[PATCH bpf-next v4 10/16] udp6: Run SK_LOOKUP BPF program on socket lookup

From: Jakub Sitnicki <jakub@cloudflare.com>
To: bpf@vger.kernel.org
Cc: netdev@vger.kernel.org, kernel-team@cloudflare.com,
	Alexei Starovoitov <ast@kernel.org>,
	Daniel Borkmann <daniel@iogearbox.net>,
	"David S. Miller" <davem@davemloft.net>,
	Jakub Kicinski <kuba@kernel.org>,
	Marek Majkowski <marek@cloudflare.com>
Subject: [PATCH bpf-next v4 10/16] udp6: Run SK_LOOKUP BPF program on socket lookup
Date: Mon, 13 Jul 2020 19:46:48 +0200	[thread overview]
Message-ID: <20200713174654.642628-11-jakub@cloudflare.com> (raw)
In-Reply-To: <20200713174654.642628-1-jakub@cloudflare.com>

Same as for udp4, let BPF program override the socket lookup result, by
selecting a receiving socket of its choice or failing the lookup, if no
connected UDP socket matched packet 4-tuple.

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_v6 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/ipv6/udp.c | 60 ++++++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 51 insertions(+), 9 deletions(-)

diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 65b843e7acde..d46c62976b5b 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -190,6 +190,31 @@ static struct sock *udp6_lib_lookup2(struct net *net,
 	return result;
 }
 
+static inline struct sock *udp6_lookup_run_bpf(struct net *net,
+					       struct udp_table *udptable,
+					       struct sk_buff *skb,
+					       const struct in6_addr *saddr,
+					       __be16 sport,
+					       const struct in6_addr *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_v6(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;
+}
+
 /* rcu_read_lock() must be held */
 struct sock *__udp6_lib_lookup(struct net *net,
 			       const struct in6_addr *saddr, __be16 sport,
@@ -200,25 +225,42 @@ struct sock *__udp6_lib_lookup(struct net *net,
 	unsigned short hnum = ntohs(dport);
 	unsigned int hash2, slot2;
 	struct udp_hslot *hslot2;
-	struct sock *result;
+	struct sock *result, *sk;
 
 	hash2 = ipv6_portaddr_hash(net, daddr, hnum);
 	slot2 = hash2 & udptable->mask;
 	hslot2 = &udptable->hash2[slot2];
 
+	/* Lookup connected or non-wildcard sockets */
 	result = udp6_lib_lookup2(net, saddr, sport,
 				  daddr, hnum, dif, sdif,
 				  hslot2, skb);
-	if (!result) {
-		hash2 = ipv6_portaddr_hash(net, &in6addr_any, hnum);
-		slot2 = hash2 & udptable->mask;
+	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 = udp6_lookup_run_bpf(net, udptable, skb,
+					 saddr, sport, daddr, hnum);
+		if (sk) {
+			result = sk;
+			goto done;
+		}
+	}
 
-		hslot2 = &udptable->hash2[slot2];
+	/* Got non-wildcard socket or error on first lookup */
+	if (result)
+		goto done;
 
-		result = udp6_lib_lookup2(net, saddr, sport,
-					  &in6addr_any, hnum, dif, sdif,
-					  hslot2, skb);
-	}
+	/* Lookup wildcard sockets */
+	hash2 = ipv6_portaddr_hash(net, &in6addr_any, hnum);
+	slot2 = hash2 & udptable->mask;
+	hslot2 = &udptable->hash2[slot2];
+
+	result = udp6_lib_lookup2(net, saddr, sport,
+				  &in6addr_any, hnum, dif, sdif,
+				  hslot2, skb);
+done:
 	if (IS_ERR(result))
 		return NULL;
 	return result;
-- 
2.25.4

