@@ -68,6 +68,7 @@ struct devlink_port {
enum devlink_port_type type;
enum devlink_port_type desired_type;
void *type_dev;
+ void *type_peer;
struct devlink_port_attrs attrs;
};
@@ -573,6 +574,9 @@ int devlink_port_register(struct devlink *devlink,
void devlink_port_unregister(struct devlink_port *devlink_port);
void devlink_port_type_eth_set(struct devlink_port *devlink_port,
struct net_device *netdev);
+void devlink_port_type_eth_set_peer(struct devlink_port *devlink_port,
+ struct net_device *netdev,
+ struct net_device *peer);
void devlink_port_type_ib_set(struct devlink_port *devlink_port,
struct ib_device *ibdev);
void devlink_port_type_clear(struct devlink_port *devlink_port);
@@ -784,6 +788,13 @@ static inline void devlink_port_type_eth_set(struct devlink_port *devlink_port,
{
}
+static inline void
+devlink_port_type_eth_set_peer(struct devlink_port *devlink_port,
+ struct net_device *netdev,
+ struct net_device *peer)
+{
+}
+
static inline void devlink_port_type_ib_set(struct devlink_port *devlink_port,
struct ib_device *ibdev)
{
@@ -338,6 +338,12 @@ enum devlink_attr {
DEVLINK_ATTR_PORT_PCI_VF_NUMBER, /* u32 */
DEVLINK_ATTR_PORT_PCI_SUBPORT, /* u32 */
+ DEVLINK_ATTR_PORT_PEER, /* nested */
+ DEVLINK_ATTR_PORT_PEER_TYPE, /* u16 */
+ DEVLINK_ATTR_PORT_PEER_NETDEV_IFINDEX, /* u32 */
+ DEVLINK_ATTR_PORT_PEER_NETDEV_NAME, /* string */
+ DEVLINK_ATTR_PORT_PEER_IBDEV_NAME, /* string */
+
/* add new attributes above here, update the policy in devlink.c */
__DEVLINK_ATTR_MAX,
@@ -552,6 +552,47 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg,
}
}
+static int devlink_nl_port_peer_put(struct sk_buff *msg,
+ struct devlink_port *devlink_port)
+{
+ struct nlattr *peer_attr;
+
+ if (!devlink_port->type_peer)
+ return 0;
+
+ peer_attr = nla_nest_start(msg, DEVLINK_ATTR_PORT_PEER);
+ if (!peer_attr)
+ return -EMSGSIZE;
+
+ /* Peer's type is got to be the same as the port's type */
+ if (nla_put_u16(msg, DEVLINK_ATTR_PORT_PEER_TYPE, devlink_port->type))
+ goto cancel_peer_attr;
+
+ if (devlink_port->type == DEVLINK_PORT_TYPE_ETH) {
+ struct net_device *netdev = devlink_port->type_peer;
+
+ if (nla_put_u32(msg, DEVLINK_ATTR_PORT_PEER_NETDEV_IFINDEX,
+ netdev->ifindex) ||
+ nla_put_string(msg, DEVLINK_ATTR_PORT_PEER_NETDEV_NAME,
+ netdev->name))
+ goto cancel_peer_attr;
+ }
+ if (devlink_port->type == DEVLINK_PORT_TYPE_IB) {
+ struct ib_device *ibdev = devlink_port->type_peer;
+
+ if (ibdev &&
+ nla_put_string(msg, DEVLINK_ATTR_PORT_PEER_IBDEV_NAME,
+ ibdev->name))
+ goto cancel_peer_attr;
+ }
+ nla_nest_end(msg, peer_attr);
+ return 0;
+
+cancel_peer_attr:
+ nla_nest_cancel(msg, peer_attr);
+ return -EMSGSIZE;
+}
+
static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink,
struct devlink_port *devlink_port,
enum devlink_command cmd, u32 portid,
@@ -593,6 +634,8 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink,
}
if (devlink_nl_port_attrs_put(msg, devlink_port))
goto nla_put_failure;
+ if (devlink_nl_port_peer_put(msg, devlink_port))
+ goto nla_put_failure;
genlmsg_end(msg, hdr);
return 0;
@@ -5370,10 +5413,11 @@ EXPORT_SYMBOL_GPL(devlink_port_unregister);
static void __devlink_port_type_set(struct devlink_port *devlink_port,
enum devlink_port_type type,
- void *type_dev)
+ void *type_dev, void *type_peer)
{
devlink_port->type = type;
devlink_port->type_dev = type_dev;
+ devlink_port->type_peer = type_peer;
devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW);
}
@@ -5387,10 +5431,26 @@ void devlink_port_type_eth_set(struct devlink_port *devlink_port,
struct net_device *netdev)
{
return __devlink_port_type_set(devlink_port,
- DEVLINK_PORT_TYPE_ETH, netdev);
+ DEVLINK_PORT_TYPE_ETH, netdev, NULL);
}
EXPORT_SYMBOL_GPL(devlink_port_type_eth_set);
+/**
+ * devlink_port_type_eth_set_peer - Set port type to Ethernet with peer
+ *
+ * @devlink_port: devlink port
+ * @netdev: related netdevice
+ * @peer: for PCIe ports the non-port netdev (actual VF or PF)
+ */
+void devlink_port_type_eth_set_peer(struct devlink_port *devlink_port,
+ struct net_device *netdev,
+ struct net_device *peer)
+{
+ return __devlink_port_type_set(devlink_port,
+ DEVLINK_PORT_TYPE_ETH, netdev, peer);
+}
+EXPORT_SYMBOL_GPL(devlink_port_type_eth_set_peer);
+
/**
* devlink_port_type_ib_set - Set port type to InfiniBand
*
@@ -5401,7 +5461,7 @@ void devlink_port_type_ib_set(struct devlink_port *devlink_port,
struct ib_device *ibdev)
{
return __devlink_port_type_set(devlink_port,
- DEVLINK_PORT_TYPE_IB, ibdev);
+ DEVLINK_PORT_TYPE_IB, ibdev, NULL);
}
EXPORT_SYMBOL_GPL(devlink_port_type_ib_set);
@@ -5413,7 +5473,7 @@ EXPORT_SYMBOL_GPL(devlink_port_type_ib_set);
void devlink_port_type_clear(struct devlink_port *devlink_port)
{
return __devlink_port_type_set(devlink_port,
- DEVLINK_PORT_TYPE_NOTSET, NULL);
+ DEVLINK_PORT_TYPE_NOTSET, NULL, NULL);
}
EXPORT_SYMBOL_GPL(devlink_port_type_clear);
Devlink ports represent ports of a switch device (or SR-IOV NIC which has an embedded switch). In case of SR-IOV when PCIe PFs are exposed the PFs which are directly connected to the local machine may also spawn PF netdev (much like VFs have a port/"repr" and an actual VF netdev). Allow devlink to expose such linking. There is currently no way to find out which netdev corresponds to which PF. Example: $ devlink port pci/0000:82:00.0/0: type eth netdev p4p1 flavour physical pci/0000:82:00.0/10000: type eth netdev eth1 flavour pci_pf pf 0 peer_netdev enp130s0 pci/0000:82:00.0/10001: type eth netdev eth0 flavour pci_vf pf 0 vf 0 pci/0000:82:00.0/10002: type eth netdev eth2 flavour pci_vf pf 0 vf 1 v2: - move the peer info into a nested attr. Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> --- include/net/devlink.h | 11 ++++++ include/uapi/linux/devlink.h | 6 ++++ net/core/devlink.c | 68 +++++++++++++++++++++++++++++++++--- 3 files changed, 81 insertions(+), 4 deletions(-)