From 1230d94820c9cf74776eaac4ee45081e33ea1a30 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Fri, 11 Dec 2020 22:12:12 -0800 Subject: devlink: Prepare code to fill multiple port function attributes Prepare code to fill zero or more port function optional attributes. Subsequent patch makes use of this to fill more port function attributes. Signed-off-by: Parav Pandit Reviewed-by: Jiri Pirko Reviewed-by: Vu Pham Signed-off-by: Saeed Mahameed --- net/core/devlink.c | 64 ++++++++++++++++++++++++++++-------------------------- 1 file changed, 33 insertions(+), 31 deletions(-) (limited to 'net/core/devlink.c') diff --git a/net/core/devlink.c b/net/core/devlink.c index ee828e4b1007..c39496311b71 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -712,6 +712,31 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg, return 0; } +static int +devlink_port_fn_hw_addr_fill(struct devlink *devlink, const struct devlink_ops *ops, + struct devlink_port *port, struct sk_buff *msg, + struct netlink_ext_ack *extack, bool *msg_updated) +{ + u8 hw_addr[MAX_ADDR_LEN]; + int hw_addr_len; + int err; + + if (!ops->port_function_hw_addr_get) + return 0; + + err = ops->port_function_hw_addr_get(devlink, port, hw_addr, &hw_addr_len, extack); + if (err) { + if (err == -EOPNOTSUPP) + return 0; + return err; + } + err = nla_put(msg, DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR, hw_addr_len, hw_addr); + if (err) + return err; + *msg_updated = true; + return 0; +} + static int devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *port, struct netlink_ext_ack *extack) @@ -719,36 +744,17 @@ devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *por struct devlink *devlink = port->devlink; const struct devlink_ops *ops; struct nlattr *function_attr; - bool empty_nest = true; - int err = 0; + bool msg_updated = false; + int err; function_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_PORT_FUNCTION); if (!function_attr) return -EMSGSIZE; ops = devlink->ops; - if (ops->port_function_hw_addr_get) { - int hw_addr_len; - u8 hw_addr[MAX_ADDR_LEN]; - - err = ops->port_function_hw_addr_get(devlink, port, hw_addr, &hw_addr_len, extack); - if (err == -EOPNOTSUPP) { - /* Port function attributes are optional for a port. If port doesn't - * support function attribute, returning -EOPNOTSUPP is not an error. - */ - err = 0; - goto out; - } else if (err) { - goto out; - } - err = nla_put(msg, DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR, hw_addr_len, hw_addr); - if (err) - goto out; - empty_nest = false; - } - -out: - if (err || empty_nest) + err = devlink_port_fn_hw_addr_fill(devlink, ops, port, msg, + extack, &msg_updated); + if (err || !msg_updated) nla_nest_cancel(msg, function_attr); else nla_nest_end(msg, function_attr); @@ -986,7 +992,6 @@ devlink_port_function_hw_addr_set(struct devlink *devlink, struct devlink_port * const struct devlink_ops *ops; const u8 *hw_addr; int hw_addr_len; - int err; hw_addr = nla_data(attr); hw_addr_len = nla_len(attr); @@ -1011,12 +1016,7 @@ devlink_port_function_hw_addr_set(struct devlink *devlink, struct devlink_port * return -EOPNOTSUPP; } - err = ops->port_function_hw_addr_set(devlink, port, hw_addr, hw_addr_len, extack); - if (err) - return err; - - devlink_port_notify(port, DEVLINK_CMD_PORT_NEW); - return 0; + return ops->port_function_hw_addr_set(devlink, port, hw_addr, hw_addr_len, extack); } static int @@ -1037,6 +1037,8 @@ devlink_port_function_set(struct devlink *devlink, struct devlink_port *port, if (attr) err = devlink_port_function_hw_addr_set(devlink, port, attr, extack); + if (!err) + devlink_port_notify(port, DEVLINK_CMD_PORT_NEW); return err; } -- cgit From b8288837ef6bdaac331752b401f5ca3b59b37430 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Fri, 11 Dec 2020 22:12:13 -0800 Subject: devlink: Introduce PCI SF port flavour and port attribute A PCI sub-function (SF) represents a portion of the device similar