[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID:
<AS1PR10MB56759C0DC193825B6BCC41D0EBD62@AS1PR10MB5675.EURPRD10.PROD.OUTLOOK.COM>
Date: Mon, 10 Mar 2025 08:08:27 +0000
From: "Bouska, Zdenek" <zdenek.bouska@...mens.com>
To: "Song, Yoong Siang" <yoong.siang.song@...el.com>, "David S . Miller"
<davem@...emloft.net>, Eric Dumazet <edumazet@...gle.com>, Jakub Kicinski
<kuba@...nel.org>, Paolo Abeni <pabeni@...hat.com>, Simon Horman
<horms@...nel.org>, Willem de Bruijn <willemb@...gle.com>, "Bezdeka, Florian"
<florian.bezdeka@...mens.com>, Donald Hunter <donald.hunter@...il.com>,
Jonathan Corbet <corbet@....net>, Bjorn Topel <bjorn@...nel.org>, "Karlsson,
Magnus" <magnus.karlsson@...el.com>, "Fijalkowski, Maciej"
<maciej.fijalkowski@...el.com>, Jonathan Lemon <jonathan.lemon@...il.com>,
Andrew Lunn <andrew+netdev@...n.ch>, Alexei Starovoitov <ast@...nel.org>,
Daniel Borkmann <daniel@...earbox.net>, Jesper Dangaard Brouer
<hawk@...nel.org>, John Fastabend <john.fastabend@...il.com>, "Damato, Joe"
<jdamato@...tly.com>, Stanislav Fomichev <sdf@...ichev.me>, Xuan Zhuo
<xuanzhuo@...ux.alibaba.com>, Mina Almasry <almasrymina@...gle.com>, Daniel
Jurgens <danielj@...dia.com>, Andrii Nakryiko <andrii@...nel.org>, Eduard
Zingerman <eddyz87@...il.com>, Mykola Lysenko <mykolal@...com>, Martin KaFai
Lau <martin.lau@...ux.dev>, Song Liu <song@...nel.org>, Yonghong Song
<yonghong.song@...ux.dev>, KP Singh <kpsingh@...nel.org>, Hao Luo
<haoluo@...gle.com>, Jiri Olsa <jolsa@...nel.org>, Shuah Khan
<shuah@...nel.org>, Alexandre Torgue <alexandre.torgue@...s.st.com>, Jose
Abreu <joabreu@...opsys.com>, Maxime Coquelin <mcoquelin.stm32@...il.com>,
"Nguyen, Anthony L" <anthony.l.nguyen@...el.com>, "Kitszel, Przemyslaw"
<przemyslaw.kitszel@...el.com>, Faizal Rahim
<faizal.abdul.rahim@...ux.intel.com>, Choong Yong Liang
<yong.liang.choong@...ux.intel.com>
CC: "netdev@...r.kernel.org" <netdev@...r.kernel.org>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
"linux-doc@...r.kernel.org" <linux-doc@...r.kernel.org>,
"bpf@...r.kernel.org" <bpf@...r.kernel.org>,
"linux-kselftest@...r.kernel.org" <linux-kselftest@...r.kernel.org>,
"linux-stm32@...md-mailman.stormreply.com"
<linux-stm32@...md-mailman.stormreply.com>,
"linux-arm-kernel@...ts.infradead.org"
<linux-arm-kernel@...ts.infradead.org>, "intel-wired-lan@...ts.osuosl.org"
<intel-wired-lan@...ts.osuosl.org>, "xdp-hints@...-project.net"
<xdp-hints@...-project.net>
Subject: RE: [PATCH bpf-next v12 5/5] igc: Add launch time support to XDP ZC
> -----Original Message-----
> From: Song, Yoong Siang <yoong.siang.song@...el.com>
> Sent: Friday, March 7, 2025 3:21 PM
>
> On Friday, March 7, 2025 9:25 PM, Bouska, Zdenek
> <zdenek.bouska@...mens.com> wrote:
>
> [...]
>
> >> @@ -2996,7 +3035,13 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring)
> >> ntu = ring->next_to_use;
> >> budget = igc_desc_unused(ring);
> >>
> >> - while (xsk_tx_peek_desc(pool, &xdp_desc) && budget--) {
> >> + /* Packets with launch time require one data descriptor and one context
> >> + * descriptor. When the launch time falls into the next Qbv cycle, we
> >> + * may need to insert an empty packet, which requires two more
> >> + * descriptors. Therefore, to be safe, we always ensure we have at least
> >> + * 4 descriptors available.
> >> + */
> >> + while (xsk_tx_peek_desc(pool, &xdp_desc) && budget >= 4) {
> >
> >I think that here is a bug: some frames could be missed if budget < 4.
> >I was able to reproduce it by sending 100000x 60 B frames with minimal IPG
> >(672 ns between starts of frames) on 1Gbit/s. Always 1026 frames were not sent
> >and were missing a AF_XDP competition. Interesting was that then even when I
> >sent more
> >frames for hours it still was 1026 frames not sent and missing competition.
> >
> >Bug seems to be fixed when I change this line to:
> >
> > while (budget >= 4 && xsk_tx_peek_desc(pool, &xdp_desc)) {
> >
> >Do you think this is a good fix?
> >
> >I think this bug is also in original code base, but I was only able to reproduce
> >it with launch time.
> >
>
> Thank you for pointing out this issue and for providing a detailed
> explanation of your findings. I personally agree with your proposed fix
> that make sure there is enough budget in the driver, before go peek the xsk
> descriptor. Do you plan to submit bug fix patch to iwl-net?
>
Yes, I plan to submit bug fix patch.
Best regards,
Zdenek Bouska
--
Siemens, s.r.o
Foundational Technologies
Powered by blists - more mailing lists