tcp/fq: move back to CLOCK_MONOTONIC

In the recent TCP/EDT patch series, I switched TCP and sch_fq
clocks from MONOTONIC to TAI, in order to meet the choice done
earlier for sch_etf packet scheduler.

But sure enough, this broke some setups were the TAI clock
jumps forward (by almost 50 year...), as reported
by Leonard Crestez.

If we want to converge later, we'll probably need to add
an skb field to differentiate the clock bases, or a socket option.

In the meantime, an UDP application will need to use CLOCK_MONOTONIC
base for its SCM_TXTIME timestamps if using fq packet scheduler.

Fixes: 72b0094f9182 ("tcp: switch tcp_clock_ns() to CLOCK_TAI base")
Fixes: 142537e41923 ("net_sched: sch_fq: switch to CLOCK_TAI")
Fixes: fd2bca2aa789 ("tcp: switch internal pacing timer to CLOCK_TAI")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Leonard Crestez <leonard.crestez@nxp.com>
Tested-by: Leonard Crestez <leonard.crestez@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/net/tcp.h b/include/net/tcp.h
index ff15d8e0d525715b17671e64f6abdead9df0a8f3..0d2929223c703c0aaabef0d485aabf7dc707aae1 100644 (file)
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -732,7 +732,7 @@ void tcp_send_window_probe(struct sock *sk);
 
 static inline u64 tcp_clock_ns(void)
 {
-       return ktime_get_tai_ns();
+       return ktime_get_ns();
 }
 
 static inline u64 tcp_clock_us(void)

diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 4f661e178da8465203266ff4dfa3e8743e60ff82..61023d50cd604d5e19464a32c33b65d29c75c81e 100644 (file)
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -758,7 +758,7 @@ void tcp_init_xmit_timers(struct sock *sk)
 {
        inet_csk_init_xmit_timers(sk, &tcp_write_timer, &tcp_delack_timer,
                                  &tcp_keepalive_timer);
-       hrtimer_init(&tcp_sk(sk)->pacing_timer, CLOCK_TAI,
+       hrtimer_init(&tcp_sk(sk)->pacing_timer, CLOCK_MONOTONIC,
                     HRTIMER_MODE_ABS_PINNED_SOFT);
        tcp_sk(sk)->pacing_timer.function = tcp_pace_kick;
 

diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 628a2cdcfc6f2fa69d9402f06881949d2e1423d9..338222a6c664b1825aaada4355e2fc0a01db9c73 100644 (file)
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -412,7 +412,7 @@ static void fq_check_throttled(struct fq_sched_data *q, u64 now)
 static struct sk_buff *fq_dequeue(struct Qdisc *sch)
 {
        struct fq_sched_data *q = qdisc_priv(sch);
-       u64 now = ktime_get_tai_ns();
+       u64 now = ktime_get_ns();
        struct fq_flow_head *head;
        struct sk_buff *skb;
        struct fq_flow *f;
@@ -776,7 +776,7 @@ static int fq_init(struct Qdisc *sch, struct nlattr *opt,
        q->fq_trees_log         = ilog2(1024);
        q->orphan_mask          = 1024 - 1;
        q->low_rate_threshold   = 550000 / 8;
-       qdisc_watchdog_init_clockid(&q->watchdog, sch, CLOCK_TAI);
+       qdisc_watchdog_init_clockid(&q->watchdog, sch, CLOCK_MONOTONIC);
 
        if (opt)
                err = fq_change(sch, opt, extack);
@@ -831,7 +831,7 @@ static int fq_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
        st.flows_plimit           = q->stat_flows_plimit;
        st.pkts_too_long          = q->stat_pkts_too_long;
        st.allocation_errors      = q->stat_allocation_errors;
-       st.time_next_delayed_flow = q->time_next_delayed_flow - ktime_get_tai_ns();
+       st.time_next_delayed_flow = q->time_next_delayed_flow - ktime_get_ns();
        st.flows                  = q->flows;
        st.inactive_flows         = q->inactive_flows;
        st.throttled_flows        = q->throttled_flows;