tcp: add tcp_comp_sack_delay_ns sysctl

This per netns sysctl allows for TCP SACK compression fine-tuning.

Its default value is 1,000,000, or 1 ms to meet TSO autosizing period.

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

5 files changed, 18 insertions, 2 deletions

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index ea304a23c8d7..7ba952959bca 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -525,6 +525,13 @@ tcp_rmem - vector of 3 INTEGERs: min, default, max
 tcp_sack - BOOLEAN
         Enable select acknowledgments (SACKS).
 
+tcp_comp_sack_delay_ns - LONG INTEGER
+        TCP tries to reduce number of SACK sent, using a timer
+        based on 5% of SRTT, capped by this sysctl, in nano seconds.
+        The default is 1ms, based on TSO autosizing period.
+
+        Default : 1,000,000 ns (1 ms)
+
 tcp_slow_start_after_idle - BOOLEAN
         If set, provide RFC2861 behavior and time out the congestion
         window after an idle period.  An idle period is defined at
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 8491bc9c86b1..927318243cfa 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -160,6 +160,7 @@ struct netns_ipv4 {
         int sysctl_tcp_pacing_ca_ratio;
         int sysctl_tcp_wmem[3];
         int sysctl_tcp_rmem[3];
+        unsigned long sysctl_tcp_comp_sack_delay_ns;
         struct inet_timewait_death_row tcp_death_row;
         int sysctl_max_syn_backlog;
         int sysctl_tcp_fastopen;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 4b195bac8ac0..11fbfdc1566e 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -1152,6 +1152,13 @@ static struct ctl_table ipv4_net_table[] = {
                 .extra1         = &one,
         },
         {
+                .procname       = "tcp_comp_sack_delay_ns",
+                .data           = &init_net.ipv4.sysctl_tcp_comp_sack_delay_ns,
+                .maxlen         = sizeof(unsigned long),
+                .mode           = 0644,
+                .proc_handler   = proc_doulongvec_minmax,
+        },
+        {
                 .procname       = "udp_rmem_min",
                 .data           = &init_net.ipv4.sysctl_udp_rmem_min,
                 .maxlen         = sizeof(init_net.ipv4.sysctl_udp_rmem_min),
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index cc2ac5346b92..6a1dae38c955 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5113,13 +5113,13 @@ send_now:
         if (hrtimer_is_queued(&tp->compressed_ack_timer))
                 return;
 
-        /* compress ack timer : 5 % of rtt, but no more than 1 ms */
+        /* compress ack timer : 5 % of rtt, but no more than tcp_comp_sack_delay_ns */
 
         rtt = tp->rcv_rtt_est.rtt_us;
         if (tp->srtt_us && tp->srtt_us < rtt)
                 rtt = tp->srtt_us;
 
-        delay = min_t(unsigned long, NSEC_PER_MSEC,
+        delay = min_t(unsigned long, sock_net(sk)->ipv4.sysctl_tcp_comp_sack_delay_ns,
                       rtt * (NSEC_PER_USEC >> 3)/20);
         sock_hold(sk);
         hrtimer_start(&tp->compressed_ack_timer, ns_to_ktime(delay),
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index caf23de88f8a..a3f4647341db 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2572,6 +2572,7 @@ static int __net_init tcp_sk_init(struct net *net)
                        init_net.ipv4.sysctl_tcp_wmem,
                        sizeof(init_net.ipv4.sysctl_tcp_wmem));
         }
+        net->ipv4.sysctl_tcp_comp_sack_delay_ns = NSEC_PER_MSEC;
         net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE;
         spin_lock_init(&net->ipv4.tcp_fastopen_ctx_lock);
         net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 60 * 60;