From: Stanislav Fomichev <sdf.kernel@gmail.com>
To: netdev@vger.kernel.org
Cc: davem@davemloft.net, edumazet@google.com, kuba@kernel.org,
pabeni@redhat.com, andrew+netdev@lunn.ch, edumazet@kernel.org,
horms@kernel.org, corbet@lwn.net, skhan@linuxfoundation.org,
rdunlap@infradead.org, michael.chan@broadcom.com,
pavan.chebbi@broadcom.com, sdf@fomichev.me,
almasrymina@google.com, bobbyeshleman@meta.com,
asml.silence@gmail.com, razor@blackwall.org,
daniel@iogearbox.net, leitao@debian.org,
linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-kselftest@vger.kernel.org
Subject: [PATCH net-next v2 0/7] net: devmem: size TX net_iovs from the dmabuf layout
Date: Tue, 3 Nov 2026 15:51:45 -0800 [thread overview]
Message-ID: <20261103235152.1904727-1-sdf@fomichev.me> (raw)
TX bindings use PAGE_SIZE net_iovs, so a frag covers at most a page.
A 64KB skb needs 16 frags, and MAX_SKB_FRAGS caps devmem skbs at about
68KB, which makes BIG TCP ineffective for devmem TX.
This series picks the TX net_iov size from the dmabuf sg table instead:
the largest power of 2, up to 2MB, which aligns every DMA segment. With
a 2MB hugepage-backed udmabuf a BIG TCP skb takes a few frags. There's
no UAPI change since TX addresses are dmabuf offsets.
TCP still bounds skbs by size_goal, so frags get larger, skbs don't.
A single frag can now be as large as the skb, which matters for
NETMEM_TX drivers with tso_max_size above 64KB:
- mlx5: 32-bit length per data segment
- gve: splits frags into 16KB descriptors
- fbnic: keeps the default 64KB tso_max_size
- bnxt: 16-bit BD length, devmem TX frags are capped at 32KB by a new
per-device limit
Tested on two mlx5 400Gb/s hosts with kperf (udmabuf, 32KB RX
net_iovs, 2MB hugepage-backed TX buffer), series backported to a 7.1
kernel on the sender only. 1 flow, MTU 4200, receiver tcp_rmem capped
at 16MB so it doesn't drop, median of 5 x 60s runs:
before after
frags per skb (sender) 16-17 1-2
throughput (Gb/s) 208.6 211.2
sender sendmsg CPU (sys) 40.8% 19.5% (-52%)
The receiver's CPU is the bottleneck, so the gain is CPU, not
throughput. More of the transmit runs from the ACK path, so the
sender's softirq grows (52% -> 59%), but sys + sirq still drops by 16%.
kperf output (sender side) of runs near the median, before:
client: == Source <sender>
client: Tx213.826 Gbps (1603901849600 bytes in 60007723 usec)
client: Rx 0.000 Gbps (0 bytes in 60007723 usec)
client: TCP retrans reord rtt rttvar d_ce snd_wnd cwnd
client: 0 0 633 2 0 15556608 7657
client: net CPU 49: usr: 0.01% sys: 0.10% idle:44.13% iow: 0.00% irq: 3.21% sirq:52.53%
client: app CPU 50: usr: 0.05% sys:41.55% idle:53.88% iow: 0.00% irq: 1.40% sirq: 3.10%
after:
client: == Source <sender>
client: Tx211.242 Gbps (1584440279040 bytes in 60004741 usec)
client: Rx 0.000 Gbps (0 bytes in 60004741 usec)
client: TCP retrans reord rtt rttvar d_ce snd_wnd cwnd
client: 0 0 556 3 0 15499264 7650
client: net CPU 13: usr: 0.01% sys: 0.08% idle:37.75% iow: 0.00% irq: 3.87% sirq:58.26%
client: app CPU 14: usr: 0.06% sys:19.48% idle:77.23% iow: 0.00% irq: 1.19% sirq: 2.02%
The bnxt patches (1 and 5) were tested on two 50Gb/s bnxt hosts with
CONFIG_MAX_SKB_FRAGS=45 (with 17 the check in patch 1 compiles out).
kperf devmem TX from a 2MB hugepage-backed udmabuf runs at line rate
(46.4Gb/s, payload validated) with 2-3 frags per skb, none above 32KB.
ncdevmem sending 1KB chunks builds skbs with up to 45 frags, the stack
segments them and the data arrives intact.
