[1/2,net-next,1/2] Add new args for cong_control in tcp_congestion_ops

Commit Message

Miao Xu April 24, 2024, 8:37 p.m. UTC

This patch adds two new arguments for cong_control of struct
tcp_congestion_ops:
 - ack
 - flag
These two arguments are inherited from the caller tcp_cong_control in
tcp_intput.c. One use case of them is to update cwnd and pacing rate
inside cong_control based on the info they provide. For example, the
flag can be used to decide if it is the right time to raise or reduce a
sender's cwnd.

Another change in this patch is to allow the write of tp->snd_cwnd_stamp
for a bpf tcp ca program. An use case of writing this field is to keep
track of the time whenever tp->snd_cwnd is raised or reduced inside the
cong_control callback.

Signed-off-by: Miao Xu <[e-mail]>
---
 include/net/tcp.h     | 2 +-
 net/ipv4/bpf_tcp_ca.c | 6 +++++-
 net/ipv4/tcp_bbr.c    | 2 +-
 net/ipv4/tcp_input.c  | 2 +-
 4 files changed, 8 insertions(+), 4 deletions(-)

Comments

Eric Dumazet April 27, 2024, 1:06 p.m. UTC | #1

On Wed, Apr 24, 2024 at 10:38 PM Miao Xu <[e-mail]> wrote:
>
> This patch adds two new arguments for cong_control of struct
> tcp_congestion_ops:
>  - ack
>  - flag
> These two arguments are inherited from the caller tcp_cong_control in
> tcp_intput.c. One use case of them is to update cwnd and pacing rate
> inside cong_control based on the info they provide. For example, the
> flag can be used to decide if it is the right time to raise or reduce a
> sender's cwnd.
>
> Another change in this patch is to allow the write of tp->snd_cwnd_stamp
> for a bpf tcp ca program. An use case of writing this field is to keep
> track of the time whenever tp->snd_cwnd is raised or reduced inside the
> cong_control callback.
>
> Signed-off-by: Miao Xu <[e-mail]>

Reviewed-by: Eric Dumazet <[e-mail]>

Patch

diff --git a/include/net/tcp.h b/include/net/tcp.h
index b935e1ae4caf..b37b8219060a 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1167,7 +1167,7 @@  struct tcp_congestion_ops {
 	/* call when packets are delivered to update cwnd and pacing rate,
 	 * after all the ca_state processing. (optional)
 	 */
-	void (*cong_control)(struct sock *sk, const struct rate_sample *rs);
+	void (*cong_control)(struct sock *sk, u32 ack, int flag, const struct rate_sample *rs);
 
 
 	/* new value of cwnd after loss (required) */
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index 7f518ea5f4ac..18227757ec0c 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -107,6 +107,9 @@  static int bpf_tcp_ca_btf_struct_access(struct bpf_verifier_log *log,
 	case offsetof(struct tcp_sock, snd_cwnd_cnt):
 		end = offsetofend(struct tcp_sock, snd_cwnd_cnt);
 		break;
+	case offsetof(struct tcp_sock, snd_cwnd_stamp):
+		end = offsetofend(struct tcp_sock, snd_cwnd_stamp);
+		break;
 	case offsetof(struct tcp_sock, snd_ssthresh):
 		end = offsetofend(struct tcp_sock, snd_ssthresh);
 		break;
@@ -307,7 +310,8 @@  static u32 bpf_tcp_ca_min_tso_segs(struct sock *sk)
 	return 0;
 }
 
-static void bpf_tcp_ca_cong_control(struct sock *sk, const struct rate_sample *rs)
+static void bpf_tcp_ca_cong_control(struct sock *sk, u32 ack, int flag,
+				    const struct rate_sample *rs)
 {
 }
 
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 05dc2d05bc7c..c13d263dae06 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -1024,7 +1024,7 @@  static void bbr_update_model(struct sock *sk, const struct rate_sample *rs)
 	bbr_update_gains(sk);
 }
 
-__bpf_kfunc static void bbr_main(struct sock *sk, const struct rate_sample *rs)
+__bpf_kfunc static void bbr_main(struct sock *sk, u32 ack, int flag, const struct rate_sample *rs)
 {
 	struct bbr *bbr = inet_csk_ca(sk);
 	u32 bw;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 384fa5e2f065..661dca9e3895 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3541,7 +3541,7 @@  static void tcp_cong_control(struct sock *sk, u32 ack, u32 acked_sacked,
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 
 	if (icsk->icsk_ca_ops->cong_control) {
-		icsk->icsk_ca_ops->cong_control(sk, rs);
+		icsk->icsk_ca_ops->cong_control(sk, ack, flag, rs);
 		return;
 	}