diff --git a/Documentation/networking/devlink/devlink-port.rst b/Documentation/networking/devlink/devlink-port.rst index c3302d23e480..3da590953ce8 100644 --- a/Documentation/networking/devlink/devlink-port.rst +++ b/Documentation/networking/devlink/devlink-port.rst @@ -125,6 +125,9 @@ this means a MAC address. Users may also set the RoCE capability of the function using `devlink port function set roce` command. +Users may also set the function as migratable using +'devlink port function set migratable' command. + Function attributes =================== @@ -194,6 +197,49 @@ VF/SF driver cannot override it. function: hw_addr 00:00:00:00:00:00 roce disable +migratable capability setup +--------------------------- +Live migration is the process of transferring a live virtual machine +from one physical host to another without disrupting its normal +operation. + +User who want PCI VFs to be able to perform live migration need to +explicitly enable the VF migratable capability. + +When user enables migratable capability for a VF, and the HV binds the VF to VFIO driver +with migration support, the user can migrate the VM with this VF from one HV to a +different one. + +However, when migratable capability is enable, device will disable features which cannot +be migrated. Thus migratable cap can impose limitations on a VF so let the user decide. + +Example of LM with migratable function configuration: +- Get migratable capability of the VF device:: + + $ devlink port show pci/0000:06:00.0/2 + pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1 + function: + hw_addr 00:00:00:00:00:00 migratable disable + +- Set migratable capability of the VF device:: + + $ devlink port function set pci/0000:06:00.0/2 migratable enable + + $ devlink port show pci/0000:06:00.0/2 + pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1 + function: + hw_addr 00:00:00:00:00:00 migratable enable + +- Bind VF to VFIO driver with migration support:: + + $ echo > /sys/bus/pci/devices/0000:08:00.0/driver/unbind + $ echo mlx5_vfio_pci > /sys/bus/pci/devices/0000:08:00.0/driver_override + $ echo > /sys/bus/pci/devices/0000:08:00.0/driver/bind + +Attach VF to the VM. +Start the VM. +Perform live migration. + Subfunction ============ diff --git a/include/net/devlink.h b/include/net/devlink.h index ce4c65d2f2e7..0f376a28b9c4 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1469,6 +1469,27 @@ struct devlink_ops { */ int (*port_fn_roce_set)(struct devlink_port *devlink_port, bool enable, struct netlink_ext_ack *extack); + /** + * @port_fn_migratable_get: Port function's migratable get function. + * + * Query migratable state of a function managed by the devlink port. + * Return -EOPNOTSUPP if port function migratable handling is not + * supported. + */ + int (*port_fn_migratable_get)(struct devlink_port *devlink_port, + bool *is_enable, + struct netlink_ext_ack *extack); + /** + * @port_fn_migratable_set: Port function's migratable set function. + * + * Enable/Disable migratable state of a function managed by the devlink + * port. + * Return -EOPNOTSUPP if port function migratable handling is not + * supported. + */ + int (*port_fn_migratable_set)(struct devlink_port *devlink_port, + bool enable, + struct netlink_ext_ack *extack); /** * port_new() - Add a new port function of a specified flavor * @devlink: Devlink instance diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 6cc2925bd478..3782d4219ac9 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -660,12 +660,15 @@ enum devlink_resource_unit { enum devlink_port_fn_attr_cap { DEVLINK_PORT_FN_ATTR_CAP_ROCE_BIT, + DEVLINK_PORT_FN_ATTR_CAP_MIGRATABLE_BIT, /* Add new caps above */ __DEVLINK_PORT_FN_ATTR_CAPS_MAX, }; #define DEVLINK_PORT_FN_CAP_ROCE _BITUL(DEVLINK_PORT_FN_ATTR_CAP_ROCE_BIT) +#define DEVLINK_PORT_FN_CAP_MIGRATABLE \ + _BITUL(DEVLINK_PORT_FN_ATTR_CAP_MIGRATABLE_BIT) enum devlink_port_function_attr { DEVLINK_PORT_FUNCTION_ATTR_UNSPEC, diff --git a/net/core/devlink.c b/net/core/devlink.c index 8c0ad52431c5..ab40ebcb4aea 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -715,6 +715,29 @@ static int devlink_port_fn_roce_fill(const struct devlink_ops *ops, return 0; } +static int devlink_port_fn_migratable_fill(const struct devlink_ops *ops, + struct devlink_port *devlink_port, + struct nla_bitfield32 *caps, + struct netlink_ext_ack *extack) +{ + bool is_enable; + int err; + + if (!ops->port_fn_migratable_get || + devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) + return 0; + + err = ops->port_fn_migratable_get(devlink_port, &is_enable, extack); + if (err) { + if (err == -EOPNOTSUPP) + return 0; + return err; + } + + devlink_port_fn_cap_fill(caps, DEVLINK_PORT_FN_CAP_MIGRATABLE, is_enable); + return 0; +} + static int devlink_port_fn_caps_fill(const struct devlink_ops *ops, struct devlink_port *devlink_port, struct sk_buff *msg, @@ -728,6 +751,10 @@ static int devlink_port_fn_caps_fill(const struct devlink_ops *ops, if (err) return err; + err = devlink_port_fn_migratable_fill(ops, devlink_port, &caps, extack); + if (err) + return err; + if (!caps.selector) return 0; err = nla_put_bitfield32(msg, DEVLINK_PORT_FN_ATTR_CAPS, caps.value, @@ -1322,6 +1349,15 @@ static int devlink_port_fn_state_fill(const struct devlink_ops *ops, return 0; } +static int +devlink_port_fn_mig_set(struct devlink_port *devlink_port, bool enable, + struct netlink_ext_ack *extack) +{ + const struct devlink_ops *ops = devlink_port->devlink->ops; + + return ops->port_fn_migratable_set(devlink_port, enable, extack); +} + static int devlink_port_fn_roce_set(struct devlink_port *devlink_port, bool enable, struct netlink_ext_ack *extack) @@ -1348,6 +1384,13 @@ static int devlink_port_fn_caps_set(struct devlink_port *devlink_port, if (err) return err; } + if (caps.selector & DEVLINK_PORT_FN_CAP_MIGRATABLE) { + err = devlink_port_fn_mig_set(devlink_port, caps_value & + DEVLINK_PORT_FN_CAP_MIGRATABLE, + extack); + if (err) + return err; + } return 0; } @@ -1769,6 +1812,18 @@ static int devlink_port_function_validate(struct devlink_port *devlink_port, "Port doesn't support RoCE function attribute"); return -EOPNOTSUPP; } + if (caps.selector & DEVLINK_PORT_FN_CAP_MIGRATABLE) { + if (!ops->port_fn_migratable_set) { + NL_SET_ERR_MSG_ATTR(extack, attr, + "Port doesn't support migratable function attribute"); + return -EOPNOTSUPP; + } + if (devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) { + NL_SET_ERR_MSG_ATTR(extack, attr, + "migratable function attribute supported for VFs only"); + return -EOPNOTSUPP; + } + } } return 0; }