Patches:
- 1: bnxt: segment GSO skbs with too many frags in the stack
- 2-3: devmem TX prep (truesize, niov_shift in the TX lookup)
- 4-5: per-device netmem TX frag size limit, 32KB for bnxt
- 6: pick the TX net_iov size from the sg table
- 7: selftest for TX from a hugepage-backed dmabuf
v2:
- reword the TX truesize commit message (Mina)
- use 1 flow results in the cover letter (Mina)
v1: https://lore.kernel.org/netdev/20261102191438.1059771-1-sdf@fomichev.me/
Stanislav Fomichev (7):
bnxt_en: let the stack segment GSO skbs with too many frags
net: devmem: charge the frag length to TX skb truesize
net: devmem: use niov_shift in net_devmem_get_niov_at()
net: devmem: add a per-device netmem TX frag size limit
bnxt_en: limit netmem TX frags to 32KB
net: devmem: size TX net_iovs from the dmabuf sg table
selftests: drv-net: devmem: TX from a hugepage-backed dmabuf
.../networking/net_cachelines/net_device.rst | 1 +
Documentation/networking/netmem.rst | 6 +++
drivers/net/ethernet/broadcom/bnxt/bnxt.c | 6 +++
include/linux/netdevice.h | 2 +
net/core/datagram.c | 3 +-
net/core/dev.c | 1 +
net/core/devmem.c | 37 +++++++++++++---
net/core/devmem.h | 1 +
net/core/netdev-genl.c | 2 +-
.../selftests/drivers/net/hw/devmem.py | 10 ++++-
.../selftests/drivers/net/hw/devmem_lib.py | 43 +++++++++++++++++--
.../selftests/drivers/net/hw/ncdevmem.c | 8 +++-
.../selftests/drivers/net/hw/nk_devmem.py | 11 ++++-
13 files changed, 115 insertions(+), 16 deletions(-)
--
2.53.0-Meta
next reply other threads:[~2026-11-03 23:51 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-03 23:51 Stanislav Fomichev [this message]
2026-11-03 23:51 ` [PATCH net-next v2 1/7] bnxt_en: let the stack segment GSO skbs with too many frags Stanislav Fomichev
2026-11-04 16:47 ` Breno Leitao
2026-11-04 17:31 ` Michael Chan
2026-11-03 23:51 ` [PATCH net-next v2 2/7] net: devmem: charge the frag length to TX skb truesize Stanislav Fomichev
2026-11-03 23:51 ` [PATCH net-next v2 3/7] net: devmem: use niov_shift in net_devmem_get_niov_at() Stanislav Fomichev
2026-11-03 23:51 ` [PATCH net-next v2 4/7] net: devmem: add a per-device netmem TX frag size limit Stanislav Fomichev
2026-11-04 15:41 ` Mina Almasry
2026-11-05 17:53 ` Stanislav Fomichev
2026-11-03 23:51 ` [PATCH net-next v2 5/7] bnxt_en: limit netmem TX frags to 32KB Stanislav Fomichev
2026-11-04 17:35 ` Michael Chan
2026-11-03 23:51 ` [PATCH net-next v2 6/7] net: devmem: size TX net_iovs from the dmabuf sg table Stanislav Fomichev
2026-11-03 23:51 ` [PATCH net-next v2 7/7] selftests: drv-net: devmem: TX from a hugepage-backed dmabuf Stanislav Fomichev
2026-11-04 14:43 ` Dragos Tatulea
2026-11-05 17:50 ` Stanislav Fomichev
2026-11-04 0:14 ` [PATCH net-next v2 0/7] net: devmem: size TX net_iovs from the dmabuf layout Mina Almasry
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=20261103235152.1904727-1-sdf@fomichev.me \
--to=sdf.kernel@gmail.com \
--cc=almasrymina@google.com \
--cc=andrew+netdev@lunn.ch \
--cc=asml.silence@gmail.com \
--cc=bobbyeshleman@meta.com \
--cc=corbet@lwn.net \
--cc=daniel@iogearbox.net \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=edumazet@kernel.org \
--cc=horms@kernel.org \
--cc=kuba@kernel.org \
--cc=leitao@debian.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-kselftest@vger.kernel.org \
--cc=michael.chan@broadcom.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=pavan.chebbi@broadcom.com \
--cc=razor@blackwall.org \
--cc=rdunlap@infradead.org \
--cc=sdf@fomichev.me \
--cc=skhan@linuxfoundation.org \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®