From f8ff182c716c6f11ca3061961f5722f26a14e101 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 16 Nov 2010 04:30:14 +0000 Subject: rtnetlink: Link address family API Each net_device contains address family specific data such as per device settings and statistics. We already expose this data via procfs/sysfs and partially netlink. The netlink method requires the requester to send one RTM_GETLINK request for each address family it wishes to receive data of and then merge this data itself. This patch implements a new API which combines all address family specific link data in a new netlink attribute IFLA_AF_SPEC. IFLA_AF_SPEC contains a sequence of nested attributes, one for each address family which in turn defines the structure of its own attribute. Example: [IFLA_AF_SPEC] = { [AF_INET] = { [IFLA_INET_CONF] = ..., }, [AF_INET6] = { [IFLA_INET6_FLAGS] = ..., [IFLA_INET6_CONF] = ..., } } The API also allows for address families to implement a function which parses the IFLA_AF_SPEC attribute sent by userspace to implement address family specific link options. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/if_link.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux/if_link.h') diff --git a/include/linux/if_link.h b/include/linux/if_link.h index 2fc66dd783ee..443d04a66a79 100644 --- a/include/linux/if_link.h +++ b/include/linux/if_link.h @@ -80,6 +80,24 @@ struct rtnl_link_ifmap { __u8 port; }; +/* + * IFLA_AF_SPEC + * Contains nested attributes for address family specific attributes. + * Each address family may create a attribute with the address family + * number as type and create its own attribute structure in it. + * + * Example: + * [IFLA_AF_SPEC] = { + * [AF_INET] = { + * [IFLA_INET_CONF] = ..., + * }, + * [AF_INET6] = { + * [IFLA_INET6_FLAGS] = ..., + * [IFLA_INET6_CONF] = ..., + * } + * } + */ + enum { IFLA_UNSPEC, IFLA_ADDRESS, @@ -116,6 +134,7 @@ enum { IFLA_STATS64, IFLA_VF_PORTS, IFLA_PORT_SELF, + IFLA_AF_SPEC, __IFLA_MAX }; -- cgit v1.2.3 From 9f0f7272ac9506f4c8c05cc597b7e376b0b9f3e4 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 16 Nov 2010 04:32:48 +0000 Subject: ipv4: AF_INET link address family Implements the AF_INET link address family exposing the per device configuration settings via netlink using the attribute IFLA_INET_CONF. The format of IFLA_INET_CONF differs depending on the direction the attribute is sent. The attribute sent by the kernel consists of a u32 array, basically a 1:1 copy of in_device->cnf.data[]. The attribute expected by the kernel must consist of a sequence of nested u32 attributes, each representing a change request, e.g. [IFLA_INET_CONF] = { [IPV4_DEVCONF_FORWARDING] = 1, [IPV4_DEVCONF_NOXFRM] = 0, } libnl userspace API documentation and example available from: http://www.infradead.org/~tgr/libnl/doc-git/group__link__inet.html Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/if_link.h | 8 ++++++ net/ipv4/devinet.c | 75 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 83 insertions(+) (limited to 'include/linux/if_link.h') diff --git a/include/linux/if_link.h b/include/linux/if_link.h index 443d04a66a79..2e02e4d7b11e 100644 --- a/include/linux/if_link.h +++ b/include/linux/if_link.h @@ -147,6 +147,14 @@ enum { #define IFLA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ifinfomsg)) #endif +enum { + IFLA_INET_UNSPEC, + IFLA_INET_CONF, + __IFLA_INET_MAX, +}; + +#define IFLA_INET_MAX (__IFLA_INET_MAX - 1) + /* ifi_flags. IFF_* flags. diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index dc94b0316b78..71afc26c2df8 