to PCI VF. In an eswitch, PCI SF may have port which is normally represented using a representor netdevice. To have better visibility of eswitch port, its association with SF, and its representor netdevice, introduce a PCI SF port flavour. When devlink port flavour is PCI SF, fill up PCI SF attributes of the port. Extend port name creation using PCI PF and SF number scheme on best effort basis, so that vendor drivers can skip defining their own scheme. This is done as cApfNSfM, where A, N and M are controller, PCI PF and PCI SF number respectively. This is similar to existing naming for PCI PF and PCI VF ports. An example view of a PCI SF port: $ devlink port show pci/0000:06:00.0/32768 pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false function: hw_addr 00:00:00:00:88:88 state active opstate attached $ devlink port show pci/0000:06:00.0/32768 -jp { "port": { "pci/0000:06:00.0/32768": { "type": "eth", "netdev": "ens2f0npf0sf88", "flavour": "pcisf", "controller": 0, "pfnum": 0, "sfnum": 88, "splittable": false, "function": { "hw_addr": "00:00:00:00:88:88", "state": "active", "opstate": "attached" } } } } Signed-off-by: Parav Pandit Reviewed-by: Jiri Pirko Reviewed-by: Vu Pham Signed-off-by: Saeed Mahameed --- net/core/devlink.c | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) (limited to 'net/core/devlink.c') diff --git a/net/core/devlink.c b/net/core/devlink.c index c39496311b71..4cbc02fb602d 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -690,6 +690,15 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg, if (nla_put_u8(msg, DEVLINK_ATTR_PORT_EXTERNAL, attrs->pci_vf.external)) return -EMSGSIZE; break; + case DEVLINK_PORT_FLAVOUR_PCI_SF: + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER, + attrs->pci_sf.controller) || + nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, + attrs->pci_sf.pf) || + nla_put_u32(msg, DEVLINK_ATTR_PORT_PCI_SF_NUMBER, + attrs->pci_sf.sf)) + return -EMSGSIZE; + break; case DEVLINK_PORT_FLAVOUR_PHYSICAL: case DEVLINK_PORT_FLAVOUR_CPU: case DEVLINK_PORT_FLAVOUR_DSA: @@ -8374,6 +8383,32 @@ void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 contro } EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_vf_set); +/** + * devlink_port_attrs_pci_sf_set - Set PCI SF port attributes + * + * @devlink_port: devlink port + * @controller: associated controller number for the devlink port instance + * @pf: associated PF for the devlink port instance + * @sf: associated SF of a PF for the devlink port instance + */ +void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, u32 controller, + u16 pf, u32 sf) +{ + struct devlink_port_attrs *attrs = &devlink_port->attrs; + int ret; + + if (WARN_ON(devlink_port->registered)) + return; + ret = __devlink_port_attrs_set(devlink_port, + DEVLINK_PORT_FLAVOUR_PCI_SF); + if (ret) + return; + attrs->pci_sf.controller = controller; + attrs->pci_sf.pf = pf; + attrs->pci_sf.sf = sf; +} +EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_sf_set); + static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, char *name, size_t len) { @@ -8422,6 +8457,10 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, n = snprintf(name, len, "pf%uvf%u", attrs->pci_vf.pf, attrs->pci_vf.vf); break; + case DEVLINK_PORT_FLAVOUR_PCI_SF: + n = snprintf(name, len, "pf%usf%u", attrs->pci_sf.pf, + attrs->pci_sf.sf); + break; } if (n >= len) -- cgit From cd76dcd68d96aa5bbc63b7ef25a87a1dbea3d73c Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Fri, 11 Dec 2020 22:12:14 -0800 Subject: devlink: Support add and delete devlink port Extended devlink interface for the user to add and delete a port. Extend devlink to connect user requests to driver to add/delete a port in the device. Driver routines are invoked without holding devlink instance lock. This enables driver to perform several devlink objects registration, unregistration such as (port, health reporter, resource etc) by using existing