All of lore.kernel.org
 help / color / mirror / Atom feed
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
To: Bui Quang Minh <minhquangbui99@gmail.com>
Cc: Stanislav Fomichev <stfomichev@gmail.com>,
	<netdev@vger.kernel.org>, Alexei Starovoitov <ast@kernel.org>,
	Daniel Borkmann <daniel@iogearbox.net>,
	"David S. Miller" <davem@davemloft.net>,
	Jakub Kicinski <kuba@kernel.org>,
	Jesper Dangaard Brouer <hawk@kernel.org>,
	John Fastabend <john.fastabend@gmail.com>,
	Eric Dumazet <edumazet@google.com>,
	Paolo Abeni <pabeni@redhat.com>, Simon Horman <horms@kernel.org>,
	Alexander Lobakin <aleksander.lobakin@intel.com>,
	<bpf@vger.kernel.org>, <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH net] xsk: respect the offsets when copying frags
Date: Wed, 23 Apr 2025 20:01:57 +0200	[thread overview]
Message-ID: <aAkrFcSpxwdb+2tA@boxer> (raw)
In-Reply-To: <6ed8452b-f370-4443-94ce-f7d65cd51a9e@gmail.com>

On Wed, Apr 23, 2025 at 09:58:16PM +0700, Bui Quang Minh wrote:
> On 4/23/25 21:41, Stanislav Fomichev wrote:
> > On 04/23, Bui Quang Minh wrote:
> > > Add the missing offsets when copying frags in xdp_copy_frags_from_zc().
> > Can you please share more about how you've hit this problem?
> > I don't see the caller of this function (xdp_build_skb_from_zc)
> > being used at all.
> > 
> > Alexander, do you have plans to use it? Or should we remove it for now?

libeth xdp support uses this:
https://lore.kernel.org/netdev/20250415172825.3731091-15-aleksander.lobakin@intel.com/

> Hi,
> 
> I've been playing around to add support for zerocopy XDP socket with multi
> buffer mergeable buffer in virtio-net (this TODO: https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git/tree/drivers/net/virtio_net.c#n1312).
> In that case, I'll have a XDP buff with frags. When we have XDP_PASS return,
> I need to convert the XDP buff with frags to skb with frags, so I think the
> helper is quite helpful. I used it and got packet dropped due to checksum
> error. Debugging the problem, I've found out this issue which makes the
> skb's frag data incorrect.

Nice! I'll take a look at patch content tomorrow and probably ack it.

> 
> Thanks,
> Quang Minh.

  reply	other threads:[~2025-04-23 18:02 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-04-23 10:10 [PATCH net] xsk: respect the offsets when copying frags Bui Quang Minh
2025-04-23 14:41 ` Stanislav Fomichev
2025-04-23 14:58   ` Bui Quang Minh
2025-04-23 18:01     ` Maciej Fijalkowski [this message]
2025-04-24 14:02 ` Alexander Lobakin
2025-04-24 14:45   ` Bui Quang Minh
2025-04-25  0:29 ` Jakub Kicinski
2025-04-25 15:46 ` Bui Quang Minh
2025-04-26  0:23   ` Jakub Kicinski

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=aAkrFcSpxwdb+2tA@boxer \
    --to=maciej.fijalkowski@intel.com \
    --cc=aleksander.lobakin@intel.com \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=hawk@kernel.org \
    --cc=horms@kernel.org \
    --cc=john.fastabend@gmail.com \
    --cc=kuba@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=minhquangbui99@gmail.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=stfomichev@gmail.com \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.