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, 36 insertions, 52 deletions

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 1ee9e56dc79a..3e2f29c14fa8 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -407,9 +407,9 @@ static int compute_score(struct sock *sk, struct net *net,
 	return score;
 }
 
-static u32 udp_ehashfn(const struct net *net, const __be32 laddr,
-		       const __u16 lport, const __be32 faddr,
-		       const __be16 fport)
+INDIRECT_CALLABLE_SCOPE
+u32 udp_ehashfn(const struct net *net, const __be32 laddr, const __u16 lport,
+		const __be32 faddr, const __be16 fport)
 {
 	static u32 udp_ehash_secret __read_mostly;
 
@@ -419,22 +419,6 @@ static u32 udp_ehashfn(const struct net *net, const __be32 laddr,
 			      udp_ehash_secret + net_hash_mix(net));
 }
 
-static struct sock *lookup_reuseport(struct net *net, struct sock *sk,
-				     struct sk_buff *skb,
-				     __be32 saddr, __be16 sport,
-				     __be32 daddr, unsigned short hnum)
-{
-	struct sock *reuse_sk = NULL;
-	u32 hash;
-
-	if (sk->sk_reuseport && sk->sk_state != TCP_ESTABLISHED) {
-		hash = udp_ehashfn(net, daddr, hnum, saddr, sport);
-		reuse_sk = reuseport_select_sock(sk, hash, skb,
-						 sizeof(struct udphdr));
-	}
-	return reuse_sk;
-}
-
 /* called with rcu_read_lock() */
 static struct sock *udp4_lib_lookup2(struct net *net,
 				     __be32 saddr, __be16 sport,
@@ -452,42 +436,36 @@ static struct sock *udp4_lib_lookup2(struct net *net,
 		score = compute_score(sk, net, saddr, sport,
 				      daddr, hnum, dif, sdif);
 		if (score > badness) {
-			result = lookup_reuseport(net, sk, skb,
-						  saddr, sport, daddr, hnum);
+			badness = score;
+
+			if (sk->sk_state == TCP_ESTABLISHED) {
+				result = sk;
+				continue;
+			}
+
+			result = inet_lookup_reuseport(net, sk, skb, sizeof(struct udphdr),
+						       saddr, sport, daddr, hnum, udp_ehashfn);
+			if (!result) {
+				result = sk;
+				continue;
+			}
+
 			/* Fall back to scoring if group has connections */
-			if (result && !reuseport_has_conns(sk))
+			if (!reuseport_has_conns(sk))
 				return result;
 
-			result = result ? : sk;
-			badness = score;
+			/* Reuseport logic returned an error, keep original score. */
+			if (IS_ERR(result))
+				continue;
+
+			badness = compute_score(result, net, saddr, sport,
+						daddr, hnum, dif, sdif);
+
 		}
 	}
 	return result;
 }
 
-static 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, const int dif)
-{
-	struct sock *sk, *reuse_sk;
-	bool no_reuseport;
-
-	if (udptable != net->ipv4.udp_table)
-		return NULL; /* only UDP is supported */
-
-	no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_UDP, saddr, sport,
-					    daddr, hnum, dif, &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
  */
@@ -512,9 +490,11 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
 		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, dif);
+	if (static_branch_unlikely(&bpf_sk_lookup_enabled) &&
+	    udptable == net->ipv4.udp_table) {
+		sk = inet_lookup_run_sk_lookup(net, IPPROTO_UDP, skb, sizeof(struct udphdr),
+					       saddr, sport, daddr, hnum, dif,
+					       udp_ehashfn);
 		if (sk) {
 			result = sk;
 			goto done;
@@ -2412,7 +2392,11 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	if (udp4_csum_init(skb, uh, proto))
 		goto csum_error;
 
-	sk = skb_steal_sock(skb, &refcounted);
+	sk = inet_steal_sock(net, skb, sizeof(struct udphdr), saddr, uh->source, daddr, uh->dest,
+			     &refcounted, udp_ehashfn);
+	if (IS_ERR(sk))
+		goto no_sk;
+
 	if (sk) {
 		struct dst_entry *dst = skb_dst(skb);
 		int ret;
@@ -2433,7 +2417,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
 	if (sk)
 		return udp_unicast_rcv_skb(sk, skb, uh);
-
+no_sk:
 	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
 		goto drop;
 	nf_reset_ct(skb);