devlink APIs. This also helps to uniformly use the code for port unregistration during driver unload and during port deletion initiated by user. Examples of add, show and delete commands: $ devlink dev eswitch set pci/0000:06:00.0 mode switchdev $ devlink port show pci/0000:06:00.0/65535: type eth netdev ens2f0np0 flavour physical port 0 splittable false $ devlink port add pci/0000:06:00.0 flavour pcisf pfnum 0 sfnum 88 pci/0000:06:00.0/32768: type eth netdev eth6 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false function: hw_addr 00:00:00:00:00:00 state inactive opstate detached $ devlink port show pci/0000:06:00.0/32768 pci/0000:06:00.0/32768: type eth netdev eth6 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false function: hw_addr 00:00:00:00:00:00 state inactive opstate detached $ udevadm test-builtin net_id /sys/class/net/eth6 Load module index Parsed configuration file /usr/lib/systemd/network/99-default.link Created link configuration context. Using default interface naming scheme 'v245'. ID_NET_NAMING_SCHEME=v245 ID_NET_NAME_PATH=enp6s0f0npf0sf88 ID_NET_NAME_SLOT=ens2f0npf0sf88 Unload module index Unloaded link configuration context. Signed-off-by: Parav Pandit Reviewed-by: Vu Pham Signed-off-by: Saeed Mahameed --- net/core/devlink.c | 121 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 121 insertions(+) (limited to 'net/core/devlink.c') diff --git a/net/core/devlink.c b/net/core/devlink.c index 4cbc02fb602d..541b5f549274 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -1147,6 +1147,111 @@ static int devlink_nl_cmd_port_unsplit_doit(struct sk_buff *skb, return devlink_port_unsplit(devlink, port_index, info->extack); } +static int devlink_port_new_notifiy(struct devlink *devlink, + unsigned int port_index, + struct genl_info *info) +{ + struct devlink_port *devlink_port; + struct sk_buff *msg; + int err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + mutex_lock(&devlink->lock); + devlink_port = devlink_port_get_by_index(devlink, port_index); + if (!devlink_port) { + err = -ENODEV; + goto out; + } + + err = devlink_nl_port_fill(msg, devlink, devlink_port, + DEVLINK_CMD_NEW, info->snd_portid, + info->snd_seq, 0, NULL); + if (err) + goto out; + + err = genlmsg_reply(msg, info); + mutex_unlock(&devlink->lock); + return err; + +out: + mutex_unlock(&devlink->lock); + nlmsg_free(msg); + return err; +} + +static int devlink_nl_cmd_port_new_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct netlink_ext_ack *extack = info->extack; + struct devlink_port_new_attrs new_attrs = {}; + struct devlink *devlink = info->user_ptr[0]; + unsigned int new_port_index; + int err; + + if (!devlink->ops->port_new || !devlink->ops->port_del) + return -EOPNOTSUPP; + + if (!info->attrs[DEVLINK_ATTR_PORT_FLAVOUR] || + !info->attrs[DEVLINK_ATTR_PORT_PCI_PF_NUMBER]) { + NL_SET_ERR_MSG_MOD(extack, "Port flavour or PCI PF are not specified"); + return -EINVAL; + } + new_attrs.flavour = nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_FLAVOUR]); + new_attrs.pfnum = + nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_PCI_PF_NUMBER]); + + if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { + /* Port index of the new port being created by driver. */ + new_attrs.port_index = + nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); + new_attrs.port_index_valid = true; + } + if (info->attrs[DEVLINK_ATTR_PORT_CONTROLLER_NUMBER]) { + new_attrs.controller = + nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_CONTROLLER_NUMBER]); + new_attrs.controller_valid = true; + } + if (new_attrs.flavour == DEVLINK_PORT_FLAVOUR_PCI_SF && + info->attrs[DEVLINK_ATTR_PORT_PCI_SF_NUMBER]) { + new_attrs.sfnum = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_PCI_SF_NUMBER]); + new_attrs.sfnum_valid = true; + } + + err = devlink->ops->port_new(devlink, &new_attrs, extack, + &new_port_index); + if (err) + return err; + + err = devlink_port_new_notifiy(devlink, new_port_index, info); + if (err && err != -ENODEV) { + /* Fail to send the response; destroy newly created port. */ + devlink->ops->port_del(devlink, new_port_index, extack); + } + return err; +} + +static int devlink_nl_cmd_port_del_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct netlink_ext_ack *extack = info->extack; + struct devlink *devlink = info->user_ptr[0]; + unsigned int port_index; + + if (!devlink->ops->port_del) + return -EOPNOTSUPP; + + if (!info->attrs[DEVLINK_ATTR_PORT_INDEX]) { + NL_SET_ERR_MSG_MOD(extack, "Port index is not specified"); + return -EINVAL; + } + port_index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); + + return devlink->ops->port_del(devlink, port_index, extack); +} + static int devlink_nl_sb_fill(struct sk_buff *msg, struct devlink *devlink, struct devlink_sb *devlink_sb, enum devlink_command cmd, u32 portid, @@ -7605,6 +7710,10 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_RELOAD_ACTION] = NLA_POLICY_RANGE(NLA_U8, DEVLINK_RELOAD_ACTION_DRIVER_REINIT, DEVLINK_RELOAD_ACTION_MAX), [DEVLINK_ATTR_RELOAD_LIMITS] = NLA_POLICY_BITFIELD32(DEVLINK_RELOAD_LIMITS_VALID_MASK), + [DEVLINK_ATTR_PORT_FLAVOUR] = { .type = NLA_U16 }, + [DEVLINK_ATTR_PORT_PCI_PF_NUMBER] = { .type = NLA_U16 }, + [DEVLINK_ATTR_PORT_PCI_SF_NUMBER] = { .type = NLA_U32 }, + [DEVLINK_ATTR_PORT_CONTROLLER_NUMBER] = { .type = NLA_U32 }, }; static const struct genl_small_ops devlink_nl_ops[] = { @@ -7644,6 +7753,18 @@ static const struct genl_small_ops devlink_nl_ops[] = { .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NO_LOCK, }, + { + .cmd = DEVLINK_CMD_PORT_NEW, + .doit = devlink_nl_cmd_port_new_doit, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NO_LOCK, + }, + { + .cmd = DEVLINK_CMD_PORT_DEL, + .doit = devlink_nl_cmd_port_del_doit, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NO_LOCK, + }, { .cmd = DEVLINK_CMD_SB_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, -- cgit From a556dded9c23c51c82654f1ebe389cbc0bc22057 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Fri, 11 Dec 2020 22:12:15 -0800 Subject: devlink: Support get and set state of port function devlink port function can be in active or inactive state. Allow users to get and set port function's state. When the port function it activated, its operational state may change after a while when the device is created and driver binds to it. Similarly on deactivation flow. To clearly describe the state of the port function and its device's operational state in the host system, define state and opstate attributes. Example of a PCI SF port which supports a port function: $ devlink dev eswitch set pci/0000:06:00.0 mode switchdev $ devlink port show pci/0000:06:00.0/65535: type eth netdev ens2f0np0 flavour physical port 0 splittable false $ devlink port add pci/0000:06:00.0 flavour pcisf pfnum 0 sfnum 88 pci/0000:08:00.0/32768: type eth netdev eth6 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false function: hw_addr 00:00:00:00:00:00 state inactive opstate detached $ devlink port show pci/0000:06:00.0/32768 pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false function: hw_addr 00:00:00:00:88:88 state inactive opstate detached $ devlink port function set pci/0000:06:00.0/32768 hw_addr 00:00:00:00:88:88 state active $ devlink port show pci/0000:06:00.0/32768 -jp { "port": { "pci/0000:06:00.0/32768": { "type": "eth", "netdev": "ens2f0npf0sf88", "flavour": "pcisf", "controller": 0, "pfnum": 0, "sfnum": 88, "external": false, "splittable": false, "function": { "hw_addr": "00:00:00:00:88:88", "state": "active", "opstate": "attached" } } } } Signed-off-by: Parav Pandit Reviewed-by: Jiri Pirko Reviewed-by: Vu Pham Signed-off-by: Saeed Mahameed --- net/core/devlink.c | 90 +++++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 89 insertions(+), 1 deletion(-) (limited to 'net/core/devlink.c') diff --git a/net/core/devlink.c b/net/core/devlink.c