tcp: switch TCP TS option (RFC 7323) to 1ms clock

TCP Timestamps option is defined in RFC 7323

Traditionally on linux, it has been tied to the internal
'jiffies' variable, because it had been a cheap and good enough
generator.

For TCP flows on the Internet, 1 ms resolution would be much better
than 4ms or 10ms (HZ=250 or HZ=100 respectively)

For TCP flows in the DC, Google has used usec resolution for more
than two years with great success [1]

Receive size autotuning (DRS) is indeed more precise and converges
faster to optimal window size.

This patch converts tp->tcp_mstamp to a plain u64 value storing
a 1 usec TCP clock.

This choice will allow us to upstream the 1 usec TS option as
discussed in IETF 97.

[1] https://www.ietf.org/proceedings/97/slides/slides-97-tcpm-tcp-options-for-low-latency-00.pdf

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 9 insertions, 8 deletions

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index d8fe25db79f2..191b2f78b19d 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -376,8 +376,9 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
         struct sock *sk;
         struct sk_buff *skb;
         struct request_sock *fastopen;
-        __u32 seq, snd_una;
-        __u32 remaining;
+        u32 seq, snd_una;
+        s32 remaining;
+        u32 delta_us;
         int err;
         struct net *net = dev_net(icmp_skb->dev);
 
@@ -483,12 +484,12 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
                 skb = tcp_write_queue_head(sk);
                 BUG_ON(!skb);
 
-                skb_mstamp_get(&tp->tcp_mstamp);
+                tcp_mstamp_refresh(tp);
+                delta_us = (u32)(tp->tcp_mstamp - skb->skb_mstamp);
                 remaining = icsk->icsk_rto -
-                            min(icsk->icsk_rto,
-                                tcp_time_stamp - tcp_skb_timestamp(skb));
+                            usecs_to_jiffies(delta_us);
 
-                if (remaining) {
+                if (remaining > 0) {
                         inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
                                                   remaining, TCP_RTO_MAX);
                 } else {
@@ -812,7 +813,7 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
         tcp_v4_send_ack(sk, skb,
                         tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
                         tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
-                        tcp_time_stamp + tcptw->tw_ts_offset,
+                        tcp_time_stamp_raw() + tcptw->tw_ts_offset,
                         tcptw->tw_ts_recent,
                         tw->tw_bound_dev_if,
                         tcp_twsk_md5_key(tcptw),
@@ -840,7 +841,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
         tcp_v4_send_ack(sk, skb, seq,
                         tcp_rsk(req)->rcv_nxt,
                         req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale,
-                        tcp_time_stamp + tcp_rsk(req)->ts_off,
+                        tcp_time_stamp_raw() + tcp_rsk(req)->ts_off,
                         req->ts_recent,
                         0,
                         tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->daddr,