1 files changed, 43 insertions, 37 deletions

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 0ce52d46e4f8..075ee8a2df3b 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -72,7 +72,7 @@ static void	tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb);
 static void	tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
 				      struct request_sock *req);
 
-static int	tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb);
+INDIRECT_CALLABLE_SCOPE int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb);
 
 static const struct inet_connection_sock_af_ops ipv6_mapped;
 const struct inet_connection_sock_af_ops ipv6_specific;
@@ -107,9 +107,9 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
 	if (dst && dst_hold_safe(dst)) {
 		const struct rt6_info *rt = (const struct rt6_info *)dst;
 
-		sk->sk_rx_dst = dst;
-		inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
-		tcp_inet6_sk(sk)->rx_dst_cookie = rt6_get_cookie(rt);
+		rcu_assign_pointer(sk->sk_rx_dst, dst);
+		sk->sk_rx_dst_ifindex = skb->skb_iif;
+		sk->sk_rx_dst_cookie = rt6_get_cookie(rt);
 	}
 }
 
@@ -414,9 +414,12 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	if (sk->sk_state == TCP_CLOSE)
 		goto out;
 
-	if (ipv6_hdr(skb)->hop_limit < tcp_inet6_sk(sk)->min_hopcount) {
-		__NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP);
-		goto out;
+	if (static_branch_unlikely(&ip6_min_hopcount)) {
+		/* min_hopcount can be changed concurrently from do_ipv6_setsockopt() */
+		if (ipv6_hdr(skb)->hop_limit < READ_ONCE(tcp_inet6_sk(sk)->min_hopcount)) {
+			__NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP);
+			goto out;
+		}
 	}
 
 	tp = tcp_sk(sk);
@@ -569,7 +572,7 @@ done:
 static void tcp_v6_reqsk_destructor(struct request_sock *req)
 {
 	kfree(inet_rsk(req)->ipv6_opt);
-	kfree_skb(inet_rsk(req)->pktopts);
+	consume_skb(inet_rsk(req)->pktopts);
 }
 
 #ifdef CONFIG_TCP_MD5SIG
@@ -599,6 +602,7 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, int optname,
 	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&cmd.tcpm_addr;
 	int l3index = 0;
 	u8 prefixlen;
+	u8 flags;
 
 	if (optlen < sizeof(cmd))
 		return -EINVAL;
@@ -609,6 +613,8 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, int optname,
 	if (sin6->sin6_family != AF_INET6)
 		return -EINVAL;
 
+	flags = cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX;
+
 	if (optname == TCP_MD5SIG_EXT &&
 	    cmd.tcpm_flags & TCP_MD5SIG_FLAG_PREFIX) {
 		prefixlen = cmd.tcpm_prefixlen;
@@ -619,7 +625,7 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, int optname,
 		prefixlen = ipv6_addr_v4mapped(&sin6->sin6_addr) ? 32 : 128;
 	}
 
-	if (optname == TCP_MD5SIG_EXT &&
+	if (optname == TCP_MD5SIG_EXT && cmd.tcpm_ifindex &&
 	    cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX) {
 		struct net_device *dev;
 
@@ -640,9 +646,9 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, int optname,
 		if (ipv6_addr_v4mapped(&sin6->sin6_addr))
 			return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3],
 					      AF_INET, prefixlen,
-					      l3index);
+					      l3index, flags);
 		return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr,
-				      AF_INET6, prefixlen, l3index);
+				      AF_INET6, prefixlen, l3index, flags);
 	}
 
 	if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN)
@@ -650,12 +656,12 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, int optname,
 
 	if (ipv6_addr_v4mapped(&sin6->sin6_addr))
 		return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3],
-				      AF_INET, prefixlen, l3index,
+				      AF_INET, prefixlen, l3index, flags,
 				      cmd.tcpm_key, cmd.tcpm_keylen,
 				      GFP_KERNEL);
 
 	return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr,
-			      AF_INET6, prefixlen, l3index,
+			      AF_INET6, prefixlen, l3index, flags,
 			      cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL);
 }
 
@@ -963,7 +969,6 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
 	fl6.flowlabel = label;
 
 	buff->ip_summed = CHECKSUM_PARTIAL;
-	buff->csum = 0;
 
 	__tcp_v6_send_check(buff, &fl6.saddr, &fl6.daddr);
 
@@ -1258,7 +1263,6 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 
 		inet_sk(newsk)->pinet6 = tcp_inet6_sk(newsk);
 
-		newinet = inet_sk(newsk);
 		newnp = tcp_inet6_sk(newsk);
 		newtp = tcp_sk(newsk);
 
