[dpdk-dev] [PATCH v2 2/4] net/mlx5: support representor of sub function

Xueming Li xuemingl at nvidia.com
Wed Jan 6 17:39:57 CET 2021


This patch supports of SF representor. Similar to VF representor, switch
port name of SF representor in sysfs phys_port_name is "pf<x>sf<y>".

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 <BDF>,representor=vf[list] -a <BDF>,representor=sf[list]

Signed-off-by: Xueming Li <xuemingl at nvidia.com>
---
 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 3bda0f8417..fc7e93842f 100644
--- a/doc/guides/nics/mlx5.rst
+++ b/doc/guides/nics/mlx5.rst
@@ -874,14 +874,18 @@ 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]
 
@@ -1253,15 +1257,15 @@ 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::
@@ -1288,6 +1292,40 @@ the DPDK application.
 
         echo switchdev > /sys/class/net/<net device>/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 eswitch 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 <mst device> 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 <mst device> reset
+
+3. Enable switchdev mode::
+
+        echo switchdev > /sys/class/net/<net device>/compat/devlink/mode
+
+4. Create SF::
+
+        mlnx-sf -d <PCI_BDF> -a create
+
+5. Probe SF representor::
+
+        testpmd> port attach <PCI_BDF>,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 7739a1b0a5..6f667dd747 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;
@@ -697,34 +700,82 @@ 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, &eth_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:
+				 *    <PF1_BDF>,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) {
@@ -732,8 +783,11 @@ 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)
@@ -741,9 +795,11 @@ 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 */
@@ -1802,6 +1858,7 @@ 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)
@@ -1812,6 +1869,27 @@ 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, &eth_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, &eth_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) {
@@ -1984,6 +2062,8 @@ 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;
@@ -2161,7 +2241,8 @@ 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,
+						 &eth_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;
 }
 
-- 
2.25.1



More information about the dev mailing list