tcp: make TCP_USER_TIMEOUT accurate for zero window probes

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 and builds on top of 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").

Fixes: 9721e709fa68 ("tcp: simplify window probe aborting on USER_TIMEOUT")
Signed-off-by: Enke Chen <enchen@paloaltonetworks.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20210122191306.GA99540@localhost.localdomain
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 78d13c88720fda50e3f1880ac741cea1985ef3e9..ca7e2c6cc663ee96dabc1ee01a69182ab770da22 100644 (file)
--- 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 a7dfca0a38cd7a0cdbe0a1c6d9b17866a33ebdc1..55c6fd6b5d139e0b3808ea4b44d45d6a36cbdbd7 100644 (file)
--- 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 ab458697881eda4503d6f223480deadf754d2d22..8478cf749821ade9c1abf52406634ed15be03a25 100644 (file)
--- 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 faa92948441ba28a821034f18a6e4cc252da2c99..4ef08079ccfa9d0e68f046b3cb329e7e3efdf1ff 100644 (file)
--- 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.