alistair23-linux/include/net/l3mdev.h
Daniel Borkmann d5256083f6 ipvlan, l3mdev: fix broken l3s mode wrt local routes
While implementing ipvlan l3 and l3s mode for kubernetes CNI plugin,
I ran into the issue that while l3 mode is working fine, l3s mode
does not have any connectivity to kube-apiserver and hence all pods
end up in Error state as well. The ipvlan master device sits on
top of a bond device and hostns traffic to kube-apiserver (also running
in hostns) is DNATed from 10.152.183.1:443 to 139.178.29.207:37573
where the latter is the address of the bond0. While in l3 mode, a
curl to https://10.152.183.1:443 or to https://139.178.29.207:37573
works fine from hostns, neither of them do in case of l3s. In the
latter only a curl to https://127.0.0.1:37573 appeared to work where
for local addresses of bond0 I saw kernel suddenly starting to emit
ARP requests to query HW address of bond0 which remained unanswered
and neighbor entries in INCOMPLETE state. These ARP requests only
happen while in l3s.

Debugging this further, I found the issue is that l3s mode is piggy-
backing on l3 master device, and in this case local routes are using
l3mdev_master_dev_rcu(dev) instead of net->loopback_dev as per commit
f5a0aab84b ("net: ipv4: dst for local input routes should use l3mdev
if relevant") and 5f02ce24c2 ("net: l3mdev: Allow the l3mdev to be
a loopback"). I found that reverting them back into using the
net->loopback_dev fixed ipvlan l3s connectivity and got everything
working for the CNI.

Now judging from 4fbae7d83c ("ipvlan: Introduce l3s mode") and the
l3mdev paper in [0] the only sole reason why ipvlan l3s is relying
on l3 master device is to get the l3mdev_ip_rcv() receive hook for
setting the dst entry of the input route without adding its own
ipvlan specific hacks into the receive path, however, any l3 domain
semantics beyond just that are breaking l3s operation. Note that
ipvlan also has the ability to dynamically switch its internal
operation from l3 to l3s for all ports via ipvlan_set_port_mode()
at runtime. In any case, l3 vs l3s soley distinguishes itself by
'de-confusing' netfilter through switching skb->dev to ipvlan slave
device late in NF_INET_LOCAL_IN before handing the skb to L4.

Minimal fix taken here is to add a IFF_L3MDEV_RX_HANDLER flag which,
if set from ipvlan setup, gets us only the wanted l3mdev_l3_rcv() hook
without any additional l3mdev semantics on top. This should also have
minimal impact since dev->priv_flags is already hot in cache. With
this set, l3s mode is working fine and I also get things like
masquerading pod traffic on the ipvlan master properly working.

  [0] https://netdevconf.org/1.2/papers/ahern-what-is-l3mdev-paper.pdf

Fixes: f5a0aab84b ("net: ipv4: dst for local input routes should use l3mdev if relevant")
Fixes: 5f02ce24c2 ("net: l3mdev: Allow the l3mdev to be a loopback")
Fixes: 4fbae7d83c ("ipvlan: Introduce l3s mode")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Mahesh Bandewar <maheshb@google.com>
Cc: David Ahern <dsa@cumulusnetworks.com>
Cc: Florian Westphal <fw@strlen.de>
Cc: Martynas Pumputis <m@lambda.lt>
Acked-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-30 22:13:34 -08:00

