Merge branch 'devlink-Introduce-PCI-PF-VF-ports-and-attributes'

Parav Pandit says:

====================
devlink: Introduce PCI PF, VF ports and attributes

This patchset carry forwards the work initiated in [1] and discussion
futher concluded at [2].

To improve visibility of representor netdevice, its association with
PF or VF, physical port, two new devlink port flavours are added as
PCI PF and PCI VF ports.

A sample eswitch view can be seen below, which will be futher extended to
mdev subdevices of a PCI function in future.

Patch-1 moves physical port's attribute to new structure
Patch-2 enhances netlink response to consider port flavour
Patch-3,4 extends devlink port attributes and port flavour
Patch-5 extends mlx5 driver to register devlink ports for PF, VF and
physical link.

+---+ +---+
vf| | | | pf
+-+-+ +-+-+
physical link <---------+ | |
| | |
| | |
+-+-+ +-+-+ +-+-+
| 1 | | 2 | | 3 |
+--+---+-----+---+------+---+--+
| physical vf pf |
| port port port |
| |
| eswitch |
| |
+------------------------------+

[1] https://www.spinics.net/lists/netdev/msg555797.html
[2] https://marc.info/?l=linux-netdev&m=155354609408485&w=2

Changelog:
v5->v6:
- Fixed port flavour check order for PCI PF vs other flavours in
netlink response.
- Changed 'physical' to 'phys'.
v4->v5:
- Split first patch to two patches to handle netlink response in
separate patch.
- Corrected typo 'otwerwise' to 'otherwise' in patches 3 and 4.
v3->v4:
- Addressed comments from Jiri.
- Split first patch to two patches.
- Renamed phys_port to physical to be consistent with pci_pf.
- Removed port_number from __devlink_port_attrs_set and moved
assignment to caller function.
- Used capital letter while moving old comment to new structure.
- Removed helper function is_devlink_phy_port_num_supported().
v2->v3:
- Made port_number and split_port_number applicable only to
physical port flavours.
v1->v2:
- Updated new APIs and mlx5 driver to drop port_number for PF, VF
attributes
- Updated port_number comment for its usage
- Limited putting port_number to physical ports
====================

Reviewed-by: Jakub Kicinski <[e-mail]>
Signed-off-by: David S. Miller <[e-mail]>

drivers/net/ethernet/mellanox/mlx5/core/en_rep.c

···
 #include <net/act_api.h>
 #include <net/netevent.h>
 #include <net/arp.h>
+#include <net/devlink.h>
 
 #include "eswitch.h"
 #include "en.h"
···
 	return ret;
 }
 
-static int mlx5e_rep_get_phys_port_name(struct net_device *dev,
-					char *buf, size_t len)
-{
-	struct mlx5e_priv *priv = netdev_priv(dev);
-	struct mlx5e_rep_priv *rpriv = priv->ppriv;
-	struct mlx5_eswitch_rep *rep = rpriv->rep;
-	unsigned int fn;
-	int ret;
-
-	fn = PCI_FUNC(priv->mdev->pdev->devfn);
-	if (fn >= MLX5_MAX_PORTS)
-		return -EOPNOTSUPP;
-
-	if (rep->vport == MLX5_VPORT_UPLINK)
-		ret = snprintf(buf, len, "p%d", fn);
-	else if (rep->vport == MLX5_VPORT_PF)
-		ret = snprintf(buf, len, "pf%d", fn);
-	else
-		ret = snprintf(buf, len, "pf%dvf%d", fn, rep->vport - 1);
-
-	if (ret >= len)
-		return -EOPNOTSUPP;
-
-	return 0;
-}
-
 static int
 mlx5e_rep_setup_tc_cls_flower(struct mlx5e_priv *priv,
 			      struct tc_cls_flower_offload *cls_flower, int flags)
···
 	return 0;
 }
 
