tcp: allow congestion control to expand send buffer differently

Currently the TCP send buffer expands to twice cwnd, in order to allow
limited transmits in the CA_Recovery state. This assumes that cwnd
does not increase in the CA_Recovery.

For some congestion control algorithms, like the upcoming BBR module,
if the losses in recovery do not indicate congestion then we may
continue to raise cwnd multiplicatively in recovery. In such cases the
current multiplier will falsely limit the sending rate, much as if it
were limited by the application.

This commit adds an optional congestion control callback to use a
different multiplier to expand the TCP send buffer. For congestion
control modules that do not specificy this callback, TCP continues to
use the previous default of 2.

Signed-off-by: Van Jacobson <vanj@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Nandita Dukkipati <nanditad@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 3 insertions, 1 deletions

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index d9ed4bb96f74..13a2e70141f5 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -289,6 +289,7 @@ static bool tcp_ecn_rcv_ecn_echo(const struct tcp_sock *tp, const struct tcphdr
 static void tcp_sndbuf_expand(struct sock *sk)
 {
         const struct tcp_sock *tp = tcp_sk(sk);
+        const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops;
         int sndmem, per_mss;
         u32 nr_segs;
 
@@ -309,7 +310,8 @@ static void tcp_sndbuf_expand(struct sock *sk)
          * Cubic needs 1.7 factor, rounded to 2 to include
          * extra cushion (application might react slowly to POLLOUT)
          */
-        sndmem = 2 * nr_segs * per_mss;
+        sndmem = ca_ops->sndbuf_expand ? ca_ops->sndbuf_expand(sk) : 2;
+        sndmem *= nr_segs * per_mss;
 
         if (sk->sk_sndbuf < sndmem)
                 sk->sk_sndbuf = min(sndmem, sysctl_tcp_wmem[2]);