tcp: support TCP_DELACK_MAX_US for set/getsockopt use

Support adjusting/reading delayed ack max for socket level by using
set/getsockopt().

This option aligns with TCP_BPF_DELACK_MAX usage. Considering that bpf
option was implemented before this patch, so we need to use a standalone
new option for pure tcp set/getsockopt() use.

Add WRITE_ONCE/READ_ONCE() to prevent data-race if setsockopt()
happens to write one value to icsk_delack_max while icsk_delack_max is
being read.

Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250317120314.41404-3-kerneljasonxing@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index a126b3860e63caaa91dafd37631e285e7094aca8..dc8fdc80e16b05ca4174c5fe683d13b36dd4dff4 100644 (file)
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -141,6 +141,7 @@ enum {
 #define TCP_IS_MPTCP           43      /* Is MPTCP being used? */
 #define TCP_RTO_MAX_MS         44      /* max rto time in ms */
 #define TCP_RTO_MIN_US         45      /* min rto time in us */
+#define TCP_DELACK_MAX_US      46      /* max delayed ack time in us */
 
 #define TCP_REPAIR_ON          1
 #define TCP_REPAIR_OFF         0

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index a8a1370d642ebf1f504a2f66c504cbe601a8bd3c..6edc441b37023de48281aa810aa7a36199fd8bc3 100644 (file)
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3353,7 +3353,7 @@ int tcp_disconnect(struct sock *sk, int flags)
        icsk->icsk_probes_tstamp = 0;
        icsk->icsk_rto = TCP_TIMEOUT_INIT;
        WRITE_ONCE(icsk->icsk_rto_min, TCP_RTO_MIN);
-       icsk->icsk_delack_max = TCP_DELACK_MAX;
+       WRITE_ONCE(icsk->icsk_delack_max, TCP_DELACK_MAX);
        tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
        tcp_snd_cwnd_set(tp, TCP_INIT_CWND);
        tp->snd_cwnd_cnt = 0;
@@ -3841,6 +3841,14 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
                WRITE_ONCE(inet_csk(sk)->icsk_rto_min, rto_min);
                return 0;
        }
+       case TCP_DELACK_MAX_US: {
+               int delack_max = usecs_to_jiffies(val);
+
+               if (delack_max > TCP_DELACK_MAX || delack_max < TCP_TIMEOUT_MIN)
+                       return -EINVAL;
+               WRITE_ONCE(inet_csk(sk)->icsk_delack_max, delack_max);
+               return 0;
+       }
        }
 
        sockopt_lock_sock(sk);
@@ -4683,6 +4691,9 @@ zerocopy_rcv_out:
        case TCP_RTO_MIN_US:
                val = jiffies_to_usecs(READ_ONCE(inet_csk(sk)->icsk_rto_min));
                break;
+       case TCP_DELACK_MAX_US:
+               val = jiffies_to_usecs(READ_ONCE(inet_csk(sk)->icsk_delack_max));
+               break;
        default:
                return -ENOPROTOOPT;
        }

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index e0a4e5432399a3874e471f2d908bf976350f2696..9a606101711450db2cf554ef1c2a64fc4eacb6e2 100644 (file)
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -4179,7 +4179,7 @@ u32 tcp_delack_max(const struct sock *sk)
 {
        u32 delack_from_rto_min = max(tcp_rto_min(sk), 2) - 1;
 
-       return min(inet_csk(sk)->icsk_delack_max, delack_from_rto_min);
+       return min(READ_ONCE(inet_csk(sk)->icsk_delack_max), delack_from_rto_min);
 }
 
 /* Send out a delayed ack, the caller does the policy checking