+static struct devlink_port *mlx5e_get_devlink_port(struct net_device *dev)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+
+	return &rpriv->dl_port;
+}
+
 static const struct net_device_ops mlx5e_netdev_ops_rep = {
 	.ndo_open                = mlx5e_rep_open,
 	.ndo_stop                = mlx5e_rep_close,
 	.ndo_start_xmit          = mlx5e_xmit,
-	.ndo_get_phys_port_name  = mlx5e_rep_get_phys_port_name,
 	.ndo_setup_tc            = mlx5e_rep_setup_tc,
+	.ndo_get_devlink_port = mlx5e_get_devlink_port,
 	.ndo_get_stats64         = mlx5e_rep_get_stats,
 	.ndo_has_offload_stats	 = mlx5e_rep_has_offload_stats,
 	.ndo_get_offload_stats	 = mlx5e_rep_get_offload_stats,
 	.ndo_change_mtu          = mlx5e_rep_change_mtu,
-	.ndo_get_port_parent_id	 = mlx5e_rep_get_port_parent_id,
 };
 
 static const struct net_device_ops mlx5e_netdev_ops_uplink_rep = {
···
 	.ndo_stop                = mlx5e_close,
 	.ndo_start_xmit          = mlx5e_xmit,
 	.ndo_set_mac_address     = mlx5e_uplink_rep_set_mac,
-	.ndo_get_phys_port_name  = mlx5e_rep_get_phys_port_name,
 	.ndo_setup_tc            = mlx5e_rep_setup_tc,
+	.ndo_get_devlink_port = mlx5e_get_devlink_port,
 	.ndo_get_stats64         = mlx5e_get_stats,
 	.ndo_has_offload_stats	 = mlx5e_rep_has_offload_stats,
 	.ndo_get_offload_stats	 = mlx5e_rep_get_offload_stats,
···
 	.ndo_get_vf_config       = mlx5e_get_vf_config,
 	.ndo_get_vf_stats        = mlx5e_get_vf_stats,
 	.ndo_set_vf_vlan         = mlx5e_uplink_rep_set_vf_vlan,
-	.ndo_get_port_parent_id	 = mlx5e_rep_get_port_parent_id,
 	.ndo_set_features        = mlx5e_set_features,
 };
 
···
 	.max_tc			= MLX5E_MAX_NUM_TC,
 };
 
+static bool
+is_devlink_port_supported(const struct mlx5_core_dev *dev,
+			  const struct mlx5e_rep_priv *rpriv)
+{
+	return rpriv->rep->vport == MLX5_VPORT_UPLINK ||
+	       rpriv->rep->vport == MLX5_VPORT_PF ||
+	       mlx5_eswitch_is_vf_vport(dev->priv.eswitch, rpriv->rep->vport);
+}
+
+static int register_devlink_port(struct mlx5_core_dev *dev,
+				 struct mlx5e_rep_priv *rpriv)
+{
+	struct devlink *devlink = priv_to_devlink(dev);
+	struct mlx5_eswitch_rep *rep = rpriv->rep;
+	struct netdev_phys_item_id ppid = {};
+	int ret;
+
+	if (!is_devlink_port_supported(dev, rpriv))
+		return 0;
+
+	ret = mlx5e_rep_get_port_parent_id(rpriv->netdev, &ppid);
+	if (ret)
+		return ret;
+
+	if (rep->vport == MLX5_VPORT_UPLINK)
+		devlink_port_attrs_set(&rpriv->dl_port,
+				       DEVLINK_PORT_FLAVOUR_PHYSICAL,
+				       PCI_FUNC(dev->pdev->devfn), false, 0,
+				       &ppid.id[0], ppid.id_len);
+	else if (rep->vport == MLX5_VPORT_PF)
+		devlink_port_attrs_pci_pf_set(&rpriv->dl_port,
+					      &ppid.id[0], ppid.id_len,
+					      dev->pdev->devfn);
+	else if (mlx5_eswitch_is_vf_vport(dev->priv.eswitch, rpriv->rep->vport))
+		devlink_port_attrs_pci_vf_set(&rpriv->dl_port,
+					      &ppid.id[0], ppid.id_len,
+					      dev->pdev->devfn,
+					      rep->vport - 1);
+
+	return devlink_port_register(devlink, &rpriv->dl_port, rep->vport);
+}
+
+static void unregister_devlink_port(struct mlx5_core_dev *dev,
+				    struct mlx5e_rep_priv *rpriv)
+{
+	if (is_devlink_port_supported(dev, rpriv))
+		devlink_port_unregister(&rpriv->dl_port);
+}
+
 /* e-Switch vport representors */
 static int
 mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
···
 		goto err_detach_netdev;
 	}
 
