From: Bobby Eshleman <bobbyeshleman@gmail.com>
To: Zhu Yanjun <yanjun.zhu@linux.dev>
Cc: Andrew Lunn <andrew+netdev@lunn.ch>,
"David S. Miller" <davem@davemloft.net>,
Eric Dumazet <edumazet@google.com>,
Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
Simon Horman <horms@kernel.org>, Jonathan Corbet <corbet@lwn.net>,
Shuah Khan <skhan@linuxfoundation.org>,
Alex Shi <alexs@kernel.org>, Yanteng Si <si.yanteng@linux.dev>,
Dongliang Mu <dzm91@hust.edu.cn>,
Michael Chan <michael.chan@broadcom.com>,
Pavan Chebbi <pavan.chebbi@broadcom.com>,
Joshua Washington <joshwash@google.com>,
Harshitha Ramamurthy <hramamurthy@google.com>,
Saeed Mahameed <saeedm@nvidia.com>,
Tariq Toukan <tariqt@nvidia.com>, Mark Bloch <mbloch@nvidia.com>,
Leon Romanovsky <leon@kernel.org>,
Alexander Duyck <alexanderduyck@fb.com>,
kernel-team@meta.com, Daniel Borkmann <daniel@iogearbox.net>,
Nikolay Aleksandrov <razor@blackwall.org>,
Shuah Khan <shuah@kernel.org>,
dw@davidwei.uk, sdf.kernel@gmail.com, mohsin.bashr@gmail.com,
willemb@google.com, jiang.kun2@zte.com.cn, xu.xin16@zte.com.cn,
wang.yaxin@zte.com.cn, netdev@vger.kernel.org,
linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-rdma@vger.kernel.org, bpf@vger.kernel.org,
linux-kselftest@vger.kernel.org,
Stanislav Fomichev <sdf@fomichev.me>,
Mina Almasry <almasrymina@google.com>,
Bobby Eshleman <bobbyeshleman@meta.com>
Subject: Re: [PATCH net-next v3 0/8] net: devmem: support devmem with netkit devices
Date: Mon, 11 May 2026 10:01:25 -0700 [thread overview]
Message-ID: <agILZaYTrRBlL+Dt@devvm29614.prn0.facebook.com> (raw)
In-Reply-To: <d7de2f17-af2d-4b6a-be65-f009d78e3d20@linux.dev>
On Sun, May 10, 2026 at 01:33:18PM -0700, Zhu Yanjun wrote:
> 在 2026/5/7 19:27, Bobby Eshleman 写道:
> > This series enables TCP devmem TX through netkit devices.
> >
> > Netkit now supports queue leasing. A physical NIC's RX queue can be
> > leased to a netkit guest interface inside a container namespace. This
> > gives the container a devmem-capable data path on the RX side (bind-rx,
> > etc...). On the TX side, the container process binds to its netkit guest
> > interface and sends traffic that netkit redirects (via BPF or ip
> > forwarding) to the physical NIC for DMA.
> >
> > Two things in the existing devmem TX path prevent this from working:
> >
> > 1. validate_xmit_unreadable_skb() requires dev->netmem_tx before it will
> > forward a dmabuf-backed (unreadable) skb. This protects skbs from
> > landing on devices that don't have the IOMMU mappings for the backing
> > dmabuf or that don't speak netmem. Netkit, however, does not support
> > DMA, doesn't attempt to read unreadable skb pages and so doesn't
> > break netmem (it is pure skb routing and redirection). It is
> > functionally capable of routing unreadable skbs, but there is no way
> > for the TX validation pathway to distinguish between a device that
> > will actually attempt DMA-ing the skb and another device
> > (like netkit) that does not DMA but also does not break
> > netmem.
> >
> > 2. bind_tx_doit uses the bound device as the DMA device. When the user
> > binds devmem TX to the netkit guest, the bind handler attempts to
> > create DMA mappings against netkit, which has no DMA capability and
> > no IOMMU mappings.
> >
> > This series solves these problems as follows:
> >
> > 1. Extend netmem_tx to two bits, assigned to one of three values:
> >
> > NETMEM_TX_NONE - netmem not supported
> > NETMEM_TX_DMA - netmem supported and performs DMA
> > NETMEM_TX_NO_DMA - netmem supported, but does not DMA
> >
> > With these bits, phys devices can set NETMEM_TX_DMA and devices like
> > netkit set NETMEM_TX_NO_DMA. The validation TX path ensures that any
> > DMA-capable netdev exactly matches the bound device, guaranteeing the
> > correct mapping of the bound dmabuf. The validation TX path also
> > allows devices with NETMEM_TX_NO_DMA to pass, knowing these devices
> > will not misuse netmem or run into IOMMU faults. After redirection or
> > routing and the skb finally makes its way through the stack to a
> > physical device's TX path, the above NETMEM_TX_DMA check is performed
> > again to guarantee the device has the appropriate binding/mappings.
> >
> > 2. On TX bind, the bind handler recognizes NETMEM_TX_NO_DMA devices and
> > finds the phys TX device and binds to that instead. For the netkit
> > case, if it has been leased a queue from a DMA-capable device
> > already, then the bind action is performed on the DMA-capable device
> > instead and the dmabuf is mapped correctly.
