Netdev Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Cong Wang <xiyou.wangcong@gmail.com>
To: Martin KaFai Lau <kafai@fb.com>
Cc: Linux Kernel Network Developers <netdev@vger.kernel.org>,
	Qitao Xu <qitao.xu@bytedance.com>,
	Cong Wang <cong.wang@bytedance.com>, bpf <bpf@vger.kernel.org>
Subject: Re: [Patch net-next 02/13] ipv4: introduce tracepoint trace_ip_queue_xmit()
Date: Wed, 11 Aug 2021 15:48:36 -0700	[thread overview]
Message-ID: <CAM_iQpUorOGfdthXe+wkAhFOv8i2zFhBgF0NUBQEBMkGYTavuw@mail.gmail.com> (raw)
In-Reply-To: <20210811212257.l3mzdkcwmlbbxd6k@kafai-mbp>

On Wed, Aug 11, 2021 at 2:23 PM Martin KaFai Lau <kafai@fb.com> wrote:
> Instead of adding tracepoints, the bpf fexit prog can be used here and
> the bpf prog will have the sk, skb, and ret available (example in fexit_test.c).
> Some tracepoints in this set can also be done with bpf fentry/fexit.
> Does bpf fentry/fexit work for your use case?

Well, kprobe works too in this perspective. The problem with kprobe
or fexit is that there is no guarantee the function still exists in kernel
during iteration. Kernel is free to delete or rename it. With tracepoint,
even if ip_queue_xmit() were renamed, the same tracepoint must
remain in the kernel.

Thanks.

  reply	other threads:[~2021-08-11 22:48 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-08-05 18:57 [Patch net-next 00/13] net: add more tracepoints to TCP/IP stack Cong Wang
2021-08-05 18:57 ` [Patch net-next 01/13] net: introduce a new header file include/trace/events/ip.h Cong Wang
2021-08-05 18:57 ` [Patch net-next 02/13] ipv4: introduce tracepoint trace_ip_queue_xmit() Cong Wang
2021-08-06 10:08   ` Eric Dumazet
2021-08-09 20:32     ` Cong Wang
2021-08-11 21:22   ` Martin KaFai Lau
2021-08-11 22:48     ` Cong Wang [this message]
2021-08-11 23:08       ` Martin KaFai Lau
2021-08-12  0:37         ` Cong Wang
2021-08-12  5:46           ` Martin KaFai Lau
2021-08-05 18:57 ` [Patch net-next 03/13] tcp: introduce tracepoint trace_tcp_transmit_skb() Cong Wang
2021-08-05 18:57 ` [Patch net-next 04/13] udp: introduce tracepoint trace_udp_send_skb() Cong Wang
2021-08-05 18:57 ` [Patch net-next 05/13] udp: introduce tracepoint trace_udp_v6_send_skb() Cong Wang
2021-08-05 18:57 ` [Patch net-next 06/13] ipv4: introduce tracepoint trace_ip_rcv() Cong Wang
2021-08-05 18:57 ` [Patch net-next 07/13] ipv6: introduce tracepoint trace_ipv6_rcv() Cong Wang
2021-08-05 18:57 ` [Patch net-next 08/13] ipv4: introduce tracepoint trace_ip_local_deliver_finish() Cong Wang
2021-08-05 18:57 ` [Patch net-next 09/13] udp: introduce tracepoint trace_udp_rcv() Cong Wang
2021-08-05 18:57 ` [Patch net-next 10/13] ipv6: introduce tracepoint trace_udpv6_rcv() Cong Wang
2021-08-05 18:57 ` [Patch net-next 11/13] tcp: introduce tracepoint trace_tcp_v4_rcv() Cong Wang
2021-08-05 18:57 ` [Patch net-next 12/13] ipv6: introduce tracepoint trace_tcp_v6_rcv() Cong Wang
2021-08-05 18:57 ` [Patch net-next 13/13] sock: introduce tracepoint trace_sk_data_ready() Cong Wang
2021-08-06  2:22 ` [Patch net-next 00/13] net: add more tracepoints to TCP/IP stack Cong Wang

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=CAM_iQpUorOGfdthXe+wkAhFOv8i2zFhBgF0NUBQEBMkGYTavuw@mail.gmail.com \
    --to=xiyou.wangcong@gmail.com \
    --cc=bpf@vger.kernel.org \
    --cc=cong.wang@bytedance.com \
    --cc=kafai@fb.com \
    --cc=netdev@vger.kernel.org \
    --cc=qitao.xu@bytedance.com \
    --subject='Re: [Patch net-next 02/13] ipv4: introduce tracepoint trace_ip_queue_xmit()' \
    /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

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).