netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Martin KaFai Lau <martin.lau@linux.dev>
To: Jason Xing <kerneljasonxing@gmail.com>
Cc: davem@davemloft.net, edumazet@google.com, kuba@kernel.org,
	pabeni@redhat.com, dsahern@kernel.org,
	willemdebruijn.kernel@gmail.com, willemb@google.com,
	ast@kernel.org, daniel@iogearbox.net, andrii@kernel.org,
	eddyz87@gmail.com, song@kernel.org, yonghong.song@linux.dev,
	john.fastabend@gmail.com, kpsingh@kernel.org, sdf@fomichev.me,
	haoluo@google.com, jolsa@kernel.org, shuah@kernel.org,
	ykolal@fb.com, bpf@vger.kernel.org, netdev@vger.kernel.org
Subject: Re: [PATCH bpf-next v10 11/12] bpf: support selective sampling for bpf timestamping
Date: Wed, 12 Feb 2025 15:49:45 -0800	[thread overview]
Message-ID: <eb579932-e85e-4241-bfe7-6e0d780ee9d6@linux.dev> (raw)
In-Reply-To: <20250212061855.71154-12-kerneljasonxing@gmail.com>

On 2/11/25 10:18 PM, Jason Xing wrote:
> Add the bpf_sock_ops_enable_tx_tstamp kfunc to allow BPF programs to
> selectively enable TX timestamping on a skb during tcp_sendmsg().
> 
> For example, BPF program will limit tracking X numbers of packets
> and then will stop there instead of tracing all the sendmsgs of
> matched flow all along. It would be helpful for users who cannot
> afford to calculate latencies from every sendmsg call probably
> due to the performance or storage space consideration.
> 
> Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
> ---
>   kernel/bpf/btf.c  |  1 +
>   net/core/filter.c | 32 +++++++++++++++++++++++++++++++-
>   2 files changed, 32 insertions(+), 1 deletion(-)
> 
> diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
> index 9433b6467bbe..740210f883dc 100644
> --- a/kernel/bpf/btf.c
> +++ b/kernel/bpf/btf.c
> @@ -8522,6 +8522,7 @@ static int bpf_prog_type_to_kfunc_hook(enum bpf_prog_type prog_type)
>   	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
>   	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
>   	case BPF_PROG_TYPE_CGROUP_SYSCTL:
> +	case BPF_PROG_TYPE_SOCK_OPS:
>   		return BTF_KFUNC_HOOK_CGROUP;
>   	case BPF_PROG_TYPE_SCHED_ACT:
>   		return BTF_KFUNC_HOOK_SCHED_ACT;
> diff --git a/net/core/filter.c b/net/core/filter.c
> index 7f56d0bbeb00..36793c68b125 100644
> --- a/net/core/filter.c
> +++ b/net/core/filter.c
> @@ -12102,6 +12102,26 @@ __bpf_kfunc int bpf_sk_assign_tcp_reqsk(struct __sk_buff *s, struct sock *sk,
>   #endif
>   }
>   
> +__bpf_kfunc int bpf_sock_ops_enable_tx_tstamp(struct bpf_sock_ops_kern *skops,
> +					      u64 flags)
> +{
> +	struct sk_buff *skb;
> +	struct sock *sk;
> +
> +	if (skops->op != BPF_SOCK_OPS_TS_SND_CB)
> +		return -EOPNOTSUPP;

It still needs to test the "flags" such that it can be used in the future....

	if (flags)
		return -EINVAL;

> +
> +	skb = skops->skb;
> +	sk = skops->sk;
> +	skb_shinfo(skb)->tx_flags |= SKBTX_BPF;
> +	if (sk_is_tcp(sk)) {

Unnecessary check like this will only confuse reader. Remove it and revisit when 
UDP will be supported.

> +		TCP_SKB_CB(skb)->txstamp_ack |= TSTAMP_ACK_BPF;
> +		skb_shinfo(skb)->tskey = TCP_SKB_CB(skb)->seq + skb->len - 1;
> +	}
> +
> +	return 0;
> +}
> +
>   __bpf_kfunc_end_defs();
>   
>   int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags,
> @@ -12135,6 +12155,10 @@ BTF_KFUNCS_START(bpf_kfunc_check_set_tcp_reqsk)
>   BTF_ID_FLAGS(func, bpf_sk_assign_tcp_reqsk, KF_TRUSTED_ARGS)
>   BTF_KFUNCS_END(bpf_kfunc_check_set_tcp_reqsk)
>   
> +BTF_KFUNCS_START(bpf_kfunc_check_set_sock_ops)
> +BTF_ID_FLAGS(func, bpf_sock_ops_enable_tx_tstamp, KF_TRUSTED_ARGS)
> +BTF_KFUNCS_END(bpf_kfunc_check_set_sock_ops)
> +
>   static const struct btf_kfunc_id_set bpf_kfunc_set_skb = {
>   	.owner = THIS_MODULE,
>   	.set = &bpf_kfunc_check_set_skb,
> @@ -12155,6 +12179,11 @@ static const struct btf_kfunc_id_set bpf_kfunc_set_tcp_reqsk = {
>   	.set = &bpf_kfunc_check_set_tcp_reqsk,
>   };
>   
> +static const struct btf_kfunc_id_set bpf_kfunc_set_sock_ops = {
> +	.owner = THIS_MODULE,
> +	.set = &bpf_kfunc_check_set_sock_ops,
> +};
> +
>   static int __init bpf_kfunc_init(void)
>   {
>   	int ret;
> @@ -12173,7 +12202,8 @@ static int __init bpf_kfunc_init(void)
>   	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &bpf_kfunc_set_xdp);
>   	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
>   					       &bpf_kfunc_set_sock_addr);
> -	return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_kfunc_set_tcp_reqsk);
> +	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_kfunc_set_tcp_reqsk);
> +	return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SOCK_OPS, &bpf_kfunc_set_sock_ops);
>   }
>   late_initcall(bpf_kfunc_init);
>   


