Merge branch 'tcp-ts-usec-resolution'

Eric Dumazet says:

====================
tcp: add optional usec resolution to TCP TS

As discussed in various public places in 2016, Google adopted
usec resolution in RFC 7323 TS values, at Van Jacobson suggestion.

Goals were :

1) better observability of delays in networking stacks/fabrics.

2) better disambiguation of events based on TSval/ecr values.

3) building block for congestion control modules needing usec resolution.

Back then we implemented a schem based on private SYN options
to safely negotiate the feature.

For upstream submission, we chose to use a much simpler route
attribute because this feature is probably going to be used
in private networks.

ip route add 10/8 ... features tcp_usec_ts

References:

https://www.ietf.org/proceedings/97/slides/slides-97-tcpm-tcp-options-for-low-latency-00.pdf
https://datatracker.ietf.org/doc/draft-wang-tcpm-low-latency-opt/

First two patches are fixing old minor bugs and might be taken
by stable teams (thanks to appropriate Fixes: tags)
====================

Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 18 insertions, 8 deletions

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 56a8d936000f..a86d8200a1e8 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3629,10 +3629,16 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 			tp->fastopen_no_cookie = val;
 		break;
 	case TCP_TIMESTAMP:
-		if (!tp->repair)
+		if (!tp->repair) {
 			err = -EPERM;
-		else
-			WRITE_ONCE(tp->tsoffset, val - tcp_time_stamp_raw());
+			break;
+		}
+		/* val is an opaque field,
+		 * and low order bit contains usec_ts enable bit.
+		 * Its a best effort, and we do not care if user makes an error.
+		 */
+		tp->tcp_usec_ts = val & 1;
+		WRITE_ONCE(tp->tsoffset, val - tcp_clock_ts(tp->tcp_usec_ts));
 		break;
 	case TCP_REPAIR_WINDOW:
 		err = tcp_repair_set_window(tp, optval, optlen);
@@ -3754,6 +3760,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 		info->tcpi_options |= TCPI_OPT_ECN_SEEN;
 	if (tp->syn_data_acked)
 		info->tcpi_options |= TCPI_OPT_SYN_DATA;
+	if (tp->tcp_usec_ts)
+		info->tcpi_options |= TCPI_OPT_USEC_TS;
 
 	info->tcpi_rto = jiffies_to_usecs(icsk->icsk_rto);
 	info->tcpi_ato = jiffies_to_usecs(min_t(u32, icsk->icsk_ack.ato,
@@ -3817,10 +3825,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	info->tcpi_total_rto = tp->total_rto;
 	info->tcpi_total_rto_recoveries = tp->total_rto_recoveries;
 	info->tcpi_total_rto_time = tp->total_rto_time;
-	if (tp->rto_stamp) {
-		info->tcpi_total_rto_time += tcp_time_stamp_raw() -
-						tp->rto_stamp;
-	}
+	if (tp->rto_stamp)
+		info->tcpi_total_rto_time += tcp_clock_ms() - tp->rto_stamp;
 
 	unlock_sock_fast(sk, slow);
 }
@@ -4145,7 +4151,11 @@ int do_tcp_getsockopt(struct sock *sk, int level,
 		break;
 
 	case TCP_TIMESTAMP:
-		val = tcp_time_stamp_raw() + READ_ONCE(tp->tsoffset);
+		val = tcp_clock_ts(tp->tcp_usec_ts) + READ_ONCE(tp->tsoffset);
+		if (tp->tcp_usec_ts)
+			val |= 1;
+		else
+			val &= ~1;
 		break;
 	case TCP_NOTSENT_LOWAT:
 		val = READ_ONCE(tp->notsent_lowat);