Merge branch 'Add FOU support for externally controlled ipip devices'

Christian Ehrig says:

====================

This patch set adds support for using FOU or GUE encapsulation with
an ipip device operating in collect-metadata mode and a set of kfuncs
for controlling encap parameters exposed to a BPF tc-hook.

BPF tc-hooks allow us to read tunnel metadata (like remote IP addresses)
in the ingress path of an externally controlled tunnel interface via
the bpf_skb_get_tunnel_{key,opt} bpf-helpers. Packets can then be
redirected to the same or a different externally controlled tunnel
interface by overwriting metadata via the bpf_skb_set_tunnel_{key,opt}
helpers and a call to bpf_redirect. This enables us to redirect packets
between tunnel interfaces - and potentially change the encapsulation
type - using only a single BPF program.

Today this approach works fine for a couple of tunnel combinations.
For example: redirecting packets between Geneve and GRE interfaces or
GRE and plain ipip interfaces. However, redirecting using FOU or GUE is
not supported today. The ip_tunnel module does not allow us to egress
packets using additional UDP encapsulation from an ipip device in
collect-metadata mode.

Patch 1 lifts this restriction by adding a struct ip_tunnel_encap to
the tunnel metadata. It can be filled by a new BPF kfunc introduced
in Patch 2 and evaluated by the ip_tunnel egress path. This will allow
us to use FOU and GUE encap with externally controlled ipip devices.

Patch 2 introduces two new BPF kfuncs: bpf_skb_{set,get}_fou_encap.
These helpers can be used to set and get UDP encap parameters from the
BPF tc-hook doing the packet redirect.

Patch 3 adds BPF tunnel selftests using the two kfuncs.
---
v3:
 - Integrate selftest into test_progs (Alexei)
v2:
 - Fixes for checkpatch.pl
 - Fixes for kernel test robot
====================

Signed-off-by: Alexei Starovoitov <[email protected]>

2 files changed, 17 insertions, 13 deletions

diff --git a/include/net/fou.h b/include/net/fou.h
index 80f56e275b08..824eb4b231fd 100644
--- a/include/net/fou.h
+++ b/include/net/fou.h
@@ -17,4 +17,6 @@ int __fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
 int __gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
 		       u8 *protocol, __be16 *sport, int type);
 
+int register_fou_bpf(void);
+
 #endif
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index fca357679816..7912f53caae0 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -57,6 +57,13 @@ struct ip_tunnel_key {
 	__u8			flow_flags;
 };
 
+struct ip_tunnel_encap {
+	u16			type;
+	u16			flags;
+	__be16			sport;
+	__be16			dport;
+};
+
 /* Flags for ip_tunnel_info mode. */
 #define IP_TUNNEL_INFO_TX	0x01	/* represents tx tunnel parameters */
 #define IP_TUNNEL_INFO_IPV6	0x02	/* key contains IPv6 addresses */
@@ -66,9 +73,9 @@ struct ip_tunnel_key {
 #define IP_TUNNEL_OPTS_MAX					\
 	GENMASK((sizeof_field(struct ip_tunnel_info,		\
 			      options_len) * BITS_PER_BYTE) - 1, 0)
-
 struct ip_tunnel_info {
 	struct ip_tunnel_key	key;
+	struct ip_tunnel_encap	encap;
 #ifdef CONFIG_DST_CACHE
 	struct dst_cache	dst_cache;
 #endif
@@ -86,13 +93,6 @@ struct ip_tunnel_6rd_parm {
 };
 #endif
 
-struct ip_tunnel_encap {
-	u16			type;
-	u16			flags;
-	__be16			sport;
-	__be16			dport;
-};
-
 struct ip_tunnel_prl_entry {
 	struct ip_tunnel_prl_entry __rcu *next;
 	__be32				addr;
@@ -293,6 +293,7 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 				   __be32 remote, __be32 local,
 				   __be32 key);
 
+void ip_tunnel_md_udp_encap(struct sk_buff *skb, struct ip_tunnel_info *info);
 int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
 		  const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst,
 		  bool log_ecn_error);
@@ -371,22 +372,23 @@ static inline int ip_encap_hlen(struct ip_tunnel_encap *e)
 	return hlen;
 }
 
-static inline int ip_tunnel_encap(struct sk_buff *skb, struct ip_tunnel *t,
+static inline int ip_tunnel_encap(struct sk_buff *skb,
+				  struct ip_tunnel_encap *e,
 				  u8 *protocol, struct flowi4 *fl4)
 {
 	const struct ip_tunnel_encap_ops *ops;
 	int ret = -EINVAL;
 
-	if (t->encap.type == TUNNEL_ENCAP_NONE)
+	if (e->type == TUNNEL_ENCAP_NONE)
 		return 0;
 
-	if (t->encap.type >= MAX_IPTUN_ENCAP_OPS)
+	if (e->type >= MAX_IPTUN_ENCAP_OPS)
 		return -EINVAL;
 
 	rcu_read_lock();
-	ops = rcu_dereference(iptun_encaps[t->encap.type]);
+	ops = rcu_dereference(iptun_encaps[e->type]);
 	if (likely(ops && ops->build_header))
-		ret = ops->build_header(skb, &t->encap, protocol, fl4);
+		ret = ops->build_header(skb, e, protocol, fl4);
 	rcu_read_unlock();
 
 	return ret;