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1256,6 +1256,72 @@ errout: rtnl_set_sk_err(net, RTNLGRP_IPV4_IFADDR, err); } +static size_t inet_get_link_af_size(const struct net_device *dev) +{ + struct in_device *in_dev = __in_dev_get_rcu(dev); + + if (!in_dev) + return 0; + + return nla_total_size(IPV4_DEVCONF_MAX * 4); /* IFLA_INET_CONF */ +} + +static int inet_fill_link_af(struct sk_buff *skb, const struct net_device *dev) +{ + struct in_device *in_dev = __in_dev_get_rcu(dev); + struct nlattr *nla; + int i; + + if (!in_dev) + return -ENODATA; + + nla = nla_reserve(skb, IFLA_INET_CONF, IPV4_DEVCONF_MAX * 4); + if (nla == NULL) + return -EMSGSIZE; + + for (i = 0; i < IPV4_DEVCONF_MAX; i++) + ((u32 *) nla_data(nla))[i] = in_dev->cnf.data[i]; + + return 0; +} + +static const struct nla_policy inet_af_policy[IFLA_INET_MAX+1] = { + [IFLA_INET_CONF] = { .type = NLA_NESTED }, +}; + +static int inet_parse_link_af(struct net_device *dev, const struct nlattr *nla) +{ + struct in_device *in_dev = __in_dev_get_rcu(dev); + struct nlattr *a, *tb[IFLA_INET_MAX+1]; + int err, rem; + + if (!in_dev) + return -EOPNOTSUPP; + + err = nla_parse_nested(tb, IFLA_INET_MAX, nla, inet_af_policy); + if (err < 0) + return err; + + if (tb[IFLA_INET_CONF]) { + nla_for_each_nested(a, tb[IFLA_INET_CONF], rem) { + int cfgid = nla_type(a); + + if (nla_len(a) < 4) + return -EINVAL; + + if (cfgid <= 0 || cfgid > IPV4_DEVCONF_MAX) + return -EINVAL; + } + } + + if (tb[IFLA_INET_CONF]) { + nla_for_each_nested(a, tb[IFLA_INET_CONF], rem) + ipv4_devconf_set(in_dev, nla_type(a), nla_get_u32(a)); + } + + return 0; +} + #ifdef CONFIG_SYSCTL static void devinet_copy_dflt_conf(struct net *net, int i) @@ -1619,6 +1685,13 @@ static __net_initdata struct pernet_operations devinet_ops = { .exit = devinet_exit_net, }; +static struct rtnl_af_ops inet_af_ops = { + .family = AF_INET, + .fill_link_af = inet_fill_link_af, + .get_link_af_size = inet_get_link_af_size, + .parse_link_af = inet_parse_link_af, +}; + void __init devinet_init(void) { register_pernet_subsys(&devinet_ops); @@ -1626,6 +1699,8 @@ void __init devinet_init(void) register_gifconf(PF_INET, inet_gifconf); register_netdevice_notifier(&ip_netdev_notifier); + rtnl_af_register(&inet_af_ops); + rtnl_register(PF_INET, RTM_NEWADDR, inet_rtm_newaddr, NULL); rtnl_register(PF_INET, RTM_DELADDR, inet_rtm_deladdr, NULL); rtnl_register(PF_INET, RTM_GETADDR, NULL, inet_dump_ifaddr); -- cgit v1.2.3 From eb06acdc85585f28864261f28659157848762ee4 Mon Sep 17 00:00:00 2001 From: Sridhar Samudrala Date: Thu, 28 Oct 2010 13:10:50 +0000 Subject: macvlan: Introduce 'passthru' mode to takeover the underlying device With the current default 'vepa' mode, a KVM guest using virtio with macvtap backend has the following limitations. - cannot change/add a mac address on the guest virtio-net - cannot create a vlan device on the guest virtio-net - cannot enable promiscuous mode on guest virtio-net To address these limitations, this patch introduces a new mode called 'passthru' when creating a macvlan device which allows takeover of the underlying device and passing it to a guest using virtio with macvtap backend. Only one macvlan device is allowed in passthru mode and it inherits the mac address from the underlying device and sets it in promiscuous mode to receive and forward all the packets. Signed-off-by: Sridhar Samudrala ------------------------------------------------------------------------- Signed-off-by: David S. Miller --- drivers/net/macvlan.c | 33 ++++++++++++++++++++++++++++++++- include/linux/if_link.h | 1 + 2 files changed, 33 insertions(+), 1 deletion(-) (limited to 'include/linux/if_link.h') diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 93f0ba25c808..6ed577b065df 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -38,6 +38,7 @@ struct macvlan_port { struct hlist_head vlan_hash[MACVLAN_HASH_SIZE]; struct list_head vlans; struct rcu_head rcu; + bool passthru; }; #define macvlan_port_get_rcu(dev) \ @@ -169,6 +170,7 @@ static struct sk_buff *macvlan_handle_frame(struct sk_buff *skb) macvlan_broadcast(skb, port, NULL, MACVLAN_MODE_PRIVATE | MACVLAN_MODE_VEPA | + MACVLAN_MODE_PASSTHRU| MACVLAN_MODE_BRIDGE); else if (src->mode == MACVLAN_MODE_VEPA) /* flood to everyone except source */ @@ -185,7 +187,10 @@ static struct sk_buff *macvlan_handle_frame(struct sk_buff *skb) return skb; } - vlan = macvlan_hash_lookup(port, eth->h_dest); + if (port->passthru) + vlan = list_first_entry(&port->vlans, struct macvlan_dev, list); + else + vlan = macvlan_hash_lookup(port, eth->h_dest); if (vlan == NULL) return skb; @@ -288,6 +293,11 @@ static int macvlan_open(struct net_device *dev) struct net_device *lowerdev = vlan->lowerdev; int err; + if (vlan->port->passthru) { + dev_set_promiscuity(lowerdev, 1); + goto hash_add; + } + err = -EBUSY; if (macvlan_addr_busy(vlan->port, dev->dev_addr)) goto out; @@ -300,6 +310,8 @@ static int macvlan_open(struct net_device *dev) if (err < 0) goto del_unicast; } + +hash_add: macvlan_hash_add(vlan); return 0; @@ -314,12 +326,18 @@ static int macvlan_stop(struct net_device *dev) struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; + if (vlan->port->passthru) { + dev_set_promiscuity(lowerdev, -1); + goto hash_del; + } + dev_mc_unsync(lowerdev, dev); if (dev->flags & IFF_ALLMULTI) dev_set_allmulti(lowerdev, -1); dev_uc_del(lowerdev, dev->dev_addr); +hash_del: macvlan_hash_del(vlan); return 0; } @@ -559,6 +577,7 @@ static int macvlan_port_create(struct net_device *dev) if (port == NULL) return -ENOMEM; + port->passthru = false; port->dev = dev; INIT_LIST_HEAD(&port->vlans); for (i = 0; i < MACVLAN_HASH_SIZE; i++) @@ -603,6 +622,7 @@ static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[]) case MACVLAN_MODE_PRIVATE: case MACVLAN_MODE_VEPA: case MACVLAN_MODE_BRIDGE: + case MACVLAN_MODE_PASSTHRU: break; default: return -EINVAL; @@ -652,6 +672,10 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev, } port = macvlan_port_get(lowerdev); + /* Only 1 macvlan device can be created in passthru mode */ + if (port->passthru) + return -EINVAL; + vlan->lowerdev = lowerdev; vlan->dev = dev; vlan->port = port; @@ -662,6 +686,13 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev, if (data && data[IFLA_MACVLAN_MODE]) vlan->mode = nla_get_u32(data[IFLA_MACVLAN_MODE]); + if (vlan->mode == MACVLAN_MODE_PASSTHRU) { + if (!list_empty(&port->vlans)) + return -EINVAL; + port->passthru = true; + memcpy(dev->dev_addr, lowerdev->dev_addr, ETH_ALEN); + } + err = register_netdevice(dev); if (err < 0) goto destroy_port; diff --git a/include/linux/if_link.h b/include/linux/if_link.h index 2e02e4d7b11e..6485d2a89bec 100644 --- a/include/linux/if_link.h +++ b/include/linux/if_link.h @@ -259,6 +259,7 @@ enum macvlan_mode { MACVLAN_MODE_PRIVATE = 1, /* don't talk to other macvlans */ MACVLAN_MODE_VEPA = 2, /* talk to other ports through ext bridge */ MACVLAN_MODE_BRIDGE = 4, /* talk to bridge ports directly */ + MACVLAN_MODE_PASSTHRU = 8,/* take over the underlying device */ }; /* SR-IOV virtual function management section */ -- cgit v1.2.3