net: Find dst with sk's xfrm policy not ctl_sk

If we set XFRM security policy by calling setsockopt with option
IPV6_XFRM_POLICY, the policy will be stored in 'sock_policy' in 'sock'
struct. However tcp_v6_send_response doesn't look up dst_entry with the
actual socket but looks up with tcp control socket. This may cause a
problem that a RST packet is sent without ESP encryption & peer's TCP
socket can't receive it.
This patch will make the function look up dest_entry with actual socket,
if the socket has XFRM policy(sock_policy), so that the TCP response
packet via this function can be encrypted, & aligned on the encrypted
TCP socket.

Tested: We encountered this problem when a TCP socket which is encrypted
in ESP transport mode encryption, receives challenge ACK at SYN_SENT
state. After receiving challenge ACK, TCP needs to send RST to
establish the socket at next SYN try. But the RST was not encrypted &
peer TCP socket still remains on ESTABLISHED state.
So we verified this with test step as below.
[Test step]
1. Making a TCP state mismatch between client(IDLE) & server(ESTABLISHED).
2. Client tries a new connection on the same TCP ports(src & dst).
3. Server will return challenge ACK instead of SYN,ACK.
4. Client will send RST to server to clear the SOCKET.
5. Client will retransmit SYN to server on the same TCP ports.
[Expected result]
The TCP connection should be established.

Cc: Maciej Żenczykowski <maze@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Cc: Sehee Lee <seheele@google.com>
Signed-off-by: Sewook Seo <sewookseo@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 9 insertions, 2 deletions

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 9287712ad977..67b799ef5f67 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1195,6 +1195,8 @@ int __xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk);
 
 static inline int xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk)
 {
+	if (!sk_fullsock(osk))
+		return 0;
 	sk->sk_policy[0] = NULL;
 	sk->sk_policy[1] = NULL;
 	if (unlikely(osk->sk_policy[0] || osk->sk_policy[1]))
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 5e32a2f86fbd..f7156845ddf7 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1700,7 +1700,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 			   tcp_hdr(skb)->source, tcp_hdr(skb)->dest,
 			   arg->uid);
 	security_skb_classify_flow(skb, flowi4_to_flowi_common(&fl4));
-	rt = ip_route_output_key(net, &fl4);
+	rt = ip_route_output_flow(net, &fl4, sk);
 	if (IS_ERR(rt))
 		return;
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 68d0d8a008e2..228d36692d08 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -819,6 +819,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 		ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ?
 				   inet_twsk(sk)->tw_priority : sk->sk_priority;
 		transmit_time = tcp_transmit_time(sk);
+		xfrm_sk_clone_policy(ctl_sk, sk);
 	}
 	ip_send_unicast_reply(ctl_sk,
 			      skb, &TCP_SKB_CB(skb)->header.h4.opt,
@@ -827,6 +828,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 			      transmit_time);
 
 	ctl_sk->sk_mark = 0;
+	xfrm_sk_free_policy(ctl_sk);
 	sock_net_set(ctl_sk, &init_net);
 	__TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
 	__TCP_INC_STATS(net, TCP_MIB_OUTRSTS);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index c72448ba6dc9..70d4890d8d2f 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -952,7 +952,10 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
 	 * Underlying function will use this to retrieve the network
 	 * namespace
 	 */
-	dst = ip6_dst_lookup_flow(sock_net(ctl_sk), ctl_sk, &fl6, NULL);
+	if (sk && sk->sk_state != TCP_TIME_WAIT)
+		dst = ip6_dst_lookup_flow(net, sk, &fl6, NULL); /*sk's xfrm_policy can be referred*/
+	else
+		dst = ip6_dst_lookup_flow(net, ctl_sk, &fl6, NULL);
 	if (!IS_ERR(dst)) {
 		skb_dst_set(buff, dst);
 		ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL,