Re: [PATCH v2 bpf-next 7/8] bpf: tcp: Add kfunc to adjust sk->sk_rcvlowat.

["Emil Tsalapatis" <emil@etsalapatis.com>]

On Wed Sep 23, 2026 at 9:35 PM UTC, Kuniyuki Iwashima wrote:
> bpf_tcp_ops.{enqueue,dequeue}_rcvq() were added to parse skb and
> adjust sk->sk_rcvlowat dynamically to suppress unnecessary wakeups.
>
> Let's add a new kfunc to set sk->sk_rcvlowat.
>
> Negative values are clamped to INT_MAX, consistent with SO_RCVLOWAT.
>
> For enqueue_rcvq(), wakeup is set to false because:
>
>   * tcp_data_ready() is always called after the hooks in
>     tcp_queue_rcv() and tcp_ofo_queue().
>
>   * when tcp_fastopen_add_skb() is called for TFO SYN, the socket is
>     not yet accept()ed, and when called for TFO SYN+ACK, the socket
>     is woken up by sk->sk_state_change() anyway.
>
> For dequeue_rcvq(), wakeup is set to true because tcp_data_ready()
> is not called in that path.
>
> An alternative would be to support bpf_setsockopt() for these
> hooks.
>
> However, that approach involves excessive conditionals and an
> unnecessary memcpy(), costs we do not want to pay for every skb
> in the TCP fast path.
>
> Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
> Acked-by: Stanislav Fomichev <sdf@fomichev.me>
> Tested-by: Clément Léger <cleger@meta.com>

Reviewed-by: Emil Tsalapatis <emil@etsalapatis.com>

> ---
>  net/ipv4/bpf_tcp_ops.c | 56 +++++++++++++++++++++++++++++++++++++++++-
>  1 file changed, 55 insertions(+), 1 deletion(-)
>
> diff --git a/net/ipv4/bpf_tcp_ops.c b/net/ipv4/bpf_tcp_ops.c
> index b0cade34cce6..e93c8d13684e 100644
> --- a/net/ipv4/bpf_tcp_ops.c
> +++ b/net/ipv4/bpf_tcp_ops.c
> @@ -368,8 +368,62 @@ static struct bpf_struct_ops bpf_tcp_ops = {
>  	.owner = THIS_MODULE,
>  };
>  
> +__bpf_kfunc_start_defs();
> +
> +__bpf_kfunc int bpf_tcp_ops_set_rcvlowat(struct sock *sk, int rcvlowat,
> +					 const struct bpf_prog_aux *aux)
> +{
> +	u32 moff = aux->attach_st_ops_member_off;
> +	bool wakeup = false;
> +
> +	if (moff == offsetof(struct bpf_tcp_ops, dequeue_rcvq))
> +		wakeup = true;
> +
> +	if (rcvlowat < 0)
> +		rcvlowat = INT_MAX;
> +
> +	return __tcp_set_rcvlowat(sk, rcvlowat, wakeup);
> +}
> +
> +__bpf_kfunc_end_defs();
> +
> +BTF_KFUNCS_START(bpf_tcp_ops_rcvlowat_kfunc_set)
> +BTF_ID_FLAGS(func, bpf_tcp_ops_set_rcvlowat, KF_IMPLICIT_ARGS)
> +BTF_KFUNCS_END(bpf_tcp_ops_rcvlowat_kfunc_set)
> +
> +static int bpf_tcp_ops_rcvlowat_kfunc_filter(const struct bpf_prog *prog,
> +					     u32 kfunc_id)
> +{
> +	u32 moff;
> +
> +	if (!btf_id_set8_contains(&bpf_tcp_ops_rcvlowat_kfunc_set, kfunc_id))
> +		return 0;
> +
> +	if (prog->aux->st_ops != &bpf_tcp_ops)
> +		return -EACCES;
> +
> +	moff = prog->aux->attach_st_ops_member_off;
> +	if (moff != offsetof(struct bpf_tcp_ops, enqueue_rcvq) &&
> +	    moff != offsetof(struct bpf_tcp_ops, dequeue_rcvq))
> +		return -EACCES;
> +
> +	return 0;
> +}
> +
> +static const struct btf_kfunc_id_set bpf_tcp_ops_rcvlowat_kfunc_id_set = {
> +	.owner = THIS_MODULE,
> +	.set = &bpf_tcp_ops_rcvlowat_kfunc_set,
> +	.filter = bpf_tcp_ops_rcvlowat_kfunc_filter,
> +};
> +
>  static int __init __bpf_tcp_ops_init(void)
>  {
> -	return register_bpf_struct_ops(&bpf_tcp_ops, bpf_tcp_ops);
> +	int ret;
> +
> +	ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS,
> +					&bpf_tcp_ops_rcvlowat_kfunc_id_set);
> +	ret = ret ?: register_bpf_struct_ops(&bpf_tcp_ops, bpf_tcp_ops);
> +
> +	return ret;
>  }
>  late_initcall(__bpf_tcp_ops_init);