tcp: provide earliest departure time in skb->tstamp

Switch internal TCP skb->skb_mstamp to skb->skb_mstamp_ns,
from usec units to nsec units.

Do not clear skb->tstamp before entering IP stacks in TX,
so that qdisc or devices can implement pacing based on the
earliest departure time instead of socket sk->sk_pacing_rate

Packets are fed with tcp_wstamp_ns, and following patch
will update tcp_wstamp_ns when both TCP and sch_fq switch to
the earliest departure time mechanism.

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

1 files changed, 6 insertions, 7 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 5a8105e84f7c..957f7a0e21c0 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1014,7 +1014,7 @@ static void tcp_internal_pacing(struct sock *sk, const struct sk_buff *skb)
 
 static void tcp_update_skb_after_send(struct tcp_sock *tp, struct sk_buff *skb)
 {
-        skb->skb_mstamp = tp->tcp_mstamp;
+        skb->skb_mstamp_ns = tp->tcp_wstamp_ns;
         list_move_tail(&skb->tcp_tsorted_anchor, &tp->tsorted_sent_queue);
 }
 
@@ -1061,7 +1061,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
                 if (unlikely(!skb))
                         return -ENOBUFS;
         }
-        skb->skb_mstamp = tp->tcp_mstamp;
+        skb->skb_mstamp_ns = tp->tcp_wstamp_ns;
 
         inet = inet_sk(sk);
         tcb = TCP_SKB_CB(skb);
@@ -1165,8 +1165,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
         skb_shinfo(skb)->gso_segs = tcp_skb_pcount(skb);
         skb_shinfo(skb)->gso_size = tcp_skb_mss(skb);
 
-        /* Our usage of tstamp should remain private */
-        skb->tstamp = 0;
+        /* Leave earliest departure time in skb->tstamp (skb->skb_mstamp_ns) */
 
         /* Cleanup our debris for IP stacks */
         memset(skb->cb, 0, max(sizeof(struct inet_skb_parm),
@@ -3221,10 +3220,10 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
         memset(&opts, 0, sizeof(opts));
 #ifdef CONFIG_SYN_COOKIES
         if (unlikely(req->cookie_ts))
-                skb->skb_mstamp = cookie_init_timestamp(req);
+                skb->skb_mstamp_ns = cookie_init_timestamp(req);
         else
 #endif
-                skb->skb_mstamp = tcp_clock_us();
+                skb->skb_mstamp_ns = tcp_clock_ns();
 
 #ifdef CONFIG_TCP_MD5SIG
         rcu_read_lock();
@@ -3440,7 +3439,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 
         err = tcp_transmit_skb(sk, syn_data, 1, sk->sk_allocation);
 
-        syn->skb_mstamp = syn_data->skb_mstamp;
+        syn->skb_mstamp_ns = syn_data->skb_mstamp_ns;
 
         /* Now full SYN+DATA was cloned and sent (or not),
          * remove the SYN from the original skb (syn_data)