It is useful to expose skb addr and sock addr to user in tracepoint
tcp_probe, so that we can get more information while monitoring
receiving of tcp data, by ebpf or other ways.
For example, we need to identify a packet by seq and end_seq when
calculate transmit latency between lay 2 and lay 4 by ebpf, but which is
not available in tcp_probe, so we can only use kprobe hooking
tcp_rcv_esatblised to get them. But we can use tcp_probe directly if skb
addr and sock addr are available, which is more efficient.
Signed-off-by: fuyuanli <[email protected]>
Link: https://lore.kernel.org/netdev/20240229052813.GA23899@didi-ThinkCentre-M920t-N000/
---
v2:
1) Add printing about those two addresses.
2) Target "net-next" in the title of patch.
---
include/trace/events/tcp.h | 10 ++++++++--
1 file changed, 8 insertions(+), 2 deletions(-)
diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h
index 7b1ddffa3dfc..efb651683781 100644
--- a/include/trace/events/tcp.h
+++ b/include/trace/events/tcp.h
@@ -258,6 +258,8 @@ TRACE_EVENT(tcp_probe,
__field(__u32, srtt)
__field(__u32, rcv_wnd)
__field(__u64, sock_cookie)
+ __field(const void *, skbaddr)
+ __field(const void *, skaddr)
),
TP_fast_assign(
@@ -285,14 +287,18 @@ TRACE_EVENT(tcp_probe,
__entry->ssthresh = tcp_current_ssthresh(sk);
__entry->srtt = tp->srtt_us >> 3;
__entry->sock_cookie = sock_gen_cookie(sk);
+
+ __entry->skbaddr = skb;
+ __entry->skaddr = sk;
),
- TP_printk("family=%s src=%pISpc dest=%pISpc mark=%#x data_len=%d snd_nxt=%#x snd_una=%#x snd_cwnd=%u ssthresh=%u snd_wnd=%u srtt=%u rcv_wnd=%u sock_cookie=%llx",
+ TP_printk("family=%s src=%pISpc dest=%pISpc mark=%#x data_len=%d snd_nxt=%#x snd_una=%#x snd_cwnd=%u ssthresh=%u snd_wnd=%u srtt=%u rcv_wnd=%u sock_cookie=%llx skbaddr=%p skaddr=%p",
show_family_name(__entry->family),
__entry->saddr, __entry->daddr, __entry->mark,
__entry->data_len, __entry->snd_nxt, __entry->snd_una,
__entry->snd_cwnd, __entry->ssthresh, __entry->snd_wnd,
- __entry->srtt, __entry->rcv_wnd, __entry->sock_cookie)
+ __entry->srtt, __entry->rcv_wnd, __entry->sock_cookie,
+ __entry->skbaddr, __entry->skaddr)
);
#define TP_STORE_ADDR_PORTS_SKB_V4(__entry, skb) \
--
2.17.1
On Mon, Mar 4, 2024 at 11:46 AM fuyuanli <[email protected]> wrote:
>
> It is useful to expose skb addr and sock addr to user in tracepoint
> tcp_probe, so that we can get more information while monitoring
> receiving of tcp data, by ebpf or other ways.
>
> For example, we need to identify a packet by seq and end_seq when
> calculate transmit latency between lay 2 and lay 4 by ebpf, but which is
> not available in tcp_probe, so we can only use kprobe hooking
> tcp_rcv_esatblised to get them. But we can use tcp_probe directly if skb
> addr and sock addr are available, which is more efficient.
>
> Signed-off-by: fuyuanli <[email protected]>
> Link: https://lore.kernel.org/netdev/20240229052813.GA23899@didi-ThinkCentre-M920t-N000/
Reviewed-by: Jason Xing <[email protected]>
On Mon, Mar 4, 2024 at 4:46 AM fuyuanli <[email protected]> wrote:
>
> It is useful to expose skb addr and sock addr to user in tracepoint
> tcp_probe, so that we can get more information while monitoring
> receiving of tcp data, by ebpf or other ways.
>
> For example, we need to identify a packet by seq and end_seq when
> calculate transmit latency between lay 2 and lay 4 by ebpf, but which is
Please use "layer 2 and layer 4".
> not available in tcp_probe, so we can only use kprobe hooking
> tcp_rcv_esatblised to get them. But we can use tcp_probe directly if skb
> addr and sock addr are available, which is more efficient.
Okay, but please fix the typo. Correct function name is tcp_rcv_established
>
> Signed-off-by: fuyuanli <[email protected]>
> Link: https://lore.kernel.org/netdev/20240229052813.GA23899@didi-ThinkCentre-M920t-N000/
>
Eric Dumazet <[email protected]> 于2024年3月4日周一 16:13写道：
>
> On Mon, Mar 4, 2024 at 4:46 AM fuyuanli <[email protected]> wrote:
> >
> > It is useful to expose skb addr and sock addr to user in tracepoint
> > tcp_probe, so that we can get more information while monitoring
> > receiving of tcp data, by ebpf or other ways.
> >
> > For example, we need to identify a packet by seq and end_seq when
> > calculate transmit latency between lay 2 and lay 4 by ebpf, but which is
>
> Please use "layer 2 and layer 4".
>
> > not available in tcp_probe, so we can only use kprobe hooking
> > tcp_rcv_esatblised to get them. But we can use tcp_probe directly if skb
> > addr and sock addr are available, which is more efficient.
>
> Okay, but please fix the typo. Correct function name is tcp_rcv_established
>
> >
> > Signed-off-by: fuyuanli <[email protected]>
> > Link: https://lore.kernel.org/netdev/20240229052813.GA23899@didi-ThinkCentre-M920t-N000/
> >
>
OK, I will submit a v3 patch, thanks for your review :)
fuyuanli