[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <CAHS8izPr_yt+PtG5Q++Ub=D4J=H7nP0S_7rOP9G7W=i2Zeau3g@mail.gmail.com>
Date: Fri, 2 May 2025 12:25:23 -0700
From: Mina Almasry <almasrymina@...gle.com>
To: Paolo Abeni <pabeni@...hat.com>
Cc: netdev@...r.kernel.org, linux-kernel@...r.kernel.org,
linux-doc@...r.kernel.org, io-uring@...r.kernel.org,
virtualization@...ts.linux.dev, kvm@...r.kernel.org,
linux-kselftest@...r.kernel.org, "David S. Miller" <davem@...emloft.net>,
Eric Dumazet <edumazet@...gle.com>, Jakub Kicinski <kuba@...nel.org>, Simon Horman <horms@...nel.org>,
Donald Hunter <donald.hunter@...il.com>, Jonathan Corbet <corbet@....net>,
Andrew Lunn <andrew+netdev@...n.ch>, Jeroen de Borst <jeroendb@...gle.com>,
Harshitha Ramamurthy <hramamurthy@...gle.com>, Kuniyuki Iwashima <kuniyu@...zon.com>,
Willem de Bruijn <willemb@...gle.com>, Jens Axboe <axboe@...nel.dk>,
Pavel Begunkov <asml.silence@...il.com>, David Ahern <dsahern@...nel.org>,
Neal Cardwell <ncardwell@...gle.com>, "Michael S. Tsirkin" <mst@...hat.com>, Jason Wang <jasowang@...hat.com>,
Xuan Zhuo <xuanzhuo@...ux.alibaba.com>, Eugenio Pérez <eperezma@...hat.com>,
Stefan Hajnoczi <stefanha@...hat.com>, Stefano Garzarella <sgarzare@...hat.com>, Shuah Khan <shuah@...nel.org>,
sdf@...ichev.me, dw@...idwei.uk, Jamal Hadi Salim <jhs@...atatu.com>,
Victor Nogueira <victor@...atatu.com>, Pedro Tammela <pctammela@...atatu.com>,
Samiullah Khawaja <skhawaja@...gle.com>, Kaiyuan Zhang <kaiyuanz@...gle.com>
Subject: Re: [PATCH net-next v13 4/9] net: devmem: Implement TX path
On Fri, May 2, 2025 at 4:51 AM Paolo Abeni <pabeni@...hat.com> wrote:
>
> On 5/2/25 1:47 PM, Paolo Abeni wrote:
> > On 4/29/25 5:26 AM, Mina Almasry wrote:
> >> Augment dmabuf binding to be able to handle TX. Additional to all the RX
> >> binding, we also create tx_vec needed for the TX path.
> >>
> >> Provide API for sendmsg to be able to send dmabufs bound to this device:
> >>
> >> - Provide a new dmabuf_tx_cmsg which includes the dmabuf to send from.
> >> - MSG_ZEROCOPY with SCM_DEVMEM_DMABUF cmsg indicates send from dma-buf.
> >>
> >> Devmem is uncopyable, so piggyback off the existing MSG_ZEROCOPY
> >> implementation, while disabling instances where MSG_ZEROCOPY falls back
> >> to copying.
> >>
> >> We additionally pipe the binding down to the new
> >> zerocopy_fill_skb_from_devmem which fills a TX skb with net_iov netmems
> >> instead of the traditional page netmems.
> >>
> >> We also special case skb_frag_dma_map to return the dma-address of these
> >> dmabuf net_iovs instead of attempting to map pages.
> >>
> >> The TX path may release the dmabuf in a context where we cannot wait.
> >> This happens when the user unbinds a TX dmabuf while there are still
> >> references to its netmems in the TX path. In that case, the netmems will
> >> be put_netmem'd from a context where we can't unmap the dmabuf, Resolve
> >> this by making __net_devmem_dmabuf_binding_free schedule_work'd.
> >>
> >> Based on work by Stanislav Fomichev <sdf@...ichev.me>. A lot of the meat
> >> of the implementation came from devmem TCP RFC v1[1], which included the
> >> TX path, but Stan did all the rebasing on top of netmem/net_iov.
> >>
> >> Cc: Stanislav Fomichev <sdf@...ichev.me>
> >> Signed-off-by: Kaiyuan Zhang <kaiyuanz@...gle.com>
> >> Signed-off-by: Mina Almasry <almasrymina@...gle.com>
> >> Acked-by: Stanislav Fomichev <sdf@...ichev.me>
> >
> > I'm sorry for the late feedback. A bunch of things I did not notice
> > before...
>
> The rest LGTM,
Does this imply I should attach your Reviewed-by or Acked-by on follow
up submissions if any? I'm happy either way, just checking.
> and my feedback here ranges from nit to corner-cases, so
> we are probably better off with a follow-up than with a repost, other
> opinions welcome!
>
Agreed a follow-up is better, but up to you and other maintainers.
There is some mounting urgency on my side (we're in the process of
optimistical backports and migrating the devmem TCP userspace that we
previously open sourced to the upstream UAPI), but we'll oblige either
way.
--
Thanks,
Mina
Powered by blists - more mailing lists