[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <20201202021437.rbllajmj27u2ezyf@ast-mbp>
Date: Tue, 1 Dec 2020 18:14:37 -0800
From: Alexei Starovoitov <alexei.starovoitov@...il.com>
To: Prankur gupta <prankgup@...com>
Cc: bpf@...r.kernel.org, kernel-team@...com, netdev@...r.kernel.org
Subject: Re: [PATCH bpf-next 1/2] bpf: Adds support for setting window clamp
On Tue, Dec 01, 2020 at 08:43:56AM -0800, Prankur gupta wrote:
> Adds a new bpf_setsockopt for TCP sockets, TCP_BPF_WINDOW_CLAMP,
> which sets the maximum receiver window size. It will be useful for
> limiting receiver window based on RTT.
>
> Signed-off-by: Prankur gupta <prankgup@...com>
> ---
> net/core/filter.c | 13 +++++++++++++
> 1 file changed, 13 insertions(+)
>
> diff --git a/net/core/filter.c b/net/core/filter.c
> index 2ca5eecebacf..8c52ffae7b0c 100644
> --- a/net/core/filter.c
> +++ b/net/core/filter.c
> @@ -4910,6 +4910,19 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname,
> tp->notsent_lowat = val;
> sk->sk_write_space(sk);
> break;
> + case TCP_WINDOW_CLAMP:
> + if (!val) {
> + if (sk->sk_state != TCP_CLOSE) {
> + ret = -EINVAL;
> + break;
> + }
> + tp->window_clamp = 0;
> + } else {
> + tp->window_clamp =
> + val < SOCK_MIN_RCVBUF / 2 ?
> + SOCK_MIN_RCVBUF / 2 : val;
> + }
May be extract this logic into a helper instead of copy-paste?
Powered by blists - more mailing lists