int l3mdev_fib_rule_match(struct net *net, struct flowi *fl,
struct fib_lookup_arg *arg)
{
struct net_device *dev;
int rc = 0;
rcu_read_lock();
dev = dev_get_by_index_rcu(net, fl->flowi_oif);
if (dev && netif_is_l3_master(dev) &&
dev->l3mdev_ops->l3mdev_fib_table) {
arg->table = dev->l3mdev_ops->l3mdev_fib_table(dev);
rc = 1;
goto out;
}
dev = dev_get_by_index_rcu(net, fl->flowi_iif);
if (dev && netif_is_l3_master(dev) &&
dev->l3mdev_ops->l3mdev_fib_table) {
arg->table = dev->l3mdev_ops->l3mdev_fib_table(dev);
rc = 1;
goto out;
}
out:
rcu_read_unlock();
return rc;
}
static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev)
{
if (netif_is_l3_master(port_dev) || netif_is_l3_slave(port_dev))
return -EINVAL;
return do_vrf_add_slave(dev, port_dev);
}
u32 l3mdev_fib_table_rcu(const struct net_device *dev)
{
u32 tb_id = 0;
if (!dev)
return 0;
if (netif_is_l3_master(dev)) {
if (dev->l3mdev_ops->l3mdev_fib_table)
tb_id = dev->l3mdev_ops->l3mdev_fib_table(dev);
} else if (netif_is_l3_slave(dev)) {
/* Users of netdev_master_upper_dev_get_rcu need non-const,
* but current inet_*type functions take a const
*/
struct net_device *_dev = (struct net_device *) dev;
const struct net_device *master;
master = netdev_master_upper_dev_get_rcu(_dev);
if (master &&
master->l3mdev_ops->l3mdev_fib_table)
tb_id = master->l3mdev_ops->l3mdev_fib_table(master);
}
return tb_id;
}
int l3mdev_master_ifindex_rcu(const struct net_device *dev)
{
int ifindex = 0;
if (!dev)
return 0;
if (netif_is_l3_master(dev)) {
ifindex = dev->ifindex;
} else if (netif_is_l3_slave(dev)) {
struct net_device *master;
struct net_device *_dev = (struct net_device *)dev;
/* netdev_master_upper_dev_get_rcu calls
* list_first_or_null_rcu to walk the upper dev list.
* list_first_or_null_rcu does not handle a const arg. We aren't
* making changes, just want the master device from that list so
* typecast to remove the const
*/
master = netdev_master_upper_dev_get_rcu(_dev);
if (master)
ifindex = master->ifindex;
}
return ifindex;
}
static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev,
struct netlink_ext_ack *extack)
{
if (netif_is_l3_master(port_dev)) {
NL_SET_ERR_MSG(extack,
"Can not enslave an L3 master device to a VRF");
return -EINVAL;
}
if (netif_is_l3_slave(port_dev))
return -EINVAL;
return do_vrf_add_slave(dev, port_dev, extack);
}
struct dst_entry *l3mdev_link_scope_lookup(struct net *net,
struct flowi6 *fl6)
{
struct dst_entry *dst = NULL;
struct net_device *dev;
if (fl6->flowi6_oif) {
rcu_read_lock();
dev = dev_get_by_index_rcu(net, fl6->flowi6_oif);
if (dev && netif_is_l3_slave(dev))
dev = netdev_master_upper_dev_get_rcu(dev);
if (dev && netif_is_l3_master(dev) &&
dev->l3mdev_ops->l3mdev_link_scope_lookup)
dst = dev->l3mdev_ops->l3mdev_link_scope_lookup(dev, fl6);
rcu_read_unlock();
}
return dst;
}
static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev,
struct net *net)
{
const struct ipv6hdr *hdr;
u32 pkt_len;
struct inet6_dev *idev;
if (skb->pkt_type == PACKET_OTHERHOST) {
kfree_skb(skb);
return NULL;
}
rcu_read_lock();
idev = __in6_dev_get(skb->dev);
__IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_IN, skb->len);
if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL ||
!idev || unlikely(idev->cnf.disable_ipv6)) {
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
goto drop;
}
memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));
/*
* Store incoming device index. When the packet will
* be queued, we cannot refer to skb->dev anymore.
