[PATCH net] tcp: make TCP_USER_TIMEOUT accurate for zero window probes

[Enke Chen]

From: Enke Chen <enchen@xxxxxxxxxxxxxxxxxxxx>

The TCP_USER_TIMEOUT is checked by the 0-window probe timer. As the
timer has backoff with a max interval of about two minutes, the
actual timeout for TCP_USER_TIMEOUT can be off by up to two minutes.

In this patch the TCP_USER_TIMEOUT is made more accurate by taking it
into account when computing the timer value for the 0-window probes.

This patch is similar to the one that made TCP_USER_TIMEOUT accurate for
RTOs in commit b701a99e431d ("tcp: Add tcp_clamp_rto_to_user_timeout()
helper to improve accuracy").

Signed-off-by: Enke Chen <enchen@xxxxxxxxxxxxxxxxxxxx>
Reviewed-by: Neal Cardwell <ncardwell@xxxxxxxxxx>
---
 include/net/tcp.h     |  1 +
 net/ipv4/tcp_input.c  |  4 ++--
 net/ipv4/tcp_output.c |  2 ++
 net/ipv4/tcp_timer.c  | 18 ++++++++++++++++++
 4 files changed, 23 insertions(+), 2 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 78d13c88720f..ca7e2c6cc663 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -630,6 +630,7 @@ static inline void tcp_clear_xmit_timers(struct sock *sk)
 
 unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu);
 unsigned int tcp_current_mss(struct sock *sk);
+u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when);
 
 /* Bound MSS / TSO packet size with the half of the window */
 static inline int tcp_bound_to_half_wnd(struct tcp_sock *tp, int pktsize)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index bafcab75f425..4923cdbea95a 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3392,8 +3392,8 @@ static void tcp_ack_probe(struct sock *sk)
 	} else {
 		unsigned long when = tcp_probe0_when(sk, TCP_RTO_MAX);
 
-		tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
-				     when, TCP_RTO_MAX);
+		when = tcp_clamp_probe0_to_user_timeout(sk, when);
+		tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, when, TCP_RTO_MAX);
 	}
 }
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index ab458697881e..8478cf749821 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -4099,6 +4099,8 @@ void tcp_send_probe0(struct sock *sk)
 		 */
 		timeout = TCP_RESOURCE_PROBE_INTERVAL;
 	}
+
+	timeout = tcp_clamp_probe0_to_user_timeout(sk, timeout);
 	tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, timeout, TCP_RTO_MAX);
 }
 
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 454732ecc8f3..90722e30ad90 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -40,6 +40,24 @@ static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk)
 	return min_t(u32, icsk->icsk_rto, msecs_to_jiffies(remaining));
 }
 
+u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+	u32 remaining;
+	s32 elapsed;
+
+	if (!icsk->icsk_user_timeout || !icsk->icsk_probes_tstamp)
+		return when;
+
+	elapsed = tcp_jiffies32 - icsk->icsk_probes_tstamp;
+	if (unlikely(elapsed < 0))
+		elapsed = 0;
+	remaining = msecs_to_jiffies(icsk->icsk_user_timeout) - elapsed;
+	remaining = max_t(u32, remaining, TCP_TIMEOUT_MIN);
+
+	return min_t(u32, remaining, when);
+}
+
 /**
  *  tcp_write_err() - close socket and save error info
  *  @sk:  The socket the error has appeared on.
-- 
2.29.2