  reply	other threads:[~2025-02-12 23:50 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-02-12  6:18 [PATCH bpf-next v10 00/12] net-timestamp: bpf extension to equip applications transparently Jason Xing
2025-02-12  6:18 ` [PATCH bpf-next v10 01/12] bpf: add networking timestamping support to bpf_get/setsockopt() Jason Xing
2025-02-12  6:18 ` [PATCH bpf-next v10 02/12] bpf: prepare the sock_ops ctx and call bpf prog for TX timestamping Jason Xing
2025-02-12  6:18 ` [PATCH bpf-next v10 03/12] bpf: prevent unsafe access to the sock fields in the BPF timestamping callback Jason Xing
2025-02-12  6:18 ` [PATCH bpf-next v10 04/12] bpf: disable unsafe helpers in TX timestamping callbacks Jason Xing
2025-02-12  6:18 ` [PATCH bpf-next v10 05/12] net-timestamp: prepare for isolating two modes of SO_TIMESTAMPING Jason Xing
2025-02-12  6:18 ` [PATCH bpf-next v10 06/12] bpf: add BPF_SOCK_OPS_TS_SCHED_OPT_CB callback Jason Xing
2025-02-12  6:18 ` [PATCH bpf-next v10 07/12] bpf: add BPF_SOCK_OPS_TS_SW_OPT_CB callback Jason Xing
2025-02-12 23:18   ` Martin KaFai Lau
2025-02-13  7:24     ` Jason Xing
2025-02-12  6:18 ` [PATCH bpf-next v10 08/12] bpf: add BPF_SOCK_OPS_TS_HW_OPT_CB callback Jason Xing
2025-02-12 23:20   ` Martin KaFai Lau
2025-02-13  7:24     ` Jason Xing
2025-02-12  6:18 ` [PATCH bpf-next v10 09/12] bpf: add BPF_SOCK_OPS_TS_ACK_OPT_CB callback Jason Xing
2025-02-12 15:26   ` Willem de Bruijn
2025-02-13  0:07     ` Jason Xing
2025-02-13  7:23       ` Jason Xing
2025-02-13 15:09         ` Willem de Bruijn
2025-02-12  6:18 ` [PATCH bpf-next v10 10/12] bpf: add BPF_SOCK_OPS_TS_SND_CB callback Jason Xing
2025-02-12  6:18 ` [PATCH bpf-next v10 11/12] bpf: support selective sampling for bpf timestamping Jason Xing
2025-02-12 23:49   ` Martin KaFai Lau [this message]
2025-02-13  7:26     ` Jason Xing
2025-02-12  6:18 ` [PATCH bpf-next v10 12/12] selftests/bpf: add simple bpf tests in the tx path for timestamping feature Jason Xing
2025-02-13  1:08   ` Martin KaFai Lau
2025-02-13 11:31     ` Jason Xing

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=eb579932-e85e-4241-bfe7-6e0d780ee9d6@linux.dev \
    --to=martin.lau@linux.dev \
    --cc=andrii@kernel.org \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=davem@davemloft.net \
    --cc=dsahern@kernel.org \
    --cc=eddyz87@gmail.com \
    --cc=edumazet@google.com \
    --cc=haoluo@google.com \
    --cc=john.fastabend@gmail.com \
    --cc=jolsa@kernel.org \
    --cc=kerneljasonxing@gmail.com \
    --cc=kpsingh@kernel.org \
    --cc=kuba@kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=sdf@fomichev.me \
    --cc=shuah@kernel.org \
    --cc=song@kernel.org \
    --cc=willemb@google.com \
    --cc=willemdebruijn.kernel@gmail.com \
    --cc=ykolal@fb.com \
    --cc=yonghong.song@linux.dev \
    /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;
as well as URLs for NNTP newsgroup(s).