Merge git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf

Pablo Neira Ayuso says:

====================
Netfilter fixes for net

1) Fix incorrect TCP connection tracking window reset for non-syn
   packets, from Florian Westphal.

2) Incorrect dependency on CONFIG_NFT_FLOW_OFFLOAD, from Volodymyr Mytnyk.

3) Fix nft_socket from the output path, from Florian Westphal.

* git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf:
  netfilter: nft_socket: only do sk lookups when indev is available
  netfilter: conntrack: fix udp offload timeout sysctl
  netfilter: nf_conntrack_tcp: re-init for syn packets only
====================

Link: https://lore.kernel.org/r/20220428142109.38726-1-pablo@netfilter.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

3 files changed, 45 insertions, 30 deletions

diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index 8ec55cd72572e0..204a5cdff5b114 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -556,24 +556,14 @@ static bool tcp_in_window(struct nf_conn *ct,
 			}
 
 		}
-	} else if (((state->state == TCP_CONNTRACK_SYN_SENT
-		     && dir == IP_CT_DIR_ORIGINAL)
-		   || (state->state == TCP_CONNTRACK_SYN_RECV
-		     && dir == IP_CT_DIR_REPLY))
-		   && after(end, sender->td_end)) {
+	} else if (tcph->syn &&
+		   after(end, sender->td_end) &&
+		   (state->state == TCP_CONNTRACK_SYN_SENT ||
+		    state->state == TCP_CONNTRACK_SYN_RECV)) {
 		/*
 		 * RFC 793: "if a TCP is reinitialized ... then it need
 		 * not wait at all; it must only be sure to use sequence
 		 * numbers larger than those recently used."
-		 */
-		sender->td_end =
-		sender->td_maxend = end;
-		sender->td_maxwin = (win == 0 ? 1 : win);
-
-		tcp_options(skb, dataoff, tcph, sender);
-	} else if (tcph->syn && dir == IP_CT_DIR_REPLY &&
-		   state->state == TCP_CONNTRACK_SYN_SENT) {
-		/* Retransmitted syn-ack, or syn (simultaneous open).
 		 *
 		 * Re-init state for this direction, just like for the first
 		 * syn(-ack) reply, it might differ in seq, ack or tcp options.
@@ -581,7 +571,8 @@ static bool tcp_in_window(struct nf_conn *ct,
 		tcp_init_sender(sender, receiver,
 				skb, dataoff, tcph,
 				end, win);
-		if (!tcph->ack)
+
+		if (dir == IP_CT_DIR_REPLY && !tcph->ack)
 			return true;
 	}
 
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 3e1afd10a9b60d..55aa55b252b209 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -823,7 +823,7 @@ static struct ctl_table nf_ct_sysctl_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
 	},
-#if IS_ENABLED(CONFIG_NFT_FLOW_OFFLOAD)
+#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
 	[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD] = {
 		.procname	= "nf_flowtable_udp_timeout",
 		.maxlen		= sizeof(unsigned int),
diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c
index 6d9e8e0a3a7d26..05ae5a338b6f00 100644
--- a/net/netfilter/nft_socket.c
+++ b/net/netfilter/nft_socket.c
@@ -54,6 +54,32 @@ nft_sock_get_eval_cgroupv2(u32 *dest, struct sock *sk, const struct nft_pktinfo
 }
 #endif
 
+static struct sock *nft_socket_do_lookup(const struct nft_pktinfo *pkt)
+{
+	const struct net_device *indev = nft_in(pkt);
+	const struct sk_buff *skb = pkt->skb;
+	struct sock *sk = NULL;
+
+	if (!indev)
+		return NULL;
+
+	switch (nft_pf(pkt)) {
+	case NFPROTO_IPV4:
+		sk = nf_sk_lookup_slow_v4(nft_net(pkt), skb, indev);
+		break;
+#if IS_ENABLED(CONFIG_NF_TABLES_IPV6)
+	case NFPROTO_IPV6:
+		sk = nf_sk_lookup_slow_v6(nft_net(pkt), skb, indev);
+		break;
+#endif
+	default:
+		WARN_ON_ONCE(1);
+		break;
+	}
+
+	return sk;
+}
+
 static void nft_socket_eval(const struct nft_expr *expr,
 			    struct nft_regs *regs,
 			    const struct nft_pktinfo *pkt)
@@ -67,20 +93,7 @@ static void nft_socket_eval(const struct nft_expr *expr,
 		sk = NULL;
 
 	if (!sk)
-		switch(nft_pf(pkt)) {
-		case NFPROTO_IPV4:
-			sk = nf_sk_lookup_slow_v4(nft_net(pkt), skb, nft_in(pkt));
-			break;
-#if IS_ENABLED(CONFIG_NF_TABLES_IPV6)
-		case NFPROTO_IPV6:
-			sk = nf_sk_lookup_slow_v6(nft_net(pkt), skb, nft_in(pkt));
-			break;
-#endif
-		default:
-			WARN_ON_ONCE(1);
-			regs->verdict.code = NFT_BREAK;
-			return;
-		}
+		sk = nft_socket_do_lookup(pkt);
 
 	if (!sk) {
 		regs->verdict.code = NFT_BREAK;
@@ -224,6 +237,16 @@ static bool nft_socket_reduce(struct nft_regs_track *track,
 	return nft_expr_reduce_bitwise(track, expr);
 }
 
+static int nft_socket_validate(const struct nft_ctx *ctx,
+			       const struct nft_expr *expr,
+			       const struct nft_data **data)
+{
+	return nft_chain_validate_hooks(ctx->chain,
+					(1 << NF_INET_PRE_ROUTING) |
+					(1 << NF_INET_LOCAL_IN) |
+					(1 << NF_INET_LOCAL_OUT));
+}
+
 static struct nft_expr_type nft_socket_type;
 static const struct nft_expr_ops nft_socket_ops = {
 	.type		= &nft_socket_type,
@@ -231,6 +254,7 @@ static const struct nft_expr_ops nft_socket_ops = {
 	.eval		= nft_socket_eval,
 	.init		= nft_socket_init,
 	.dump		= nft_socket_dump,
+	.validate	= nft_socket_validate,
 	.reduce		= nft_socket_reduce,
 };