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>

3 files changed, 94 insertions, 82 deletions

diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index b64b49012655..b0e8d278e8a9 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -39,6 +39,7 @@ u32 inet6_ehashfn(const struct net *net,
 	return __inet6_ehashfn(lhash, lport, fhash, fport,
 			       inet6_ehash_secret + net_hash_mix(net));
 }
+EXPORT_SYMBOL_GPL(inet6_ehashfn);
 
 /*
  * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so
@@ -111,22 +112,40 @@ static inline int compute_score(struct sock *sk, struct net *net,
 	return score;
 }
 
-static inline struct sock *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_lookup_reuseport() - execute reuseport logic on AF_INET6 socket if necessary.
+ * @net: network namespace.
+ * @sk: AF_INET6 socket, must be in TCP_LISTEN state for TCP or TCP_CLOSE for UDP.
+ * @skb: context for a potential SK_REUSEPORT program.
+ * @doff: header offset.
+ * @saddr: source address.
+ * @sport: source port.
+ * @daddr: destination address.
+ * @hnum: destination port in host byte order.
+ * @ehashfn: hash function used to generate the fallback hash.
+ *
+ * Return: NULL if sk doesn't have SO_REUSEPORT set, otherwise a pointer to
+ *         the selected sock or an error.
+ */
+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 *reuse_sk = NULL;
 	u32 phash;
 
 	if (sk->sk_reuseport) {
-		phash = inet6_ehashfn(net, daddr, hnum, saddr, sport);
+		phash = INDIRECT_CALL_INET(ehashfn, udp6_ehashfn, inet6_ehashfn,
+					   net, daddr, hnum, saddr, sport);
 		reuse_sk = reuseport_select_sock(sk, phash, skb, doff);
 	}
 	return reuse_sk;
 }
+EXPORT_SYMBOL_GPL(inet6_lookup_reuseport);
 
 /* called with rcu_read_lock() */
 static struct sock *inet6_lhash2_lookup(struct net *net,
@@ -143,8 +162,8 @@ static struct sock *inet6_lhash2_lookup(struct net *net,
 	sk_nulls_for_each_rcu(sk, node, &ilb2->nulls_head) {
 		score = compute_score(sk, net, hnum, daddr, dif, sdif);
 		if (score > hiscore) {
-			result = lookup_reuseport(net, sk, skb, doff,
-						  saddr, sport, daddr, hnum);
+			result = inet6_lookup_reuseport(net, sk, skb, doff,
+							saddr, sport, daddr, hnum, inet6_ehashfn);
 			if (result)
 				return result;
 
@@ -156,30 +175,30 @@ static struct sock *inet6_lhash2_lookup(struct net *net,
 	return result;
 }
 
-static inline struct sock *inet6_lookup_run_bpf(struct net *net,
-						struct inet_hashinfo *hashinfo,
-						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)
+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)
 {
 	struct sock *sk, *reuse_sk;
 	bool no_reuseport;
 
-	if (hashinfo != net->ipv4.tcp_death_row.hashinfo)
-		return NULL; /* only TCP is supported */
-
-	no_reuseport = bpf_sk_lookup_run_v6(net, IPPROTO_TCP, saddr, sport,
+	no_reuseport = bpf_sk_lookup_run_v6(net, protocol, saddr, sport,
 					    daddr, hnum, dif, &sk);
 	if (no_reuseport || IS_ERR_OR_NULL(sk))
 		return sk;
 
-	reuse_sk = lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum);
+	reuse_sk = inet6_lookup_reuseport(net, sk, skb, doff,
+					  saddr, sport, daddr, hnum, ehashfn);
 	if (reuse_sk)
 		sk = reuse_sk;
 	return sk;
 }
+EXPORT_SYMBOL_GPL(inet6_lookup_run_sk_lookup);
 
 struct sock *inet6_lookup_listener(struct net *net,
 		struct inet_hashinfo *hashinfo,
@@ -193,9 +212,11 @@ struct sock *inet6_lookup_listener(struct net *net,
 	unsigned int hash2;
 
 	/* Lookup redirect from BPF */
-	if (static_branch_unlikely(&bpf_sk_lookup_enabled)) {
-		result = inet6_lookup_run_bpf(net, hashinfo, skb, doff,
-					      saddr, sport, daddr, hnum, dif);
+	if (static_branch_unlikely(&bpf_sk_lookup_enabled) &&
+	    hashinfo == net->ipv4.tcp_death_row.hashinfo) {
+		result = inet6_lookup_run_sk_lookup(net, IPPROTO_TCP, skb, doff,
+						    saddr, sport, daddr, hnum, dif,
+						    inet6_ehashfn);
 		if (result)
 			goto done;
 	}
diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
index cb4eb1d2c620..d59b296b4f51 100644
--- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
+++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
@@ -10,6 +10,7 @@
 #include <linux/module.h>
 #include <linux/skbuff.h>
 #include <linux/icmp.h>
+#include <linux/rcupdate.h>
 #include <linux/sysctl.h>
 #include <net/ipv6_frag.h>
 
@@ -96,6 +97,12 @@ static void __net_exit defrag6_net_exit(struct net *net)
 	}
 }
 
+static const struct nf_defrag_hook defrag_hook = {
+	.owner = THIS_MODULE,
+	.enable = nf_defrag_ipv6_enable,
+	.disable = nf_defrag_ipv6_disable,
+};
+
 static struct pernet_operations defrag6_net_ops = {
 	.exit = defrag6_net_exit,
 };
@@ -114,6 +121,9 @@ static int __init nf_defrag_init(void)
 		pr_err("nf_defrag_ipv6: can't register pernet ops\n");
 		goto cleanup_frag6;
 	}
+
+	rcu_assign_pointer(nf_defrag_v6_hook, &defrag_hook);
+
 	return ret;
 
 cleanup_frag6:
@@ -124,6 +134,7 @@ cleanup_frag6:
 
 static void __exit nf_defrag_fini(void)
 {
+	rcu_assign_pointer(nf_defrag_v6_hook, NULL);
 	unregister_pernet_subsys(&defrag6_net_ops);
 	nf_ct_frag6_cleanup();
 }
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 486d893b8e3c..1ea01b0d9be3 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -72,11 +72,12 @@ int udpv6_init_sock(struct sock *sk)
 	return 0;
 }
 
-static u32 udp6_ehashfn(const struct net *net,
-			const struct in6_addr *laddr,
-			const u16 lport,
-			const struct in6_addr *faddr,
-			const __be16 fport)
+INDIRECT_CALLABLE_SCOPE
+u32 udp6_ehashfn(const struct net *net,
+		 const struct in6_addr *laddr,
+		 const u16 lport,
+		 const struct in6_addr *faddr,
+		 const __be16 fport)
 {
 	static u32 udp6_ehash_secret __read_mostly;
 	static u32 udp_ipv6_hash_secret __read_mostly;
@@ -161,24 +162,6 @@ static int compute_score(struct sock *sk, struct net *net,
 	return score;
 }
 
-static struct sock *lookup_reuseport(struct net *net, struct sock *sk,
-				     struct sk_buff *skb,
-				     const struct in6_addr *saddr,
-				     __be16 sport,
-				     const struct in6_addr *daddr,
-				     unsigned int hnum)
-{
-	struct sock *reuse_sk = NULL;
-	u32 hash;
-
-	if (sk->sk_reuseport && sk->sk_state != TCP_ESTABLISHED) {
-		hash = udp6_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 *udp6_lib_lookup2(struct net *net,
 		const struct in6_addr *saddr, __be16 sport,
@@ -195,44 +178,35 @@ static struct sock *udp6_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 = inet6_lookup_reuseport(net, sk, skb, sizeof(struct udphdr),
+							saddr, sport, daddr, hnum, udp6_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(sk, net, saddr, sport,
+						daddr, hnum, dif, sdif);
 		}
 	}
 	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, 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_v6(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;
-}
-
 /* rcu_read_lock() must be held */
 struct sock *__udp6_lib_lookup(struct net *net,
 			       const struct in6_addr *saddr, __be16 sport,
@@ -257,9 +231,11 @@ struct sock *__udp6_lib_lookup(struct net *net,
 		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, dif);
+	if (static_branch_unlikely(&bpf_sk_lookup_enabled) &&
+	    udptable == net->ipv4.udp_table) {
+		sk = inet6_lookup_run_sk_lookup(net, IPPROTO_UDP, skb, sizeof(struct udphdr),
+						saddr, sport, daddr, hnum, dif,
+						udp6_ehashfn);
 		if (sk) {
 			result = sk;
 			goto done;
@@ -992,7 +968,11 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 		goto csum_error;
 
 	/* Check if the socket is already available, e.g. due to early demux */
-	sk = skb_steal_sock(skb, &refcounted);
+	sk = inet6_steal_sock(net, skb, sizeof(struct udphdr), saddr, uh->source, daddr, uh->dest,
+			      &refcounted, udp6_ehashfn);
+	if (IS_ERR(sk))
+		goto no_sk;
+
 	if (sk) {
 		struct dst_entry *dst = skb_dst(skb);
 		int ret;
@@ -1026,7 +1006,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 			goto report_csum_error;
 		return udp6_unicast_rcv_skb(sk, skb, uh);
 	}
-
+no_sk:
 	reason = SKB_DROP_REASON_NO_SOCKET;
 
 	if (!uh->check)