From: Miao Xu <miaxu@meta.com>
To: Eric Dumazet <edumazet@google.com>,
"David S . Miller" <davem@davemloft.net>,
Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
David Ahern <dsahern@kernel.org>, Martin Lau <kafai@meta.com>
Cc: <netdev@vger.kernel.org>, <bpf@vger.kernel.org>,
Miao Xu <miaxu@meta.com>
Subject: [PATCH net-next v3 1/3] tcp: Add new args for cong_control in tcp_congestion_ops
Date: Wed, 1 May 2024 21:23:16 -0700 [thread overview]
Message-ID: <20240502042318.801932-2-miaxu@meta.com> (raw)
In-Reply-To: <20240502042318.801932-1-miaxu@meta.com>
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.
Reviewed-by: Eric Dumazet <edumazet@google.com>
---
Changes in v3:
* Fixed the broken selftest
Changes in v2:
* Split the v1 patch into 2 separate patches. In particular, spin out
bpf_tcp_ca.c as a separate patch because it is bpf specific.
Signed-off-by: Miao Xu <miaxu@meta.com>
---
include/net/tcp.h | 2 +-
net/ipv4/bpf_tcp_ca.c | 3 ++-
net/ipv4/tcp_bbr.c | 2 +-
net/ipv4/tcp_input.c | 2 +-
tools/testing/selftests/bpf/progs/tcp_ca_kfunc.c | 6 +++---
5 files changed, 8 insertions(+), 7 deletions(-)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index fe98fb01879b..7294da8fb780 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1172,7 +1172,7 @@ 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..6bd7f8db189a 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -307,7 +307,8 @@ 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 7e52ab24e40a..760941e55153 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 53e1150f706f..23ccfc7b1d3c 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;
}
diff --git a/tools/testing/selftests/bpf/progs/tcp_ca_kfunc.c b/tools/testing/selftests/bpf/progs/tcp_ca_kfunc.c
index fcfbfe0336b4..52b610357309 100644
--- a/tools/testing/selftests/bpf/progs/tcp_ca_kfunc.c
+++ b/tools/testing/selftests/bpf/progs/tcp_ca_kfunc.c
@@ -5,7 +5,7 @@
#include <bpf/bpf_tracing.h>
extern void bbr_init(struct sock *sk) __ksym;
-extern void bbr_main(struct sock *sk, const struct rate_sample *rs) __ksym;
+extern void bbr_main(struct sock *sk, u32 ack, int flag, const struct rate_sample *rs) __ksym;
extern u32 bbr_sndbuf_expand(struct sock *sk) __ksym;
extern u32 bbr_undo_cwnd(struct sock *sk) __ksym;
extern void bbr_cwnd_event(struct sock *sk, enum tcp_ca_event event) __ksym;
@@ -42,9 +42,9 @@ void BPF_PROG(in_ack_event, struct sock *sk, u32 flags)
}
SEC("struct_ops/cong_control")
-void BPF_PROG(cong_control, struct sock *sk, const struct rate_sample *rs)
+void BPF_PROG(cong_control, struct sock *sk, u32 ack, int flag, const struct rate_sample *rs)
{
- bbr_main(sk, rs);
+ bbr_main(sk, ack, flag, rs);
}
SEC("struct_ops/cong_avoid")
--
2.43.0
next prev parent reply other threads:[~2024-05-02 4:23 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-05-02 4:23 [PATCH net-next v3 0/3] Add new args into tcp_congestion_ops' cong_control Miao Xu
2024-05-02 4:23 ` Miao Xu [this message]
2024-05-02 4:23 ` [PATCH net-next v3 2/3] bpf: tcp: Allow to write tp->snd_cwnd_stamp in bpf_tcp_ca Miao Xu
2024-05-02 4:23 ` [PATCH net-next v3 3/3] selftests/bpf: Add test for the use of new args in cong_control Miao Xu
2024-05-02 23:39 ` Martin KaFai Lau
2024-05-02 23:40 ` [PATCH net-next v3 0/3] Add new args into tcp_congestion_ops' cong_control patchwork-bot+netdevbpf
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20240502042318.801932-2-miaxu@meta.com \
--to=miaxu@meta.com \
--cc=bpf@vger.kernel.org \
--cc=davem@davemloft.net \
--cc=dsahern@kernel.org \
--cc=edumazet@google.com \
--cc=kafai@meta.com \
--cc=kuba@kernel.org \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox