[PATCH bpf-next v4 08/16] udp: Run SK_LOOKUP BPF program on socket lookup

[Jakub Sitnicki <jakub@cloudflare.com>]

Following INET/TCP socket lookup changes, modify UDP socket lookup to let
BPF program select a receiving socket before searching for a socket by
destination address and port as usual.

Lookup of connected sockets that match packet 4-tuple is unaffected by this
change. BPF program runs, and potentially overrides the lookup result, only
if a 4-tuple match was not found.

Suggested-by: Marek Majkowski <marek@cloudflare.com>
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
---

Notes:
    v4:
    - Adapt to change in bpf_sk_lookup_run_v4 return value semantics.
    
    v3:
    - Use a static_key to minimize the hook overhead when not used. (Alexei)
    - Adapt for running an array of attached programs. (Alexei)
    - Adapt for optionally skipping reuseport selection. (Martin)

 net/ipv4/udp.c | 59 ++++++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 50 insertions(+), 9 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 0d03e0277263..e82db3ab49d3 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -456,6 +456,29 @@ static struct sock *udp4_lib_lookup2(struct net *net,
 	return result;
 }
 
+static inline struct sock *udp4_lookup_run_bpf(struct net *net,
+					       struct udp_table *udptable,
+					       struct sk_buff *skb,
+					       __be32 saddr, __be16 sport,
+					       __be32 daddr, u16 hnum)
+{
+	struct sock *sk, *reuse_sk;
+	bool no_reuseport;
+
+	if (udptable != &udp_table)
+		return NULL; /* only UDP is supported */
+
+	no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_UDP,
+					    saddr, sport, daddr, hnum, &sk);
+	if (no_reuseport || IS_ERR_OR_NULL(sk))
+		return sk;
+
+	reuse_sk = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum);
+	if (reuse_sk)
+		sk = reuse_sk;
+	return sk;
+}
+
 /* UDP is nearly always wildcards out the wazoo, it makes no sense to try
  * harder than this. -DaveM
  */
@@ -463,27 +486,45 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
 		__be16 sport, __be32 daddr, __be16 dport, int dif,
 		int sdif, struct udp_table *udptable, struct sk_buff *skb)
 {
-	struct sock *result;
 	unsigned short hnum = ntohs(dport);
 	unsigned int hash2, slot2;
 	struct udp_hslot *hslot2;
+	struct sock *result, *sk;
 
 	hash2 = ipv4_portaddr_hash(net, daddr, hnum);
 	slot2 = hash2 & udptable->mask;
 	hslot2 = &udptable->hash2[slot2];
 
+	/* Lookup connected or non-wildcard socket */
 	result = udp4_lib_lookup2(net, saddr, sport,
 				  daddr, hnum, dif, sdif,
 				  hslot2, skb);
-	if (!result) {
-		hash2 = ipv4_portaddr_hash(net, htonl(INADDR_ANY), hnum);
-		slot2 = hash2 & udptable->mask;
-		hslot2 = &udptable->hash2[slot2];
-
-		result = udp4_lib_lookup2(net, saddr, sport,
-					  htonl(INADDR_ANY), hnum, dif, sdif,
-					  hslot2, skb);
+	if (!IS_ERR_OR_NULL(result) && result->sk_state == TCP_ESTABLISHED)
+		goto done;
+
+	/* Lookup redirect from BPF */
+	if (static_branch_unlikely(&bpf_sk_lookup_enabled)) {
+		sk = udp4_lookup_run_bpf(net, udptable, skb,
+					 saddr, sport, daddr, hnum);
+		if (sk) {
+			result = sk;
+			goto done;
+		}
 	}
+
+	/* Got non-wildcard socket or error on first lookup */
+	if (result)
+		goto done;
+
+	/* Lookup wildcard sockets */
+	hash2 = ipv4_portaddr_hash(net, htonl(INADDR_ANY), hnum);
+	slot2 = hash2 & udptable->mask;
+	hslot2 = &udptable->hash2[slot2];
+
+	result = udp4_lib_lookup2(net, saddr, sport,
+				  htonl(INADDR_ANY), hnum, dif, sdif,
+				  hslot2, skb);
+done:
 	if (IS_ERR(result))
 		return NULL;
 	return result;
-- 
2.25.4