[PATCH net v2] tcp: fix TCP_USER_TIMEOUT with zero window

[Enke Chen]

From: Enke Chen <enchen@xxxxxxxxxxxxxxxxxxxx>

The TCP session does not terminate with TCP_USER_TIMEOUT when data
remain untransmitted due to zero window.

The number of unanswered zero-window probes (tcp_probes_out) is
reset to zero with incoming acks irrespective of the window size,
as described in tcp_probe_timer():

    RFC 1122 4.2.2.17 requires the sender to stay open indefinitely
    as long as the receiver continues to respond probes. We support
    this by default and reset icsk_probes_out with incoming ACKs.

This counter, however, is the wrong one to be used in calculating the
duration that the window remains closed and data remain untransmitted.
Thanks to Jonathan Maxwell <jmaxwell37@xxxxxxxxx> for diagnosing the
actual issue.

In this patch a new timestamp is introduced for the socket in order to
track the elapsed time for the zero-window probes that have not been
answered with any non-zero window ack.

Fixes: 9721e709fa68 ("tcp: simplify window probe aborting on USER_TIMEOUT")
Reported-by: William McCall <william.mccall@xxxxxxxxx>
Co-developed-by: Neal Cardwell <ncardwell@xxxxxxxxxx>
Signed-off-by: Neal Cardwell <ncardwell@xxxxxxxxxx>
Signed-off-by: Enke Chen <enchen@xxxxxxxxxxxxxxxxxxxx>
Reviewed-by: Yuchung Cheng <ycheng@xxxxxxxxxx>
Reviewed-by: Eric Dumazet <edumazet@xxxxxxxxxx>
---
 include/net/inet_connection_sock.h |  3 +++
 net/ipv4/inet_connection_sock.c    |  1 +
 net/ipv4/tcp.c                     |  1 +
 net/ipv4/tcp_input.c               |  1 +
 net/ipv4/tcp_output.c              |  1 +
 net/ipv4/tcp_timer.c               | 14 +++++++-------
 6 files changed, 14 insertions(+), 7 deletions(-)

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 7338b3865a2a..111d7771b208 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -76,6 +76,8 @@ struct inet_connection_sock_af_ops {
  * @icsk_ext_hdr_len:	   Network protocol overhead (IP/IPv6 options)
  * @icsk_ack:		   Delayed ACK control data
  * @icsk_mtup;		   MTU probing control data
+ * @icsk_probes_tstamp:    Probe timestamp (cleared by non-zero window ack)
+ * @icsk_user_timeout:	   TCP_USER_TIMEOUT value
  */
 struct inet_connection_sock {
 	/* inet_sock has to be the first member! */
@@ -129,6 +131,7 @@ struct inet_connection_sock {
 
 		u32		  probe_timestamp;
 	} icsk_mtup;
+	u32			  icsk_probes_tstamp;
 	u32			  icsk_user_timeout;
 
 	u64			  icsk_ca_priv[104 / sizeof(u64)];
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index fd8b8800a2c3..6bd7ca09af03 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -851,6 +851,7 @@ struct sock *inet_csk_clone_lock(const struct sock *sk,
 		newicsk->icsk_retransmits = 0;
 		newicsk->icsk_backoff	  = 0;
 		newicsk->icsk_probes_out  = 0;
+		newicsk->icsk_probes_tstamp = 0;
 
 		/* Deinitialize accept_queue to trap illegal accesses. */
 		memset(&newicsk->icsk_accept_queue, 0, sizeof(newicsk->icsk_accept_queue));
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index ed42d2193c5c..32545ecf2ab1 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2937,6 +2937,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 
 	icsk->icsk_backoff = 0;
 	icsk->icsk_probes_out = 0;
+	icsk->icsk_probes_tstamp = 0;
 	icsk->icsk_rto = TCP_TIMEOUT_INIT;
 	icsk->icsk_rto_min = TCP_RTO_MIN;
 	icsk->icsk_delack_max = TCP_DELACK_MAX;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index c7e16b0ed791..bafcab75f425 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3384,6 +3384,7 @@ static void tcp_ack_probe(struct sock *sk)
 		return;
 	if (!after(TCP_SKB_CB(head)->end_seq, tcp_wnd_end(tp))) {
 		icsk->icsk_backoff = 0;
+		icsk->icsk_probes_tstamp = 0;
 		inet_csk_clear_xmit_timer(sk, ICSK_TIME_PROBE0);
 		/* Socket must be waked up by subsequent tcp_data_snd_check().
 		 * This function is not for random using!
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index f322e798a351..ab458697881e 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -4084,6 +4084,7 @@ void tcp_send_probe0(struct sock *sk)
 		/* Cancel probe timer, if it is not required. */
 		icsk->icsk_probes_out = 0;
 		icsk->icsk_backoff = 0;
+		icsk->icsk_probes_tstamp = 0;
 		return;
 	}
 
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 6c62b9ea1320..454732ecc8f3 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -349,6 +349,7 @@ static void tcp_probe_timer(struct sock *sk)
 
 	if (tp->packets_out || !skb) {
 		icsk->icsk_probes_out = 0;
+		icsk->icsk_probes_tstamp = 0;
 		return;
 	}
 
@@ -360,13 +361,12 @@ static void tcp_probe_timer(struct sock *sk)
 	 * corresponding system limit. We also implement similar policy when
 	 * we use RTO to probe window in tcp_retransmit_timer().
 	 */
-	if (icsk->icsk_user_timeout) {
-		u32 elapsed = tcp_model_timeout(sk, icsk->icsk_probes_out,
-						tcp_probe0_base(sk));
-
-		if (elapsed >= icsk->icsk_user_timeout)
-			goto abort;
-	}
+	if (!icsk->icsk_probes_tstamp)
+		icsk->icsk_probes_tstamp = tcp_jiffies32;
+	else if (icsk->icsk_user_timeout &&
+		 (s32)(tcp_jiffies32 - icsk->icsk_probes_tstamp) >=
+		 msecs_to_jiffies(icsk->icsk_user_timeout))
+		goto abort;
 
 	max_probes = sock_net(sk)->ipv4.sysctl_tcp_retries2;
 	if (sock_flag(sk, SOCK_DEAD)) {
-- 
2.29.2