300 lines
6.3 KiB
C

/*
* include/net/l3mdev.h - L3 master device API
* Copyright (c) 2015 Cumulus Networks
* Copyright (c) 2015 David Ahern <dsa@cumulusnetworks.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.
*/
#ifndef _NET_L3MDEV_H_
#define _NET_L3MDEV_H_
#include <net/dst.h>
#include <net/fib_rules.h>
/**
* struct l3mdev_ops - l3mdev operations
*
* @l3mdev_fib_table: Get FIB table id to use for lookups
*
* @l3mdev_l3_rcv: Hook in L3 receive path
*
* @l3mdev_l3_out: Hook in L3 output path
*
* @l3mdev_link_scope_lookup: IPv6 lookup for linklocal and mcast destinations
*/
struct l3mdev_ops {
u32 (*l3mdev_fib_table)(const struct net_device *dev);
struct sk_buff * (*l3mdev_l3_rcv)(struct net_device *dev,
struct sk_buff *skb, u16 proto);
struct sk_buff * (*l3mdev_l3_out)(struct net_device *dev,
struct sock *sk, struct sk_buff *skb,
u16 proto);
/* IPv6 ops */
struct dst_entry * (*l3mdev_link_scope_lookup)(const struct net_device *dev,
struct flowi6 *fl6);
};
#ifdef CONFIG_NET_L3_MASTER_DEV
int l3mdev_fib_rule_match(struct net *net, struct flowi *fl,
struct fib_lookup_arg *arg);
void l3mdev_update_flow(struct net *net, struct flowi *fl);
int l3mdev_master_ifindex_rcu(const struct net_device *dev);
static inline int l3mdev_master_ifindex(struct net_device *dev)
{
int ifindex;
rcu_read_lock();
ifindex = l3mdev_master_ifindex_rcu(dev);
rcu_read_unlock();
return ifindex;
}
static inline int l3mdev_master_ifindex_by_index(struct net *net, int ifindex)
{
struct net_device *dev;
int rc = 0;
if (likely(ifindex)) {
rcu_read_lock();
dev = dev_get_by_index_rcu(net, ifindex);
if (dev)
rc = l3mdev_master_ifindex_rcu(dev);
rcu_read_unlock();
}
return rc;
}
static inline
struct net_device *l3mdev_master_dev_rcu(const 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
*/
struct net_device *dev = (struct net_device *)_dev;
struct net_device *master;
if (!dev)
return NULL;
if (netif_is_l3_master(dev))
master = dev;
else if (netif_is_l3_slave(dev))
master = netdev_master_upper_dev_get_rcu(dev);
else
master = NULL;
return master;
}
int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex);
static inline
int l3mdev_master_upper_ifindex_by_index(struct net *net, int ifindex)
{
rcu_read_lock();
ifindex = l3mdev_master_upper_ifindex_by_index_rcu(net, ifindex);
rcu_read_unlock();
return ifindex;
}
u32 l3mdev_fib_table_rcu(const struct net_device *dev);
u32 l3mdev_fib_table_by_index(struct net *net, int ifindex);
static inline u32 l3mdev_fib_table(const struct net_device *dev)
{
u32 tb_id;
rcu_read_lock();
tb_id = l3mdev_fib_table_rcu(dev);
rcu_read_unlock();
return tb_id;
}
static inline bool netif_index_is_l3_master(struct net *net, int ifindex)
{
struct net_device *dev;
bool rc = false;
if (ifindex == 0)
return false;
rcu_read_lock();
dev = dev_get_by_index_rcu(net, ifindex);
if (dev)
rc = netif_is_l3_master(dev);
rcu_read_unlock();
return rc;
}
struct dst_entry *l3mdev_link_scope_lookup(struct net *net, struct flowi6 *fl6);
static inline
struct sk_buff *l3mdev_l3_rcv(struct sk_buff *skb, u16 proto)
{
struct net_device *master = NULL;
if (netif_is_l3_slave(skb->dev))
master = netdev_master_upper_dev_get_rcu(skb->dev);
else if (netif_is_l3_master(skb->dev) ||
netif_has_l3_rx_handler(skb->dev))
master = skb->dev;
if (master && master->l3mdev_ops->l3mdev_l3_rcv)
skb = master->l3mdev_ops->l3mdev_l3_rcv(master, skb, proto);
return skb;
}
static inline
struct sk_buff *l3mdev_ip_rcv(struct sk_buff *skb)
{
return l3mdev_l3_rcv(skb, AF_INET);
}
static inline
struct sk_buff *l3mdev_ip6_rcv(struct sk_buff *skb)
{
return l3mdev_l3_rcv(skb, AF_INET6);
}
static inline
struct sk_buff *l3mdev_l3_out(struct sock *sk, struct sk_buff *skb, u16 proto)
{
struct net_device *dev = skb_dst(skb)->dev;
if (netif_is_l3_slave(dev)) {
struct net_device *master;
master = netdev_master_upper_dev_get_rcu(dev);
if (master && master->l3mdev_ops->l3mdev_l3_out)
skb = master->l3mdev_ops->l3mdev_l3_out(master, sk,
skb, proto);
}
return skb;
}
static inline
struct sk_buff *l3mdev_ip_out(struct sock *sk, struct sk_buff *skb)
{
return l3mdev_l3_out(sk, skb, AF_INET);
}
static inline
struct sk_buff *l3mdev_ip6_out(struct sock *sk, struct sk_buff *skb)
{
return l3mdev_l3_out(sk, skb, AF_INET6);
}
#else
static inline int l3mdev_master_ifindex_rcu(const struct net_device *dev)
{
return 0;
}
static inline int l3mdev_master_ifindex(struct net_device *dev)
{
return 0;
}
static inline int l3mdev_master_ifindex_by_index(struct net *net, int ifindex)
{
return 0;
}
static inline
int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex)
{
return 0;
}
static inline
int l3mdev_master_upper_ifindex_by_index(struct net *net, int ifindex)
{
return 0;
}
static inline
struct net_device *l3mdev_master_dev_rcu(const struct net_device *dev)
{
return NULL;
}
static inline u32 l3mdev_fib_table_rcu(const struct net_device *dev)
{
return 0;
}
static inline u32 l3mdev_fib_table(const struct net_device *dev)
{
return 0;
}
static inline u32 l3mdev_fib_table_by_index(struct net *net, int ifindex)
{
return 0;
}
static inline bool netif_index_is_l3_master(struct net *net, int ifindex)
{
return false;
}
static inline
struct dst_entry *l3mdev_link_scope_lookup(struct net *net, struct flowi6 *fl6)
{
return NULL;
}
static inline
struct sk_buff *l3mdev_ip_rcv(struct sk_buff *skb)
{
return skb;
}
static inline
struct sk_buff *l3mdev_ip6_rcv(struct sk_buff *skb)
{
return skb;
}
static inline
struct sk_buff *l3mdev_ip_out(struct sock *sk, struct sk_buff *skb)
{
return skb;
}
static inline
struct sk_buff *l3mdev_ip6_out(struct sock *sk, struct sk_buff *skb)
{
return skb;
}
static inline
int l3mdev_fib_rule_match(struct net *net, struct flowi *fl,
struct fib_lookup_arg *arg)
{
return 1;
}
static inline
void l3mdev_update_flow(struct net *net, struct flowi *fl)
{
}
#endif
#endif /* _NET_L3MDEV_H_ */