Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Martin KaFai Lau says:

====================
pull-request: bpf-next 2023-08-03

We've added 54 non-merge commits during the last 10 day(s) which contain
a total of 84 files changed, 4026 insertions(+), 562 deletions(-).

The main changes are:

1) Add SO_REUSEPORT support for TC bpf_sk_assign from Lorenz Bauer,
   Daniel Borkmann

2) Support new insns from cpu v4 from Yonghong Song

3) Non-atomically allocate freelist during prefill from YiFei Zhu

4) Support defragmenting IPv(4|6) packets in BPF from Daniel Xu

5) Add tracepoint to xdp attaching failure from Leon Hwang

6) struct netdev_rx_queue and xdp.h reshuffling to reduce
   rebuild time from Jakub Kicinski

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (54 commits)
  net: invert the netdevice.h vs xdp.h dependency
  net: move struct netdev_rx_queue out of netdevice.h
  eth: add missing xdp.h includes in drivers
  selftests/bpf: Add testcase for xdp attaching failure tracepoint
  bpf, xdp: Add tracepoint to xdp attaching failure
  selftests/bpf: fix static assert compilation issue for test_cls_*.c
  bpf: fix bpf_probe_read_kernel prototype mismatch
  riscv, bpf: Adapt bpf trampoline to optimized riscv ftrace framework
  libbpf: fix typos in Makefile
  tracing: bpf: use struct trace_entry in struct syscall_tp_t
  bpf, devmap: Remove unused dtab field from bpf_dtab_netdev
  bpf, cpumap: Remove unused cmap field from bpf_cpu_map_entry
  netfilter: bpf: Only define get_proto_defrag_hook() if necessary
  bpf: Fix an array-index-out-of-bounds issue in disasm.c
  net: remove duplicate INDIRECT_CALLABLE_DECLARE of udp[6]_ehashfn
  docs/bpf: Fix malformed documentation
  bpf: selftests: Add defrag selftests
  bpf: selftests: Support custom type and proto for client sockets
  bpf: selftests: Support not connecting client socket
  netfilter: bpf: Support BPF_F_NETFILTER_IP_DEFRAG in netfilter link
  ...
====================

Link: https://lore.kernel.org/r/20230803174845.825419-1-martin.lau@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 76 insertions, 5 deletions

diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index 56f1286583d3..284b5ce7205d 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -48,6 +48,22 @@ struct sock *__inet6_lookup_established(struct net *net,
 					const u16 hnum, const int dif,
 					const int sdif);
 
+typedef u32 (inet6_ehashfn_t)(const struct net *net,
+			       const struct in6_addr *laddr, const u16 lport,
+			       const struct in6_addr *faddr, const __be16 fport);
+
+inet6_ehashfn_t inet6_ehashfn;
+
+INDIRECT_CALLABLE_DECLARE(inet6_ehashfn_t udp6_ehashfn);
+
+struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk,
+				    struct sk_buff *skb, int doff,
+				    const struct in6_addr *saddr,
+				    __be16 sport,
+				    const struct in6_addr *daddr,
+				    unsigned short hnum,
+				    inet6_ehashfn_t *ehashfn);
+
 struct sock *inet6_lookup_listener(struct net *net,
 				   struct inet_hashinfo *hashinfo,
 				   struct sk_buff *skb, int doff,
@@ -57,6 +73,15 @@ struct sock *inet6_lookup_listener(struct net *net,
 				   const unsigned short hnum,
 				   const int dif, const int sdif);
 
+struct sock *inet6_lookup_run_sk_lookup(struct net *net,
+					int protocol,
+					struct sk_buff *skb, int doff,
+					const struct in6_addr *saddr,
+					const __be16 sport,
+					const struct in6_addr *daddr,
+					const u16 hnum, const int dif,
+					inet6_ehashfn_t *ehashfn);
+
 static inline struct sock *__inet6_lookup(struct net *net,
 					  struct inet_hashinfo *hashinfo,
 					  struct sk_buff *skb, int doff,
@@ -78,6 +103,46 @@ static inline struct sock *__inet6_lookup(struct net *net,
 				     daddr, hnum, dif, sdif);
 }
 
+static inline
+struct sock *inet6_steal_sock(struct net *net, struct sk_buff *skb, int doff,
+			      const struct in6_addr *saddr, const __be16 sport,
+			      const struct in6_addr *daddr, const __be16 dport,
+			      bool *refcounted, inet6_ehashfn_t *ehashfn)
+{
+	struct sock *sk, *reuse_sk;
+	bool prefetched;
+
+	sk = skb_steal_sock(skb, refcounted, &prefetched);
+	if (!sk)
+		return NULL;
+
+	if (!prefetched)
+		return sk;
+
+	if (sk->sk_protocol == IPPROTO_TCP) {
+		if (sk->sk_state != TCP_LISTEN)
+			return sk;
+	} else if (sk->sk_protocol == IPPROTO_UDP) {
+		if (sk->sk_state != TCP_CLOSE)
+			return sk;
+	} else {
+		return sk;
+	}
+
+	reuse_sk = inet6_lookup_reuseport(net, sk, skb, doff,
+					  saddr, sport, daddr, ntohs(dport),
+					  ehashfn);
+	if (!reuse_sk)
+		return sk;
+
+	/* We've chosen a new reuseport sock which is never refcounted. This
+	 * implies that sk also isn't refcounted.
+	 */
+	WARN_ON_ONCE(*refcounted);
+
+	return reuse_sk;
+}
+
 static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo,
 					      struct sk_buff *skb, int doff,
 					      const __be16 sport,
@@ -85,14 +150,20 @@ static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo,
 					      int iif, int sdif,
 					      bool *refcounted)
 {
-	struct sock *sk = skb_steal_sock(skb, refcounted);
-
+	struct net *net = dev_net(skb_dst(skb)->dev);
+	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
+	struct sock *sk;
+
+	sk = inet6_steal_sock(net, skb, doff, &ip6h->saddr, sport, &ip6h->daddr, dport,
+			      refcounted, inet6_ehashfn);
+	if (IS_ERR(sk))
+		return NULL;
 	if (sk)
 		return sk;
 
-	return __inet6_lookup(dev_net(skb_dst(skb)->dev), hashinfo, skb,
-			      doff, &ipv6_hdr(skb)->saddr, sport,
-			      &ipv6_hdr(skb)->daddr, ntohs(dport),
+	return __inet6_lookup(net, hashinfo, skb,
+			      doff, &ip6h->saddr, sport,
+			      &ip6h->daddr, ntohs(dport),
 			      iif, sdif, refcounted);
 }