Support adjusting RTO MIN for socket level in non BPF case.
Signed-off-by: Jason Xing <kerneljasonxing@xxxxxxxxx>
---
Documentation/networking/ip-sysctl.rst | 4 ++--
include/net/tcp.h | 2 +-
include/uapi/linux/tcp.h | 1 +
net/ipv4/tcp.c | 16 +++++++++++++++-
4 files changed, 19 insertions(+), 4 deletions(-)
diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index 054561f8dcae..56eabcff0ed0 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -1229,8 +1229,8 @@ tcp_pingpong_thresh - INTEGER
tcp_rto_min_us - INTEGER
Minimal TCP retransmission timeout (in microseconds). Note that the
rto_min route option has the highest precedence for configuring this
- setting, followed by the TCP_BPF_RTO_MIN socket option, followed by
- this tcp_rto_min_us sysctl.
+ setting, followed by the TCP_BPF_RTO_MIN and TCP_RTO_MIN_US socket
+ options, followed by this tcp_rto_min_us sysctl.
The recommended practice is to use a value less or equal to 200000
microseconds.
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 9745c7f18170..e850550deb6f 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -803,7 +803,7 @@ u32 tcp_delack_max(const struct sock *sk);
static inline u32 tcp_rto_min(const struct sock *sk)
{
const struct dst_entry *dst = __sk_dst_get(sk);
- u32 rto_min = inet_csk(sk)->icsk_rto_min;
+ u32 rto_min = READ_ONCE(inet_csk(sk)->icsk_rto_min);
if (dst && dst_metric_locked(dst, RTAX_RTO_MIN))
rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN);
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index 32a27b4a5020..b2476cf7058e 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -137,6 +137,7 @@ 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_REPAIR_ON 1
#define TCP_REPAIR_OFF 0
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 08d73f17e816..2a0fd56358c3 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3339,7 +3339,7 @@ int tcp_disconnect(struct sock *sk, int flags)
icsk->icsk_probes_out = 0;
icsk->icsk_probes_tstamp = 0;
icsk->icsk_rto = TCP_TIMEOUT_INIT;
- icsk->icsk_rto_min = TCP_RTO_MIN;
+ WRITE_ONCE(icsk->icsk_rto_min, TCP_RTO_MIN);
icsk->icsk_delack_max = TCP_DELACK_MAX;
tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
tcp_snd_cwnd_set(tp, TCP_INIT_CWND);
@@ -3820,6 +3820,14 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
return -EINVAL;
WRITE_ONCE(inet_csk(sk)->icsk_rto_max, msecs_to_jiffies(val));
return 0;
+ case TCP_RTO_MIN_US: {
+ int rto_min = usecs_to_jiffies(val);
+
+ if (rto_min > TCP_RTO_MIN || rto_min < TCP_TIMEOUT_MIN)
+ return -EINVAL;
+ WRITE_ONCE(inet_csk(sk)->icsk_rto_min, rto_min);
+ return 0;
+ }
}
sockopt_lock_sock(sk);
@@ -4659,6 +4667,12 @@ int do_tcp_getsockopt(struct sock *sk, int level,
case TCP_RTO_MAX_MS:
val = jiffies_to_msecs(tcp_rto_max(sk));
break;
+ case TCP_RTO_MIN_US: {
+ int rto_min = READ_ONCE(inet_csk(sk)->icsk_rto_min);
+
+ val = jiffies_to_usecs(rto_min);
+ break;
+ }
default:
return -ENOPROTOOPT;
}
--
2.43.5