+	err = register_devlink_port(dev, rpriv);
+	if (err) {
+		esw_warn(dev, "Failed to register devlink port %d\n",
+			 rep->vport);
+		goto err_neigh_cleanup;
+	}
+
 	err = register_netdev(netdev);
 	if (err) {
 		pr_warn("Failed to register representor netdev for vport %d\n",
 			rep->vport);
-		goto err_neigh_cleanup;
+		goto err_devlink_cleanup;
 	}
 
+	if (is_devlink_port_supported(dev, rpriv))
+		devlink_port_type_eth_set(&rpriv->dl_port, netdev);
 	return 0;
+
+err_devlink_cleanup:
+	unregister_devlink_port(dev, rpriv);
 
 err_neigh_cleanup:
 	mlx5e_rep_neigh_cleanup(rpriv);
···
 	struct mlx5e_rep_priv *rpriv = mlx5e_rep_to_rep_priv(rep);
 	struct net_device *netdev = rpriv->netdev;
 	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5_core_dev *dev = priv->mdev;
 	void *ppriv = priv->ppriv;
 
+	if (is_devlink_port_supported(dev, rpriv))
+		devlink_port_type_clear(&rpriv->dl_port);
 	unregister_netdev(netdev);
+	unregister_devlink_port(dev, rpriv);
 	mlx5e_rep_neigh_cleanup(rpriv);
 	mlx5e_detach_netdev(priv);
 	if (rep->vport == MLX5_VPORT_UPLINK)

drivers/net/ethernet/mellanox/mlx5/core/en_rep.h

···
 	struct mlx5_flow_handle *vport_rx_rule;
 	struct list_head       vport_sqs_list;
 	struct mlx5_rep_uplink_priv uplink_priv; /* valid for uplink rep */
+	struct devlink_port dl_port;
 };
 
 static inline

include/net/devlink.h

···
 	char priv[0] __aligned(NETDEV_ALIGN);
 };
 
+struct devlink_port_phys_attrs {
+	u32 port_number; /* Same value as "split group".
+			  * A physical port which is visible to the user
+			  * for a given port flavour.
+			  */
+	u32 split_subport_number;
+};
+
+struct devlink_port_pci_pf_attrs {
+	u16 pf;	/* Associated PCI PF for this port. */
+};
+
+struct devlink_port_pci_vf_attrs {
+	u16 pf;	/* Associated PCI PF for this port. */
+	u16 vf;	/* Associated PCI VF for of the PCI PF for this port. */
+};
+
 struct devlink_port_attrs {
 	u8 set:1,
 	   split:1,
 	   switch_port:1;
 	enum devlink_port_flavour flavour;
-	u32 port_number; /* same value as "split group" */
-	u32 split_subport_number;
 	struct netdev_phys_item_id switch_id;
+	union {
+		struct devlink_port_phys_attrs phys;
+		struct devlink_port_pci_pf_attrs pci_pf;
+		struct devlink_port_pci_vf_attrs pci_vf;
+	};
 };
 
 struct devlink_port {
···
 			    u32 split_subport_number,
 			    const unsigned char *switch_id,
 			    unsigned char switch_id_len);
+void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port,
+				   const unsigned char *switch_id,
+				   unsigned char switch_id_len, u16 pf);
+void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port,
+				   const unsigned char *switch_id,
+				   unsigned char switch_id_len,
+				   u16 pf, u16 vf);
 int devlink_sb_register(struct devlink *devlink, unsigned int sb_index,
 			u32 size, u16 ingress_pools_count,
 			u16 egress_pools_count, u16 ingress_tc_count,

include/uapi/linux/devlink.h

···
 	DEVLINK_PORT_FLAVOUR_DSA, /* Distributed switch architecture
 				   * interconnect port.
 				   */
+	DEVLINK_PORT_FLAVOUR_PCI_PF, /* Represents eswitch port for
+				      * the PCI PF. It is an internal
+				      * port that faces the PCI PF.
+				      */
+	DEVLINK_PORT_FLAVOUR_PCI_VF, /* Represents eswitch port
+				      * for the PCI VF. It is an internal
+				      * port that faces the PCI VF.
+				      */
 };
 
 enum devlink_param_cmode {
···
 	DEVLINK_ATTR_FLASH_UPDATE_STATUS_MSG,	/* string */
 	DEVLINK_ATTR_FLASH_UPDATE_STATUS_DONE,	/* u64 */
 	DEVLINK_ATTR_FLASH_UPDATE_STATUS_TOTAL,	/* u64 */
+
+	DEVLINK_ATTR_PORT_PCI_PF_NUMBER,	/* u16 */
+	DEVLINK_ATTR_PORT_PCI_VF_NUMBER,	/* u16 */
 
 	/* add new attributes above here, update the policy in devlink.c */
 

net/core/devlink.c

···
 		return 0;
 	if (nla_put_u16(msg, DEVLINK_ATTR_PORT_FLAVOUR, attrs->flavour))
 		return -EMSGSIZE;
-	if (nla_put_u32(msg, DEVLINK_ATTR_PORT_NUMBER, attrs->port_number))
+	if (devlink_port->attrs.flavour == DEVLINK_PORT_FLAVOUR_PCI_PF) {
+		if (nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER,
+				attrs->pci_pf.pf))
+			return -EMSGSIZE;
+	} else if (devlink_port->attrs.flavour == DEVLINK_PORT_FLAVOUR_PCI_VF) {
+		if (nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER,
+				attrs->pci_vf.pf) ||
+		    nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_VF_NUMBER,
+				attrs->pci_vf.vf))
+			return -EMSGSIZE;
+	}
+	if (devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PHYSICAL &&
+	    devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_CPU &&
+	    devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_DSA)
+		return 0;
+	if (nla_put_u32(msg, DEVLINK_ATTR_PORT_NUMBER,
+			attrs->phys.port_number))
 		return -EMSGSIZE;
 	if (!attrs->split)
 		return 0;
-	if (nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_GROUP, attrs->port_number))
+	if (nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_GROUP,
+			attrs->phys.port_number))
 		return -EMSGSIZE;
 	if (nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_SUBPORT_NUMBER,
-			attrs->split_subport_number))
+			attrs->phys.split_subport_number))
 		return -EMSGSIZE;
 	return 0;
 }
···
 }
 EXPORT_SYMBOL_GPL(devlink_port_type_clear);
 
+static int __devlink_port_attrs_set(struct devlink_port *devlink_port,
+				    enum devlink_port_flavour flavour,
+				    const unsigned char *switch_id,
+				    unsigned char switch_id_len)
+{
+	struct devlink_port_attrs *attrs = &devlink_port->attrs;
+
+	if (WARN_ON(devlink_port->registered))
+		return -EEXIST;
+	attrs->set = true;
+	attrs->flavour = flavour;
+	if (switch_id) {
+		attrs->switch_port = true;
+		if (WARN_ON(switch_id_len > MAX_PHYS_ITEM_ID_LEN))
+			switch_id_len = MAX_PHYS_ITEM_ID_LEN;
+		memcpy(attrs->switch_id.id, switch_id, switch_id_len);
+		attrs->switch_id.id_len = switch_id_len;
+	} else {
+		attrs->switch_port = false;
+	}
+	return 0;
+}
+
 /**
  *	devlink_port_attrs_set - Set port attributes
  *
···
 			    unsigned char switch_id_len)
 {
 	struct devlink_port_attrs *attrs = &devlink_port->attrs;
+	int ret;
 
