tcp: address problems caused by EDT misshaps

When a qdisc setup including pacing FQ is dismantled and recreated,
some TCP packets are sent earlier than instructed by TCP stack.

TCP can be fooled when ACK comes back, because the following
operation can return a negative value.

    tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr;

Some paths in TCP stack were not dealing properly with this,
this patch addresses four of them.

Fixes: ab408b6dc7 ("tcp: switch tcp and sch_fq to new earliest departure time model")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Eric Dumazet 2018-11-24 09:12:24 -08:00 committed by David S. Miller
parent d146194f31
commit 9efdda4e3a
2 changed files with 16 additions and 10 deletions

View File

@ -579,10 +579,12 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk,
u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr;
u32 delta_us;
if (!delta)
delta = 1;
delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
tcp_rcv_rtt_update(tp, delta_us, 0);
if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) {
if (!delta)
delta = 1;
delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
tcp_rcv_rtt_update(tp, delta_us, 0);
}
}
}
@ -2910,9 +2912,11 @@ static bool tcp_ack_update_rtt(struct sock *sk, const int flag,
if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr &&
flag & FLAG_ACKED) {
u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr;
u32 delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
seq_rtt_us = ca_rtt_us = delta_us;
if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) {
seq_rtt_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
ca_rtt_us = seq_rtt_us;
}
}
rs->rtt_us = ca_rtt_us; /* RTT of last (S)ACKed packet (or -1) */
if (seq_rtt_us < 0)

View File

@ -40,15 +40,17 @@ static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
u32 elapsed, start_ts;
s32 remaining;
start_ts = tcp_retransmit_stamp(sk);
if (!icsk->icsk_user_timeout || !start_ts)
return icsk->icsk_rto;
elapsed = tcp_time_stamp(tcp_sk(sk)) - start_ts;
if (elapsed >= icsk->icsk_user_timeout)
remaining = icsk->icsk_user_timeout - elapsed;
if (remaining <= 0)
return 1; /* user timeout has passed; fire ASAP */
else
return min_t(u32, icsk->icsk_rto, msecs_to_jiffies(icsk->icsk_user_timeout - elapsed));
return min_t(u32, icsk->icsk_rto, msecs_to_jiffies(remaining));
}
/**
@ -209,7 +211,7 @@ static bool retransmits_timed_out(struct sock *sk,
(boundary - linear_backoff_thresh) * TCP_RTO_MAX;
timeout = jiffies_to_msecs(timeout);
}
return (tcp_time_stamp(tcp_sk(sk)) - start_ts) >= timeout;
return (s32)(tcp_time_stamp(tcp_sk(sk)) - start_ts - timeout) >= 0;
}
/* A write timeout has occurred. Process the after effects. */