This change is mostly from an internal patch and adapts it from sysctl
config to the bpf_setsockopt setup.
The bpf_prog can set the max delay ack by using
bpf_setsockopt(TCP_BPF_DELACK_MAX). This max delay ack can be communicated
to its peer through bpf header option. The receiving peer can then use
this max delay ack and set a potentially lower rto by using
bpf_setsockopt(TCP_BPF_RTO_MIN). A latter patch will use it
like this in a test as an example.
Signed-off-by: Martin KaFai Lau <kafai@xxxxxx>
---
include/net/inet_connection_sock.h | 2 ++
include/net/tcp.h | 2 +-
include/uapi/linux/bpf.h | 2 ++
net/core/filter.c | 15 +++++++++++++++
net/ipv4/tcp.c | 4 ++++
net/ipv4/tcp_output.c | 2 ++
tools/include/uapi/linux/bpf.h | 2 ++
7 files changed, 28 insertions(+), 1 deletion(-)
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index e5b388f5fa20..43d45864e5f0 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -93,6 +93,8 @@ struct inet_connection_sock {
struct timer_list icsk_retransmit_timer;
struct timer_list icsk_delack_timer;
__u32 icsk_rto;
+ __u32 icsk_rto_min;
+ __u32 icsk_delack_max;
__u32 icsk_pmtu_cookie;
const struct tcp_congestion_ops *icsk_ca_ops;
const struct inet_connection_sock_af_ops *icsk_af_ops;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index e93ef2d324f3..8a682d678971 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -703,7 +703,7 @@ static inline void tcp_fast_path_check(struct sock *sk)
static inline u32 tcp_rto_min(struct sock *sk)
{
const struct dst_entry *dst = __sk_dst_get(sk);
- u32 rto_min = TCP_RTO_MIN;
+ u32 rto_min = 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/bpf.h b/include/uapi/linux/bpf.h
index 479b83d05811..2ccc81548eef 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -4299,6 +4299,8 @@ enum {
* is not saved by TCP_SAVE_SYN.
*/
TCP_BPF_SYN_HDR_OPT = 1003,
+ TCP_BPF_DELACK_MAX = 1004, /* Max delay ack in usecs */
+ TCP_BPF_RTO_MIN = 1005, /* Min delay ack in usecs */
};
struct bpf_perf_event_value {
diff --git a/net/core/filter.c b/net/core/filter.c
index 5784f1bede2f..4b80934e6876 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4431,6 +4431,7 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname,
} else {
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
+ unsigned long timeout;
if (optlen != sizeof(int))
return -EINVAL;
@@ -4452,6 +4453,20 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname,
tp->snd_ssthresh = val;
}
break;
+ case TCP_BPF_DELACK_MAX:
+ timeout = usecs_to_jiffies(val);
+ if (timeout > TCP_DELACK_MAX ||
+ timeout < TCP_TIMEOUT_MIN)
+ return -EINVAL;
+ inet_csk(sk)->icsk_delack_max = timeout;
+ break;
+ case TCP_BPF_RTO_MIN:
+ timeout = usecs_to_jiffies(val);
+ if (timeout > TCP_RTO_MIN ||
+ timeout < TCP_TIMEOUT_MIN)
+ return -EINVAL;
+ inet_csk(sk)->icsk_rto_min = timeout;
+ break;
case TCP_SAVE_SYN:
if (val < 0 || val > 1)
ret = -EINVAL;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 60093a211f4d..02be3e2a2fdb 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -418,6 +418,8 @@ void tcp_init_sock(struct sock *sk)
INIT_LIST_HEAD(&tp->tsorted_sent_queue);
icsk->icsk_rto = TCP_TIMEOUT_INIT;
+ icsk->icsk_rto_min = TCP_RTO_MIN;
+ icsk->icsk_delack_max = TCP_DELACK_MAX;
tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
minmax_reset(&tp->rtt_min, tcp_jiffies32, ~0U);
@@ -2685,6 +2687,8 @@ int tcp_disconnect(struct sock *sk, int flags)
icsk->icsk_backoff = 0;
icsk->icsk_probes_out = 0;
icsk->icsk_rto = TCP_TIMEOUT_INIT;
+ icsk->icsk_rto_min = TCP_RTO_MIN;
+ icsk->icsk_delack_max = TCP_DELACK_MAX;
tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
tp->snd_cwnd = TCP_INIT_CWND;
tp->snd_cwnd_cnt = 0;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index a78a29980e1f..db872a2a01c6 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3899,6 +3899,8 @@ void tcp_send_delayed_ack(struct sock *sk)
ato = min(ato, max_ato);
}
+ ato = min_t(u32, ato, inet_csk(sk)->icsk_delack_max);
+
/* Stay within the limit we were given */
timeout = jiffies + ato;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 479b83d05811..2ccc81548eef 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4299,6 +4299,8 @@ enum {
* is not saved by TCP_SAVE_SYN.
*/
TCP_BPF_SYN_HDR_OPT = 1003,
+ TCP_BPF_DELACK_MAX = 1004, /* Max delay ack in usecs */
+ TCP_BPF_RTO_MIN = 1005, /* Min delay ack in usecs */
};
struct bpf_perf_event_value {
--
2.24.1