@@ -1404,7 +1408,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 		 * across. Shucks.
 		 */
 		tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newsk->sk_v6_daddr,
-			       AF_INET6, 128, l3index, key->key, key->keylen,
+			       AF_INET6, 128, l3index, key->flags, key->key, key->keylen,
 			       sk_gfp_mask(sk, GFP_ATOMIC));
 	}
 #endif
@@ -1462,7 +1466,8 @@ INDIRECT_CALLABLE_DECLARE(struct dst_entry *ipv4_dst_check(struct dst_entry *,
  * This is because we cannot sleep with the original spinlock
  * held.
  */
-static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
+INDIRECT_CALLABLE_SCOPE
+int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
 {
 	struct ipv6_pinfo *np = tcp_inet6_sk(sk);
 	struct sk_buff *opt_skb = NULL;
@@ -1501,16 +1506,19 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
 		opt_skb = skb_clone(skb, sk_gfp_mask(sk, GFP_ATOMIC));
 
 	if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
-		struct dst_entry *dst = sk->sk_rx_dst;
+		struct dst_entry *dst;
+
+		dst = rcu_dereference_protected(sk->sk_rx_dst,
+						lockdep_sock_is_held(sk));
 
 		sock_rps_save_rxhash(sk, skb);
 		sk_mark_napi_id(sk, skb);
 		if (dst) {
-			if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif ||
+			if (sk->sk_rx_dst_ifindex != skb->skb_iif ||
 			    INDIRECT_CALL_1(dst->ops->check, ip6_dst_check,
-					    dst, np->rx_dst_cookie) == NULL) {
+					    dst, sk->sk_rx_dst_cookie) == NULL) {
+				RCU_INIT_POINTER(sk->sk_rx_dst, NULL);
 				dst_release(dst);
-				sk->sk_rx_dst = NULL;
 			}
 		}
 
@@ -1588,7 +1596,7 @@ ipv6_pktoptions:
 		}
 	}
 
-	kfree_skb(opt_skb);
+	consume_skb(opt_skb);
 	return 0;
 }
 
@@ -1618,7 +1626,6 @@ static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr,
 
 INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb)
 {
-	struct sk_buff *skb_to_free;
 	int sdif = inet6_sdif(skb);
 	int dif = inet6_iif(skb);
 	const struct tcphdr *th;
@@ -1724,9 +1731,13 @@ process:
 			return 0;
 		}
 	}
-	if (hdr->hop_limit < tcp_inet6_sk(sk)->min_hopcount) {
-		__NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP);
-		goto discard_and_relse;
+
+	if (static_branch_unlikely(&ip6_min_hopcount)) {
+		/* min_hopcount can be changed concurrently from do_ipv6_setsockopt() */
+		if (hdr->hop_limit < READ_ONCE(tcp_inet6_sk(sk)->min_hopcount)) {
+			__NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP);
+			goto discard_and_relse;
+		}
 	}
 
 	if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb))
@@ -1750,21 +1761,17 @@ process:
 
 	sk_incoming_cpu_update(sk);
 
+	sk_defer_free_flush(sk);
 	bh_lock_sock_nested(sk);
 	tcp_segs_in(tcp_sk(sk), skb);
 	ret = 0;
 	if (!sock_owned_by_user(sk)) {
-		skb_to_free = sk->sk_rx_skb_cache;
-		sk->sk_rx_skb_cache = NULL;
 		ret = tcp_v6_do_rcv(sk, skb);
 	} else {
 		if (tcp_add_backlog(sk, skb))
 			goto discard_and_relse;
-		skb_to_free = NULL;
 	}
 	bh_unlock_sock(sk);
-	if (skb_to_free)
-		__kfree_skb(skb_to_free);
 put_and_return:
 	if (refcounted)
 		sock_put(sk);
@@ -1872,12 +1879,12 @@ INDIRECT_CALLABLE_SCOPE void tcp_v6_early_demux(struct sk_buff *skb)
 		skb->sk = sk;
 		skb->destructor = sock_edemux;
 		if (sk_fullsock(sk)) {
-			struct dst_entry *dst = READ_ONCE(sk->sk_rx_dst);
+			struct dst_entry *dst = rcu_dereference(sk->sk_rx_dst);
 
 			if (dst)
-				dst = dst_check(dst, tcp_inet6_sk(sk)->rx_dst_cookie);
+				dst = dst_check(dst, sk->sk_rx_dst_cookie);
 			if (dst &&
-			    inet_sk(sk)->rx_dst_ifindex == skb->skb_iif)
+			    sk->sk_rx_dst_ifindex == skb->skb_iif)
 				skb_dst_set_noref(skb, dst);
 		}
 	}
@@ -1891,9 +1898,7 @@ static struct timewait_sock_ops tcp6_timewait_sock_ops = {
 
 INDIRECT_CALLABLE_SCOPE void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb)
 {
-	struct ipv6_pinfo *np = inet6_sk(sk);
-
-	__tcp_v6_send_check(skb, &np->saddr, &sk->sk_v6_daddr);
+	__tcp_v6_send_check(skb, &sk->sk_v6_rcv_saddr, &sk->sk_v6_daddr);
 }
 
 const struct inet_connection_sock_af_ops ipv6_specific = {
@@ -2176,6 +2181,7 @@ struct proto tcpv6_prot = {
 	.hash			= inet6_hash,
 	.unhash			= inet_unhash,
 	.get_port		= inet_csk_get_port,
+	.put_port		= inet_put_port,
 #ifdef CONFIG_BPF_SYSCALL
 	.psock_update_sk_prot	= tcp_bpf_update_proto,
 #endif