Commit 5f6188a8 authored by Eric Dumazet's avatar Eric Dumazet Committed by David S. Miller
Browse files

tcp: do not change tcp_wstamp_ns in tcp_mstamp_refresh 



In EDT design, I made the mistake of using tcp_wstamp_ns
to store the last tcp_clock_ns() sample and to store the
pacing virtual timer.

This causes major regressions at high speed flows.

Introduce tcp_clock_cache to store last tcp_clock_ns().
This is needed because some arches have slow high-resolution
kernel time service.

tcp_wstamp_ns is only updated when a packet is sent.

Note that we can remove tcp_mstamp in the future since
tcp_mstamp is essentially tcp_clock_cache/1000, so the
apparent socket size increase is temporary.

Fixes: 9799ccb0 ("tcp: add tcp_wstamp_ns socket field")
Signed-off-by: default avatarEric Dumazet <edumazet@google.com>
Acked-by: default avatarSoheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent 1a3aea25

include/linux/tcp.h

+1 −0
Original line number Diff line number Diff line
@@ -249,6 +249,7 @@ struct tcp_sock { 
	u32	tlp_high_seq;	/* snd_nxt at the time of TLP retransmit. */



	u64	tcp_wstamp_ns;	/* departure time for next sent data packet */

	u64	tcp_clock_cache; /* cache last tcp_clock_ns() (see tcp_mstamp_refresh()) */



/* RTT measurement */

	u64	tcp_mstamp;	/* most recent packet received/sent */

net/ipv4/tcp_output.c

+6 −3
Original line number Diff line number Diff line
@@ -52,9 +52,8 @@ void tcp_mstamp_refresh(struct tcp_sock *tp) 
{

	u64 val = tcp_clock_ns();



	/* departure time for next data packet */

	if (val > tp->tcp_wstamp_ns)

		tp->tcp_wstamp_ns = val;

	if (val > tp->tcp_clock_cache)

		tp->tcp_clock_cache = val;



	val = div_u64(val, NSEC_PER_USEC);

	if (val > tp->tcp_mstamp)
@@ -1050,6 +1049,10 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, 
		if (unlikely(!skb))

			return -ENOBUFS;

	}



	/* TODO: might take care of jitter here */

	tp->tcp_wstamp_ns = max(tp->tcp_wstamp_ns, tp->tcp_clock_cache);



	skb->skb_mstamp_ns = tp->tcp_wstamp_ns;



	inet = inet_sk(sk);

net/ipv4/tcp_timer.c

+1 −1
Original line number Diff line number Diff line
@@ -360,7 +360,7 @@ static void tcp_probe_timer(struct sock *sk) 
	 */

	start_ts = tcp_skb_timestamp(skb);

	if (!start_ts)

		skb->skb_mstamp_ns = tp->tcp_wstamp_ns;

		skb->skb_mstamp_ns = tp->tcp_clock_cache;

	else if (icsk->icsk_user_timeout &&

		 (s32)(tcp_time_stamp(tp) - start_ts) > icsk->icsk_user_timeout)

		goto abort;

CRA Git | Maintained and supported by SUSTech CRA and CCSE