-	if (WARN_ON(devlink_port->registered))
+	ret = __devlink_port_attrs_set(devlink_port, flavour,
+				       switch_id, switch_id_len);
+	if (ret)
 		return;
-	attrs->set = true;
-	attrs->flavour = flavour;
-	attrs->port_number = port_number;
 	attrs->split = split;
-	attrs->split_subport_number = split_subport_number;
-	if (switch_id) {
-		attrs->switch_port = true;
-		if (WARN_ON(switch_id_len > MAX_PHYS_ITEM_ID_LEN))
-			switch_id_len = MAX_PHYS_ITEM_ID_LEN;
-		memcpy(attrs->switch_id.id, switch_id, switch_id_len);
-		attrs->switch_id.id_len = switch_id_len;
-	} else {
-		attrs->switch_port = false;
-	}
+	attrs->phys.port_number = port_number;
+	attrs->phys.split_subport_number = split_subport_number;
 }
 EXPORT_SYMBOL_GPL(devlink_port_attrs_set);
+
+/**
+ *	devlink_port_attrs_pci_pf_set - Set PCI PF port attributes
+ *
+ *	@devlink_port: devlink port
+ *	@pf: associated PF for the devlink port instance
+ *	@switch_id: if the port is part of switch, this is buffer with ID,
+ *	            otherwise this is NULL
+ *	@switch_id_len: length of the switch_id buffer
+ */
+void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port,
+				   const unsigned char *switch_id,
+				   unsigned char switch_id_len, u16 pf)
+{
+	struct devlink_port_attrs *attrs = &devlink_port->attrs;
+	int ret;
+
+	ret = __devlink_port_attrs_set(devlink_port,
+				       DEVLINK_PORT_FLAVOUR_PCI_PF,
+				       switch_id, switch_id_len);
+	if (ret)
+		return;
+
+	attrs->pci_pf.pf = pf;
+}
+EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_pf_set);
+
+/**
+ *	devlink_port_attrs_pci_vf_set - Set PCI VF port attributes
+ *
+ *	@devlink_port: devlink port
+ *	@pf: associated PF for the devlink port instance
+ *	@vf: associated VF of a PF for the devlink port instance
+ *	@switch_id: if the port is part of switch, this is buffer with ID,
+ *	            otherwise this is NULL
+ *	@switch_id_len: length of the switch_id buffer
+ */
+void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port,
+				   const unsigned char *switch_id,
+				   unsigned char switch_id_len,
+				   u16 pf, u16 vf)
+{
+	struct devlink_port_attrs *attrs = &devlink_port->attrs;
+	int ret;
+
+	ret = __devlink_port_attrs_set(devlink_port,
+				       DEVLINK_PORT_FLAVOUR_PCI_VF,
+				       switch_id, switch_id_len);
+	if (ret)
+		return;
+	attrs->pci_vf.pf = pf;
+	attrs->pci_vf.vf = vf;
+}
+EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_vf_set);
 
 static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port,
 					     char *name, size_t len)
···
 	switch (attrs->flavour) {
 	case DEVLINK_PORT_FLAVOUR_PHYSICAL:
 		if (!attrs->split)
-			n = snprintf(name, len, "p%u", attrs->port_number);
+			n = snprintf(name, len, "p%u", attrs->phys.port_number);
 		else
-			n = snprintf(name, len, "p%us%u", attrs->port_number,
-				     attrs->split_subport_number);
+			n = snprintf(name, len, "p%us%u",
+				     attrs->phys.port_number,
+				     attrs->phys.split_subport_number);
 		break;
 	case DEVLINK_PORT_FLAVOUR_CPU:
 	case DEVLINK_PORT_FLAVOUR_DSA:
···
 		 */
 		WARN_ON(1);
 		return -EINVAL;
+	case DEVLINK_PORT_FLAVOUR_PCI_PF:
+		n = snprintf(name, len, "pf%u", attrs->pci_pf.pf);
+		break;
+	case DEVLINK_PORT_FLAVOUR_PCI_VF:
+		n = snprintf(name, len, "pf%uvf%u",
+			     attrs->pci_vf.pf, attrs->pci_vf.vf);
+		break;
 	}
 
 	if (n >= len)