mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, } /* Amend owner pci address if owner PF ID specified. */ if (eth_da.nb_representor_ports) - owner_pci.function += eth_da.ports[0]; + owner_pci.function += owner_id; DRV_LOG(INFO, "PCI information matches for" " slave %d bonding device \"%s\"", bd, ibv_list[ret]->name); @@ -2294,6 +2276,60 @@ mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, return ret; } +/** + * DPDK callback to register a PCI device. + * + * This function spawns Ethernet devices out of a given PCI device. + * + * @param[in] pci_drv + * PCI driver structure (mlx5_driver). + * @param[in] pci_dev + * PCI device information. + * + * @return + * 0 on success, a negative errno value otherwise and rte_errno is set. + */ +int +mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, + struct rte_pci_device *pci_dev) +{ + struct rte_eth_devargs eth_da = { .type = RTE_ETH_REPRESENTOR_NONE }; + int ret = 0; + uint16_t p; + + if (pci_dev->device.devargs) { + /* Parse representor information from device argument. */ + if (pci_dev->device.devargs->cls_str) + ret = rte_eth_devargs_parse( + pci_dev->device.devargs->cls_str, ð_da); + if (ret) { + DRV_LOG(ERR, "failed to parse device arguments: %s", + pci_dev->device.devargs->cls_str); + return -rte_errno; + } + if (eth_da.type == RTE_ETH_REPRESENTOR_NONE) { + /* Support legacy device argument */ + ret = rte_eth_devargs_parse( + pci_dev->device.devargs->args, ð_da); + if (ret) { + DRV_LOG(ERR, "failed to parse device arguments: %s", + pci_dev->device.devargs->args); + return -rte_errno; + } + } + } + + if (eth_da.nb_ports > 0) { + /* Iterate all port if devargs pf is range: "pf[0-1]vf[...]". */ + for (p = 0; p < eth_da.nb_ports; p++) + ret = mlx5_os_pci_probe_pf(pci_dev, ð_da, + eth_da.ports[p]); + } else { + ret = mlx5_os_pci_probe_pf(pci_dev, ð_da, 0); + } + return ret; +} + static int mlx5_config_doorbell_mapping_env(const struct mlx5_dev_config *config) { From patchwork Tue Jan 19 07:28:14 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Xueming Li X-Patchwork-Id: 86873 X-Patchwork-Delegate: rasland@nvidia.com Return-Path: X-Original-To: patchwork@inbox.dpdk.org Delivered-To: patchwork@inbox.dpdk.org Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124]) by inbox.dpdk.org (Postfix) with ESMTP id A8FBAA0A03; Tue, 19 Jan 2021 08:31:07 +0100 (CET) Received: from [217.70.189.124] (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id 19106140DDB; Tue, 19 Jan 2021 08:30:07 +0100 (CET) Received: from mellanox.co.il (mail-il-dmz.mellanox.com [193.47.165.129]) by mails.dpdk.org (Postfix) with ESMTP id B7991140D5D for ; Tue, 19 Jan 2021 08:29:58 +0100 (CET) Received: from Internal Mail-Server by MTLPINE1 (envelope-from xuemingl@nvidia.com) with SMTP; 19 Jan 2021 09:29:53 +0200 Received: from nvidia.com (pegasus05.mtr.labs.mlnx [10.210.16.100]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id 10J7Tpqr014531; Tue, 19 Jan 2021 09:29:53 +0200 From: Xueming Li To: Viacheslav Ovsiienko Cc: dev@dpdk.org, xuemingl@nvidia.com, Asaf Penso Date: Tue, 19 Jan 2021 07:28:14 +0000 Message-Id: <1611041295-12797-9-git-send-email-xuemingl@nvidia.com> X-Mailer: git-send-email 1.8.3.1 In-Reply-To: <1611041295-12797-1-git-send-email-xuemingl@nvidia.com> References: <1611041295-12797-1-git-send-email-xuemingl@nvidia.com> In-Reply-To: <1608304614-13908-2-git-send-email-xuemingl@nvidia.com> References: <1608304614-13908-2-git-send-email-xuemingl@nvidia.com> Subject: [dpdk-dev] [PATCH v4 8/8] net/mlx5: improve bonding xstats 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 Sender: "dev" In case of kernel bonding device, counter was read from first bonding PF member. This patch reads all member PFs and sums to get bond xstats. Signed-off-by: Xueming Li Acked-by: Viacheslav Ovsiienko --- drivers/net/mlx5/linux/mlx5_ethdev_os.c | 127 +++++++++++++++++++----- 1 file changed, 102 insertions(+), 25 deletions(-) diff --git a/drivers/net/mlx5/linux/mlx5_ethdev_os.c b/drivers/net/mlx5/linux/mlx5_ethdev_os.c index 84610a7bc0..27afb74aff 100644 --- a/drivers/net/mlx5/linux/mlx5_ethdev_os.c +++ b/drivers/net/mlx5/linux/mlx5_ethdev_os.c @@ -169,10 +169,10 @@ mlx5_get_ifname(const struct rte_eth_dev *dev, char (*ifname)[MLX5_NAMESIZE]) } /** - * Perform ifreq ioctl() on associated Ethernet device. + * Perform ifreq ioctl() on associated netdev ifname. * - * @param[in] dev - * Pointer to Ethernet device. + * @param[in] ifname + * Pointer to netdev name. * @param req * Request number to pass to ioctl(). * @param[out] ifr @@ -182,7 +182,7 @@ mlx5_get_ifname(const struct rte_eth_dev *dev, char (*ifname)[MLX5_NAMESIZE]) * 0 on success, a negative errno value otherwise and rte_errno is set. */ static int -mlx5_ifreq(const struct rte_eth_dev *dev, int req, struct ifreq *ifr) +mlx5_ifreq_by_ifname(const char *ifname, int req, struct ifreq *ifr) { int sock = socket(PF_INET, SOCK_DGRAM, IPPROTO_IP); int ret = 0; @@ -191,9 +191,7 @@ mlx5_ifreq(const struct rte_eth_dev *dev, int req, struct ifreq *ifr) rte_errno = errno; return -rte_errno; } - ret = mlx5_get_ifname(dev, &ifr->ifr_name); - if (ret) - goto error; + rte_strscpy(ifr->ifr_name, ifname, sizeof(ifr->ifr_name)); ret = ioctl(sock, req, ifr); if (ret == -1) { rte_errno = errno; @@ -206,6 +204,31 @@ mlx5_ifreq(const struct rte_eth_dev *dev, int req, struct ifreq *ifr) return -rte_errno; } +/** + * Perform ifreq ioctl() on associated Ethernet device. + * + * @param[in] dev + * Pointer to Ethernet device. + * @param req + * Request number to pass to ioctl(). + * @param[out] ifr + * Interface request structure output buffer. + * + * @return + * 0 on success, a negative errno value otherwise and rte_errno is set. + */ +static int +mlx5_ifreq(const struct rte_eth_dev *dev, int req, struct ifreq *ifr) +{ + char ifname[sizeof(ifr->ifr_name)]; + int ret; + + ret = mlx5_get_ifname(dev, &ifname); + if (ret) + return -rte_errno; + return mlx5_ifreq_by_ifname(ifname, req, ifr); +} + /** * Get device MTU. * @@ -1243,6 +1266,8 @@ int mlx5_get_module_eeprom(struct rte_eth_dev *dev, * * @param dev * Pointer to Ethernet device. + * @param[in] pf + * PF index in case of bonding device, -1 otherwise * @param[out] stats * Counters table output buffer. * @@ -1250,8 +1275,8 @@ int mlx5_get_module_eeprom(struct rte_eth_dev *dev, * 0 on success and stats is filled, negative errno value otherwise and * rte_errno is set. */ -int -mlx5_os_read_dev_counters(struct rte_eth_dev *dev, uint64_t *stats) +static int +_mlx5_os_read_dev_counters(struct rte_eth_dev *dev, int pf, uint64_t *stats) { struct mlx5_priv *priv = dev->data->dev_private; struct mlx5_xstats_ctrl *xstats_ctrl = &priv->xstats_ctrl; @@ -1265,7 +1290,11 @@ mlx5_os_read_dev_counters(struct rte_eth_dev *dev, uint64_t *stats) et_stats->cmd = ETHTOOL_GSTATS; et_stats->n_stats = xstats_ctrl->stats_n; ifr.ifr_data = (caddr_t)et_stats; - ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr); + if (pf >= 0) + ret = mlx5_ifreq_by_ifname(priv->sh->bond.ports[pf].ifname, + SIOCETHTOOL, &ifr); + else + ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr); if (ret) { DRV_LOG(WARNING, "port %u unable to read statistic values from device", @@ -1273,23 +1302,60 @@ mlx5_os_read_dev_counters(struct rte_eth_dev *dev, uint64_t *stats) return ret; } for (i = 0; i != xstats_ctrl->mlx5_stats_n; ++i) { - if (xstats_ctrl->info[i].dev) { - ret = mlx5_os_read_dev_stat(priv, - xstats_ctrl->info[i].ctr_name, - &stats[i]); - /* return last xstats counter if fail to read. */ - if (ret == 0) - xstats_ctrl->xstats[i] = stats[i]; - else - stats[i] = xstats_ctrl->xstats[i]; - } else { - stats[i] = (uint64_t) - et_stats->data[xstats_ctrl->dev_table_idx[i]]; - } + if (xstats_ctrl->info[i].dev) + continue; + stats[i] += (uint64_t) + et_stats->data[xstats_ctrl->dev_table_idx[i]]; } return 0; } +/** + * Read device counters. + * + * @param dev + * Pointer to Ethernet device. + * @param[out] stats + * Counters table output buffer. + * + * @return + * 0 on success and stats is filled, negative errno value otherwise and + * rte_errno is set. + */ +int +mlx5_os_read_dev_counters(struct rte_eth_dev *dev, uint64_t *stats) +{ + struct mlx5_priv *priv = dev->data->dev_private; + struct mlx5_xstats_ctrl *xstats_ctrl = &priv->xstats_ctrl; + int ret = 0, i; + + memset(stats, 0, sizeof(*stats) * xstats_ctrl->mlx5_stats_n); + /* Read ifreq counters. */ + if (priv->master && priv->pf_bond >= 0) { + /* Sum xstats from bonding device member ports. */ + for (i = 0; i < priv->sh->bond.n_port; i++) { + ret = _mlx5_os_read_dev_counters(dev, i, stats); + if (ret) + return ret; + } + } else { + ret = _mlx5_os_read_dev_counters(dev, -1, stats); + } + /* Read IB counters. */ + for (i = 0; i != xstats_ctrl->mlx5_stats_n; ++i) { + if (!xstats_ctrl->info[i].dev) + continue; + ret = mlx5_os_read_dev_stat(priv, xstats_ctrl->info[i].ctr_name, + &stats[i]); + /* return last xstats counter if fail to read. */ + if (ret != 0) + xstats_ctrl->xstats[i] = stats[i]; + else + stats[i] = xstats_ctrl->xstats[i]; + } + return ret; +} + /** * Query the number of statistics provided by ETHTOOL. * @@ -1303,13 +1369,19 @@ mlx5_os_read_dev_counters(struct rte_eth_dev *dev, uint64_t *stats) int mlx5_os_get_stats_n(struct rte_eth_dev *dev) { + struct mlx5_priv *priv = dev->data->dev_private; struct ethtool_drvinfo drvinfo; struct ifreq ifr; int ret; drvinfo.cmd = ETHTOOL_GDRVINFO; ifr.ifr_data = (caddr_t)&drvinfo; - ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr); + if (priv->master && priv->pf_bond >= 0) + /* Bonding PF. */ + ret = mlx5_ifreq_by_ifname(priv->sh->bond.ports[0].ifname, + SIOCETHTOOL, &ifr); + else + ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr); if (ret) { DRV_LOG(WARNING, "port %u unable to query number of statistics", dev->data->port_id); @@ -1480,7 +1552,12 @@ mlx5_os_stats_init(struct rte_eth_dev *dev) strings->string_set = ETH_SS_STATS; strings->len = dev_stats_n; ifr.ifr_data = (caddr_t)strings; - ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr); + if (priv->master && priv->pf_bond >= 0) + /* Bonding master. */ + ret = mlx5_ifreq_by_ifname(priv->sh->bond.ports[0].ifname, + SIOCETHTOOL, &ifr); + else + ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr); if (ret) { DRV_LOG(WARNING, "port %u unable to get statistic names", dev->data->port_id);