*
* BTW, when we send a packet for our own local address on a
* non-loopback interface (e.g. ethX), it is being delivered
* via the loopback interface (lo) here; skb->dev = loopback_dev.
* It, however, should be considered as if it is being
* arrived via the sending interface (ethX), because of the
* nature of scoping architecture. --yoshfuji
*/
IP6CB(skb)->iif = skb_valid_dst(skb) ? ip6_dst_idev(skb_dst(skb))->dev->ifindex : dev->ifindex;
if (unlikely(!pskb_may_pull(skb, sizeof(*hdr))))
goto err;
hdr = ipv6_hdr(skb);
if (hdr->version != 6)
goto err;
__IP6_ADD_STATS(net, idev,
IPSTATS_MIB_NOECTPKTS +
(ipv6_get_dsfield(hdr) & INET_ECN_MASK),
max_t(unsigned short, 1, skb_shinfo(skb)->gso_segs));
/*
* RFC4291 2.5.3
* The loopback address must not be used as the source address in IPv6
* packets that are sent outside of a single node. [..]
* A packet received on an interface with a destination address
* of loopback must be dropped.
*/
if ((ipv6_addr_loopback(&hdr->saddr) ||
ipv6_addr_loopback(&hdr->daddr)) &&
!(dev->flags & IFF_LOOPBACK) &&
!netif_is_l3_master(dev))
goto err;
/* RFC4291 Errata ID: 3480
* Interface-Local scope spans only a single interface on a
* node and is useful only for loopback transmission of
* multicast. Packets with interface-local scope received
* from another node must be discarded.
*/
if (!(skb->pkt_type == PACKET_LOOPBACK ||
dev->flags & IFF_LOOPBACK) &&
ipv6_addr_is_multicast(&hdr->daddr) &&
IPV6_ADDR_MC_SCOPE(&hdr->daddr) == 1)
goto err;
/* If enabled, drop unicast packets that were encapsulated in link-layer
* multicast or broadcast to protected against the so-called "hole-196"
* attack in 802.11 wireless.
*/
if (!ipv6_addr_is_multicast(&hdr->daddr) &&
(skb->pkt_type == PACKET_BROADCAST ||
skb->pkt_type == PACKET_MULTICAST) &&
idev->cnf.drop_unicast_in_l2_multicast)
goto err;
/* RFC4291 2.7
* Nodes must not originate a packet to a multicast address whose scope
* field contains the reserved value 0; if such a packet is received, it
* must be silently dropped.
*/
if (ipv6_addr_is_multicast(&hdr->daddr) &&
IPV6_ADDR_MC_SCOPE(&hdr->daddr) == 0)
goto err;
/*
* RFC4291 2.7
* Multicast addresses must not be used as source addresses in IPv6
* packets or appear in any Routing header.
*/
if (ipv6_addr_is_multicast(&hdr->saddr))
goto err;
skb->transport_header = skb->network_header + sizeof(*hdr);
IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr);
pkt_len = ntohs(hdr->payload_len);
/* pkt_len may be zero if Jumbo payload option is present */
if (pkt_len || hdr->nexthdr != NEXTHDR_HOP) {
if (pkt_len + sizeof(struct ipv6hdr) > skb->len) {
__IP6_INC_STATS(net,
idev, IPSTATS_MIB_INTRUNCATEDPKTS);
goto drop;
}
if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr))) {
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
goto drop;
}
hdr = ipv6_hdr(skb);
}
if (hdr->nexthdr == NEXTHDR_HOP) {
if (ipv6_parse_hopopts(skb) < 0) {
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
rcu_read_unlock();
return NULL;
}
}
rcu_read_unlock();
/* Must drop socket now because of tproxy. */
skb_orphan(skb);
return skb;
err:
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
drop:
rcu_read_unlock();
kfree_skb(skb);
return NULL;
}