dummy/linux-stable-mirror
1
0
Fork 1
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ synced 2025-04-19 20:58:31 +09:00
Code Issues Packages Projects Releases Wiki Activity

tcp: support TCP_RTO_MIN_US for set/getsockopt use

Browse Source 
Support adjusting/reading RTO MIN for socket level by using set/getsockopt().

This new option has the same effect as TCP_BPF_RTO_MIN, which means it
doesn't affect RTAX_RTO_MIN usage (by using ip route...). Considering that
bpf option was implemented before this patch, so we need to use a standalone
new option for pure tcp set/getsockopt() use.

When the socket is created, its icsk_rto_min is set to the default
value that is controlled by sysctl_tcp_rto_min_us. Then if application
calls setsockopt() with TCP_RTO_MIN_US flag to pass a valid value, then
icsk_rto_min will be overridden in jiffies unit.

This patch adds WRITE_ONCE/READ_ONCE to avoid data-race around
icsk_rto_min.

Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250317120314.41404-2-kerneljasonxing@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This commit is contained in:
Jason Xing 2025-03-17 20:03:13 +08:00 committed by Jakub Kicinski
parent 98b2c048e2
commit f38805c5d2
4 changed files with 16 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
Documentation/networking/ip-sysctl.rst
View File

@ -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.

2
include/net/tcp.h
View File

@ -844,7 +844,7 @@ 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);

1
include/uapi/linux/tcp.h
View File

@ -140,6 +140,7 @@ 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

13
net/ipv4/tcp.c
View File

@ -3352,7 +3352,7 @@ 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);
@ -3833,6 +3833,14 @@ 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);
@ -4672,6 +4680,9 @@ zerocopy_rcv_out:
case TCP_RTO_MAX_MS:
val = jiffies_to_msecs(tcp_rto_max(sk));
break;
case TCP_RTO_MIN_US:
val = jiffies_to_usecs(READ_ONCE(inet_csk(sk)->icsk_rto_min));
break;
default:
return -ENOPROTOOPT;
}