[PATCH bpf-next v2 5/6] tcp: support TCP_DELACK_MAX_US for set/getsockopt use

[Jason Xing <kerneljasonxing@gmail.com>]

Support adjusting delayed ack max for socket level in non BPF case.

Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
---
 include/uapi/linux/tcp.h |  1 +
 net/ipv4/tcp.c           | 16 +++++++++++++++-
 net/ipv4/tcp_output.c    |  2 +-
 3 files changed, 17 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index b2476cf7058e..2377e22f2c4b 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -138,6 +138,7 @@ 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 2a0fd56358c3..ed652c5e9e96 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3340,7 +3340,7 @@ 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;
@@ -3828,6 +3828,14 @@ 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);
@@ -4673,6 +4681,12 @@ int do_tcp_getsockopt(struct sock *sk, int level,
 		val = jiffies_to_usecs(rto_min);
 		break;
 	}
+	case TCP_DELACK_MAX_US: {
+		int delack_max = READ_ONCE(inet_csk(sk)->icsk_delack_max);
+
+		val = jiffies_to_usecs(delack_max);
+		break;
+	}
 	default:
 		return -ENOPROTOOPT;
 	}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 9a3cf51eab78..00267b17f5e4 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -4173,7 +4173,7 @@ 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
-- 
2.43.5