netfilter: Introduce egress hook

Commit e687ad60af09 ("netfilter: add netfilter ingress hook after
handle_ing() under unique static key") introduced the ability to
classify packets on ingress.

Allow the same on egress.  Position the hook immediately before a packet
is handed to tc and then sent out on an interface, thereby mirroring the
ingress order.  This order allows marking packets in the netfilter
egress hook and subsequently using the mark in tc.  Another benefit of
this order is consistency with a lot of existing documentation which
says that egress tc is performed after netfilter hooks.

Egress hooks already exist for the most common protocols, such as
NF_INET_LOCAL_OUT or NF_ARP_OUT, and those are to be preferred because
they are executed earlier during packet processing.  However for more
exotic protocols, there is currently no provision to apply netfilter on
egress.  A common workaround is to enslave the interface to a bridge and
use ebtables, or to resort to tc.  But when the ingress hook was
introduced, consensus was that users should be given the choice to use
netfilter or tc, whichever tool suits their needs best:
https://lore.kernel.org/netdev/20150430153317.GA3230@salvia/
This hook is also useful for NAT46/NAT64, tunneling and filtering of
locally generated af_packet traffic such as dhclient.

There have also been occasional user requests for a netfilter egress
hook in the past, e.g.:
https://www.spinics.net/lists/netfilter/msg50038.html

Performance measurements with pktgen surprisingly show a speedup rather
than a slowdown with this commit:

* Without this commit:
  Result: OK: 34240933(c34238375+d2558) usec, 100000000 (60byte,0frags)
  2920481pps 1401Mb/sec (1401830880bps) errors: 0

* With this commit:
  Result: OK: 33997299(c33994193+d3106) usec, 100000000 (60byte,0frags)
  2941410pps 1411Mb/sec (1411876800bps) errors: 0

* Without this commit + tc egress:
  Result: OK: 39022386(c39019547+d2839) usec, 100000000 (60byte,0frags)
  2562631pps 1230Mb/sec (1230062880bps) errors: 0

* With this commit + tc egress:
  Result: OK: 37604447(c37601877+d2570) usec, 100000000 (60byte,0frags)
  2659259pps 1276Mb/sec (1276444320bps) errors: 0

* With this commit + nft egress:
  Result: OK: 41436689(c41434088+d2600) usec, 100000000 (60byte,0frags)
  2413320pps 1158Mb/sec (1158393600bps) errors: 0

Tested on a bare-metal Core i7-3615QM, each measurement was performed
three times to verify that the numbers are stable.

Commands to perform a measurement:
modprobe pktgen
echo "add_device lo@3" > /proc/net/pktgen/kpktgend_3
samples/pktgen/pktgen_bench_xmit_mode_queue_xmit.sh -i 'lo@3' -n 100000000

Commands for testing tc egress:
tc qdisc add dev lo clsact
tc filter add dev lo egress protocol ip prio 1 u32 match ip dst 4.3.2.1/32

Commands for testing nft egress:
nft add table netdev t
nft add chain netdev t co \{ type filter hook egress device lo priority 0 \; \}
nft add rule netdev t co ip daddr 4.3.2.1/32 drop

All testing was performed on the loopback interface to avoid distorting
measurements by the packet handling in the low-level Ethernet driver.

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

3 files changed, 32 insertions, 0 deletions

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 654808bfad83..15f1e32b430c 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1751,6 +1751,7 @@ enum netdev_priv_flags {
  *	@xps_maps:	XXX: need comments on this one
  *	@miniq_egress:		clsact qdisc specific data for
  *				egress processing
+ *	@nf_hooks_egress:	netfilter hooks executed for egress packets
  *	@qdisc_hash:		qdisc hash table
  *	@watchdog_timeo:	Represents the timeout that is used by
  *				the watchdog (see dev_watchdog())
@@ -2026,6 +2027,9 @@ struct net_device {
 #ifdef CONFIG_NET_CLS_ACT
 	struct mini_Qdisc __rcu	*miniq_egress;
 #endif
+#ifdef CONFIG_NETFILTER_EGRESS
+	struct nf_hook_entries __rcu *nf_hooks_egress;
+#endif
 
 #ifdef CONFIG_NET_SCHED
 	DECLARE_HASHTABLE	(qdisc_hash, 4);
diff --git a/include/linux/netfilter_netdev.h b/include/linux/netfilter_netdev.h
index 49e26479642e..92d3611a782e 100644
--- a/include/linux/netfilter_netdev.h
+++ b/include/linux/netfilter_netdev.h
@@ -47,6 +47,9 @@ static inline void nf_hook_netdev_init(struct net_device *dev)
 #ifdef CONFIG_NETFILTER_INGRESS
 	RCU_INIT_POINTER(dev->nf_hooks_ingress, NULL);
 #endif
+#ifdef CONFIG_NETFILTER_EGRESS
+	RCU_INIT_POINTER(dev->nf_hooks_egress, NULL);
+#endif
 }
 
 #ifdef CONFIG_NETFILTER_INGRESS
@@ -72,4 +75,28 @@ static inline int nf_hook_ingress(struct sk_buff *skb)
 	return 0;
 }
 #endif /* CONFIG_NETFILTER_INGRESS */
+
+#ifdef CONFIG_NETFILTER_EGRESS
+static inline bool nf_hook_egress_active(const struct sk_buff *skb)
+{
+	return nf_hook_netdev_active(NF_NETDEV_EGRESS,
+				     skb->dev->nf_hooks_egress);
+}
+
+static inline int nf_hook_egress(struct sk_buff *skb)
+{
+	return nf_hook_netdev(skb, NF_NETDEV_EGRESS,
+			      skb->dev->nf_hooks_egress);
+}
+#else /* CONFIG_NETFILTER_EGRESS */
+static inline int nf_hook_egress_active(struct sk_buff *skb)
+{
+	return 0;
+}
+
+static inline int nf_hook_egress(struct sk_buff *skb)
+{
+	return 0;
+}
+#endif /* CONFIG_NETFILTER_EGRESS */
 #endif /* _NETFILTER_INGRESS_H_ */
diff --git a/include/uapi/linux/netfilter.h b/include/uapi/linux/netfilter.h
index ca9e63d6e0e4..d1616574c54f 100644
--- a/include/uapi/linux/netfilter.h
+++ b/include/uapi/linux/netfilter.h
@@ -50,6 +50,7 @@ enum nf_inet_hooks {
 
 enum nf_dev_hooks {
 	NF_NETDEV_INGRESS,
+	NF_NETDEV_EGRESS,
 	NF_NETDEV_NUMHOOKS
 };