diff options
author | Daniel Borkmann <daniel@iogearbox.net> | 2019-02-08 13:55:31 +0100 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2019-02-08 11:16:48 -0800 |
commit | c675e06a98a474f7ad0af32ce467613da818da52 (patch) | |
tree | 89d60212e3566eb1d81de4ba55b78c9264ae9403 /drivers/net/ipvlan/ipvlan_l3s.c | |
parent | 998a8a8387ff5f65da456d1fc448dbb926fb5d78 (diff) | |
download | lwn-c675e06a98a474f7ad0af32ce467613da818da52.tar.gz lwn-c675e06a98a474f7ad0af32ce467613da818da52.zip |
ipvlan: decouple l3s mode dependencies from other modes
Right now ipvlan has a hard dependency on CONFIG_NETFILTER and
otherwise it cannot be built. However, the only ipvlan operation
mode that actually depends on netfilter is l3s, everything else
is independent of it. Break this hard dependency such that users
are able to use ipvlan l3 mode on systems where netfilter is not
compiled in.
Therefore, this adds a hidden CONFIG_IPVLAN_L3S bool which is
defaulting to y when CONFIG_NETFILTER is set in order to retain
existing behavior for l3s. All l3s related code is refactored
into ipvlan_l3s.c that is compiled in when enabled.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Mahesh Bandewar <maheshb@google.com>
Cc: Florian Westphal <fw@strlen.de>
Cc: Martynas Pumputis <m@lambda.lt>
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'drivers/net/ipvlan/ipvlan_l3s.c')
-rw-r--r-- | drivers/net/ipvlan/ipvlan_l3s.c | 227 |
1 files changed, 227 insertions, 0 deletions
diff --git a/drivers/net/ipvlan/ipvlan_l3s.c b/drivers/net/ipvlan/ipvlan_l3s.c new file mode 100644 index 000000000000..9a2f24078a54 --- /dev/null +++ b/drivers/net/ipvlan/ipvlan_l3s.c @@ -0,0 +1,227 @@ +/* Copyright (c) 2014 Mahesh Bandewar <maheshb@google.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 of + * the License, or (at your option) any later version. + */ + +#include "ipvlan.h" + +static unsigned int ipvlan_netid __read_mostly; + +struct ipvlan_netns { + unsigned int ipvl_nf_hook_refcnt; +}; + +static struct ipvl_addr *ipvlan_skb_to_addr(struct sk_buff *skb, + struct net_device *dev) +{ + struct ipvl_addr *addr = NULL; + struct ipvl_port *port; + int addr_type; + void *lyr3h; + + if (!dev || !netif_is_ipvlan_port(dev)) + goto out; + + port = ipvlan_port_get_rcu(dev); + if (!port || port->mode != IPVLAN_MODE_L3S) + goto out; + + lyr3h = ipvlan_get_L3_hdr(port, skb, &addr_type); + if (!lyr3h) + goto out; + + addr = ipvlan_addr_lookup(port, lyr3h, addr_type, true); +out: + return addr; +} + +static struct sk_buff *ipvlan_l3_rcv(struct net_device *dev, + struct sk_buff *skb, u16 proto) +{ + struct ipvl_addr *addr; + struct net_device *sdev; + + addr = ipvlan_skb_to_addr(skb, dev); + if (!addr) + goto out; + + sdev = addr->master->dev; + switch (proto) { + case AF_INET: + { + struct iphdr *ip4h = ip_hdr(skb); + int err; + + err = ip_route_input_noref(skb, ip4h->daddr, ip4h->saddr, + ip4h->tos, sdev); + if (unlikely(err)) + goto out; + break; + } +#if IS_ENABLED(CONFIG_IPV6) + case AF_INET6: + { + struct dst_entry *dst; + struct ipv6hdr *ip6h = ipv6_hdr(skb); + int flags = RT6_LOOKUP_F_HAS_SADDR; + struct flowi6 fl6 = { + .flowi6_iif = sdev->ifindex, + .daddr = ip6h->daddr, + .saddr = ip6h->saddr, + .flowlabel = ip6_flowinfo(ip6h), + .flowi6_mark = skb->mark, + .flowi6_proto = ip6h->nexthdr, + }; + + skb_dst_drop(skb); + dst = ip6_route_input_lookup(dev_net(sdev), sdev, &fl6, + skb, flags); + skb_dst_set(skb, dst); + break; + } +#endif + default: + break; + } +out: + return skb; +} + +static const struct l3mdev_ops ipvl_l3mdev_ops = { + .l3mdev_l3_rcv = ipvlan_l3_rcv, +}; + +static unsigned int ipvlan_nf_input(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct ipvl_addr *addr; + unsigned int len; + + addr = ipvlan_skb_to_addr(skb, skb->dev); + if (!addr) + goto out; + + skb->dev = addr->master->dev; + len = skb->len + ETH_HLEN; + ipvlan_count_rx(addr->master, len, true, false); +out: + return NF_ACCEPT; +} + +static const struct nf_hook_ops ipvl_nfops[] = { + { + .hook = ipvlan_nf_input, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_LOCAL_IN, + .priority = INT_MAX, + }, +#if IS_ENABLED(CONFIG_IPV6) + { + .hook = ipvlan_nf_input, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_LOCAL_IN, + .priority = INT_MAX, + }, +#endif +}; + +static int ipvlan_register_nf_hook(struct net *net) +{ + struct ipvlan_netns *vnet = net_generic(net, ipvlan_netid); + int err = 0; + + if (!vnet->ipvl_nf_hook_refcnt) { + err = nf_register_net_hooks(net, ipvl_nfops, + ARRAY_SIZE(ipvl_nfops)); + if (!err) + vnet->ipvl_nf_hook_refcnt = 1; + } else { + vnet->ipvl_nf_hook_refcnt++; + } + + return err; +} + +static void ipvlan_unregister_nf_hook(struct net *net) +{ + struct ipvlan_netns *vnet = net_generic(net, ipvlan_netid); + + if (WARN_ON(!vnet->ipvl_nf_hook_refcnt)) + return; + + vnet->ipvl_nf_hook_refcnt--; + if (!vnet->ipvl_nf_hook_refcnt) + nf_unregister_net_hooks(net, ipvl_nfops, + ARRAY_SIZE(ipvl_nfops)); +} + +void ipvlan_migrate_l3s_hook(struct net *oldnet, struct net *newnet) +{ + struct ipvlan_netns *old_vnet; + + ASSERT_RTNL(); + + old_vnet = net_generic(oldnet, ipvlan_netid); + if (!old_vnet->ipvl_nf_hook_refcnt) + return; + + ipvlan_register_nf_hook(newnet); + ipvlan_unregister_nf_hook(oldnet); +} + +static void ipvlan_ns_exit(struct net *net) +{ + struct ipvlan_netns *vnet = net_generic(net, ipvlan_netid); + + if (WARN_ON_ONCE(vnet->ipvl_nf_hook_refcnt)) { + vnet->ipvl_nf_hook_refcnt = 0; + nf_unregister_net_hooks(net, ipvl_nfops, + ARRAY_SIZE(ipvl_nfops)); + } +} + +static struct pernet_operations ipvlan_net_ops = { + .id = &ipvlan_netid, + .size = sizeof(struct ipvlan_netns), + .exit = ipvlan_ns_exit, +}; + +int ipvlan_l3s_init(void) +{ + return register_pernet_subsys(&ipvlan_net_ops); +} + +void ipvlan_l3s_cleanup(void) +{ + unregister_pernet_subsys(&ipvlan_net_ops); +} + +int ipvlan_l3s_register(struct ipvl_port *port) +{ + struct net_device *dev = port->dev; + int ret; + + ASSERT_RTNL(); + + ret = ipvlan_register_nf_hook(read_pnet(&port->pnet)); + if (!ret) { + dev->l3mdev_ops = &ipvl_l3mdev_ops; + dev->priv_flags |= IFF_L3MDEV_MASTER; + } + + return ret; +} + +void ipvlan_l3s_unregister(struct ipvl_port *port) +{ + struct net_device *dev = port->dev; + + ASSERT_RTNL(); + + dev->priv_flags &= ~IFF_L3MDEV_MASTER; + ipvlan_unregister_nf_hook(read_pnet(&port->pnet)); + dev->l3mdev_ops = NULL; +} |