index 541b5f549274..9f1be69bd5f8 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -87,6 +87,9 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_trap_report); static const struct nla_policy devlink_function_nl_policy[DEVLINK_PORT_FUNCTION_ATTR_MAX + 1] = { [DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] = { .type = NLA_BINARY }, + [DEVLINK_PORT_FN_ATTR_STATE] = + NLA_POLICY_RANGE(NLA_U8, DEVLINK_PORT_FN_STATE_INACTIVE, + DEVLINK_PORT_FN_STATE_ACTIVE), }; static LIST_HEAD(devlink_list); @@ -746,6 +749,58 @@ devlink_port_fn_hw_addr_fill(struct devlink *devlink, const struct devlink_ops * return 0; } +static bool +devlink_port_fn_state_valid(enum devlink_port_fn_state state) +{ + return state == DEVLINK_PORT_FN_STATE_INACTIVE || + state == DEVLINK_PORT_FN_STATE_ACTIVE; +} + +static bool +devlink_port_fn_opstate_valid(enum devlink_port_fn_opstate opstate) +{ + return opstate == DEVLINK_PORT_FN_OPSTATE_DETACHED || + opstate == DEVLINK_PORT_FN_OPSTATE_ATTACHED; +} + +static int +devlink_port_fn_state_fill(struct devlink *devlink, + const struct devlink_ops *ops, + struct devlink_port *port, struct sk_buff *msg, + struct netlink_ext_ack *extack, + bool *msg_updated) +{ + enum devlink_port_fn_opstate opstate; + enum devlink_port_fn_state state; + int err; + + if (!ops->port_fn_state_get) + return 0; + + err = ops->port_fn_state_get(devlink, port, &state, &opstate, extack); + if (err) { + if (err == -EOPNOTSUPP) + return 0; + return err; + } + if (!devlink_port_fn_state_valid(state)) { + WARN_ON_ONCE(1); + NL_SET_ERR_MSG_MOD(extack, "Invalid state read from driver"); + return -EINVAL; + } + if (!devlink_port_fn_opstate_valid(opstate)) { + WARN_ON_ONCE(1); + NL_SET_ERR_MSG_MOD(extack, + "Invalid operational state read from driver"); + return -EINVAL; + } + if (nla_put_u8(msg, DEVLINK_PORT_FN_ATTR_STATE, state) || + nla_put_u8(msg, DEVLINK_PORT_FN_ATTR_OPSTATE, opstate)) + return -EMSGSIZE; + *msg_updated = true; + return 0; +} + static int devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *port, struct netlink_ext_ack *extack) @@ -763,6 +818,11 @@ devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *por ops = devlink->ops; err = devlink_port_fn_hw_addr_fill(devlink, ops, port, msg, extack, &msg_updated); + if (err) + goto out; + err = devlink_port_fn_state_fill(devlink, ops, port, msg, extack, + &msg_updated); +out: if (err || !msg_updated) nla_nest_cancel(msg, function_attr); else @@ -1028,6 +1088,24 @@ devlink_port_function_hw_addr_set(struct devlink *devlink, struct devlink_port * return ops->port_function_hw_addr_set(devlink, port, hw_addr, hw_addr_len, extack); } +static int devlink_port_fn_state_set(struct devlink *devlink, + struct devlink_port *port, + const struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + enum devlink_port_fn_state state; + const struct devlink_ops *ops; + + state = nla_get_u8(attr); + ops = devlink->ops; + if (!ops->port_fn_state_set) { + NL_SET_ERR_MSG_MOD(extack, + "Function does not support state setting"); + return -EOPNOTSUPP; + } + return ops->port_fn_state_set(devlink, port, state, extack); +} + static int devlink_port_function_set(struct devlink *devlink, struct devlink_port *port, const struct nlattr *attr, struct netlink_ext_ack *extack) @@ -1043,8 +1121,18 @@ devlink_port_function_set(struct devlink *devlink, struct devlink_port *port, } attr = tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR]; - if (attr) + if (attr) { err = devlink_port_function_hw_addr_set(devlink, port, attr, extack); + if (err) + return err; + } + /* Keep this as the last function attribute set, so that when + * multiple port function attributes are set along with state, + * Those can be applied first before activating the state. + */ + attr = tb[DEVLINK_PORT_FN_ATTR_STATE]; + if (attr) + err = devlink_port_fn_state_set(devlink, port, attr, extack); if (!err) devlink_port_notify(port, DEVLINK_CMD_PORT_NEW); -- cgit