> >
> > ---
> > Changes in v3:
> > - Fix validate_xmit_unreadable_skb() logic for non-devmem
> > unreadable niovs (should not be dropped) (Sashiko)
> > - Simplify lock handling in bind_tx, no premature release (Jakub)
> > - split NO_DMA changes into separate patch (Jakub)
> > - fixed some pylint issues, one required an additional patch ("selftests:
> > drv-net: make attr _nk_guest_ifname public") to rename a variable from
> > private to public
> > - see per-patch changelist for more detailed changes
> > - Link to v2: https://lore.kernel.org/r/20260504-tcp-dm-netkit-v2-0-56d52ac72fd4@meta.com
> >
> > Changes in v2:
> > - Squash driver conversion patches (2-5) into patch 1 (Jakub)
> > - In validate_xmit_unreadable_skb() to check netmem_tx mode before inspecting
> > frags (Jakub)
> > - Lock bind_dev around netdev_queue_get_dma_dev() when bind_dev != netdev to
> > fix lockdep (Sashiko)
> > - Move require_devmem() into individual test functions so KsftSkipEx goes up to
> > ksft_run() (Sashiko)
> > - Add nk_devmem.py to TEST_PROGS in Makefile (Sashiko)
> > - Link to v1:
> > https://lore.kernel.org/all/20260428-tcp-dm-netkit-v1-0-719280eba4d2@meta.com/
> >
> > Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
> >
> > ---
> > Bobby Eshleman (8):
> > net: convert netmem_tx flag to enum
> > net: netkit: declare NETMEM_TX_NO_DMA mode
> > net: devmem: support TX over NETMEM_TX_NO_DMA devices
>
> I applied this patchset in my local kernel tree and built a new kernel
> image. I loaded this new kernel image in my test environment. It seems that
> all the testcases can pass.
>
> I think that this patchset would not cause any regression problem in my test
> environment.
>
> Zhu Yanjun
Thanks for testing!
Best,
Bobby
prev parent reply other threads:[~2026-05-11 17:01 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-05-08 2:27 [PATCH net-next v3 0/8] net: devmem: support devmem with netkit devices Bobby Eshleman
2026-05-08 2:27 ` [PATCH net-next v3 1/8] net: convert netmem_tx flag to enum Bobby Eshleman
2026-05-08 14:56 ` Stanislav Fomichev
2026-05-08 16:11 ` Bobby Eshleman
2026-05-08 2:27 ` [PATCH net-next v3 2/8] net: netkit: declare NETMEM_TX_NO_DMA mode Bobby Eshleman
2026-05-08 14:57 ` Stanislav Fomichev
2026-05-08 2:27 ` [PATCH net-next v3 3/8] net: devmem: support TX over NETMEM_TX_NO_DMA devices Bobby Eshleman
2026-05-08 15:01 ` Stanislav Fomichev
2026-05-08 16:19 ` Bobby Eshleman
2026-05-08 20:44 ` Jakub Kicinski
2026-05-08 20:47 ` Jakub Kicinski
2026-05-08 21:28 ` Bobby Eshleman
2026-05-08 22:27 ` Jakub Kicinski
2026-05-08 23:03 ` Bobby Eshleman
2026-05-08 2:27 ` [PATCH net-next v3 4/8] selftests: drv-net: ncdevmem: add -n flag to skip NIC configuration Bobby Eshleman
2026-05-08 15:01 ` Stanislav Fomichev
2026-05-08 2:27 ` [PATCH net-next v3 5/8] selftests: drv-net: make attr _nk_guest_ifname public Bobby Eshleman
2026-05-08 15:01 ` Stanislav Fomichev
2026-05-08 2:27 ` [PATCH net-next v3 6/8] selftests: drv-net: refactor devmem command builders into lib module Bobby Eshleman
2026-05-08 15:03 ` Stanislav Fomichev
2026-05-08 16:19 ` Bobby Eshleman
2026-05-08 2:27 ` [PATCH net-next v3 7/8] selftests: drv-net: add primary_rx_redirect support to NetDrvContEnv Bobby Eshleman
2026-05-08 15:03 ` Stanislav Fomichev
2026-05-08 2:27 ` [PATCH net-next v3 8/8] selftests: drv-net: add netkit devmem tests Bobby Eshleman
2026-05-08 15:03 ` Stanislav Fomichev
2026-05-10 20:33 ` [PATCH net-next v3 0/8] net: devmem: support devmem with netkit devices Zhu Yanjun
2026-05-11 17:01 ` Bobby Eshleman [this message]
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=agILZaYTrRBlL+Dt@devvm29614.prn0.facebook.com \
--to=bobbyeshleman@gmail.com \
--cc=alexanderduyck@fb.com \
--cc=alexs@kernel.org \
--cc=almasrymina@google.com \
--cc=andrew+netdev@lunn.ch \
--cc=bobbyeshleman@meta.com \
--cc=bpf@vger.kernel.org \
--cc=corbet@lwn.net \
--cc=daniel@iogearbox.net \
--cc=davem@davemloft.net \
--cc=dw@davidwei.uk \
--cc=dzm91@hust.edu.cn \
--cc=edumazet@google.com \
--cc=horms@kernel.org \
--cc=hramamurthy@google.com \
--cc=jiang.kun2@zte.com.cn \
--cc=joshwash@google.com \
--cc=kernel-team@meta.com \
--cc=kuba@kernel.org \
--cc=leon@kernel.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-kselftest@vger.kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=mbloch@nvidia.com \
--cc=michael.chan@broadcom.com \
--cc=mohsin.bashr@gmail.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=pavan.chebbi@broadcom.com \
--cc=razor@blackwall.org \
--cc=saeedm@nvidia.com \
--cc=sdf.kernel@gmail.com \
--cc=sdf@fomichev.me \
--cc=shuah@kernel.org \
--cc=si.yanteng@linux.dev \
--cc=skhan@linuxfoundation.org \
--cc=tariqt@nvidia.com \
--cc=wang.yaxin@zte.com.cn \
--cc=willemb@google.com \
--cc=xu.xin16@zte.com.cn \
--cc=yanjun.zhu@linux.dev \
/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.