From: Tariq Toukan <tariqt@nvidia.com>
To: Eric Dumazet <edumazet@google.com>,
Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
Andrew Lunn <andrew+netdev@lunn.ch>,
"David S. Miller" <davem@davemloft.net>
Cc: Saeed Mahameed <saeedm@nvidia.com>,
Leon Romanovsky <leon@kernel.org>,
Tariq Toukan <tariqt@nvidia.com>, Mark Bloch <mbloch@nvidia.com>,
"Alexei Starovoitov" <ast@kernel.org>,
Daniel Borkmann <daniel@iogearbox.net>,
"Jesper Dangaard Brouer" <hawk@kernel.org>,
John Fastabend <john.fastabend@gmail.com>,
Richard Cochran <richardcochran@gmail.com>,
<netdev@vger.kernel.org>, <linux-rdma@vger.kernel.org>,
<linux-kernel@vger.kernel.org>, <bpf@vger.kernel.org>,
Gal Pressman <gal@nvidia.com>,
Dragos Tatulea <dtatulea@nvidia.com>,
Cosmin Ratiu <cratiu@nvidia.com>,
Pavel Begunkov <asml.silence@gmail.com>,
David Wei <dw@davidwei.uk>
Subject: [PATCH net-next 00/15] net/mlx5e: SHAMPO, Allow high order pages in zerocopy mode
Date: Mon, 23 Feb 2026 22:41:40 +0200 [thread overview]
Message-ID: <20260223204155.1783580-1-tariqt@nvidia.com> (raw)
Hi,
This series adds support for high order pages when io_uring/devmem
zero copy is used.
See detailed description by Dragos below.
Regards,
Tariq
The first patches are moving code around to allow using queue specific
parameters that are not just for XSK. They are a bit large as they touch
a lot of functions.
The middle part of the series is updating various formulas to remove
remaining hardcoded use of PAGE_SIZE/PAGE_SHIFT.
The last part adds support for high order pages by implementing the
queue configuration functions and allowing larger rx_page_size
configurations when in zero-copy mode.
Results show an increase in BW and a decrease in CPU usage.
The benchmark was done with the zcrx samples from liburing [0].
rx_buf_len=4K, oncpu [1]:
packets=3358832 (MB=820027), rps=55794 (MB/s=13621)
Average: CPU %usr %nice %sys %iowait %irq %soft %steal %guest %gnice %idle
Average: 9 1.56 0.00 18.09 13.42 0.00 66.80 0.00 0.00 0.00 0.12
rx_buf_len=128K, oncpu [2]:
packets=3781376 (MB=923187), rps=62813 (MB/s=15335)
Average: CPU %usr %nice %sys %iowait %irq %soft %steal %guest %gnice %idle
Average: 9 0.33 0.00 7.61 18.86 0.00 73.08 0.00 0.00 0.00 0.12
rx_buf_len=4K, offcpu [3]:
packets=3460368 (MB=844816), rps=57481 (MB/s=14033)
Average: CPU %usr %nice %sys %iowait %irq %soft %steal %guest %gnice %idle
Average: 9 0.00 0.00 0.26 0.00 0.00 92.63 0.00 0.00 0.00 7.11
Average: 11 3.04 0.00 68.09 28.87 0.00 0.00 0.00 0.00 0.00 0.00
rx_buf_len=128K, offcpu [4]:
packets=4119840 (MB=1005820), rps=68435 (MB/s=16707)
Average: CPU %usr %nice %sys %iowait %irq %soft %steal %guest %gnice %idle
Average: 9 0.00 0.00 0.87 0.00 0.00 63.77 0.00 0.00 0.00 35.36
Average: 11 1.96 0.00 43.68 54.37 0.00 0.00 0.00 0.00 0.00 0.00
[0] https://github.com/isilence/liburing/tree/zcrx/rx-buf-len
[1] commands:
$> taskset -c 9 ./zcrx 6 -i eth2 -q 9 -A 1 -B 4096 -S 33554432
$> ./send-zerocopy tcp -6 -D 2001:db8::1 -t 60 -C 0 -l 1 -b 1 -n 1 -z 1 -d -s 256000
[2] commands:
$> taskset -c 9 ./zcrx 6 -i eth2 -q 9 -A 1 -B 131072 -S 33554432
$> ./send-zerocopy tcp -6 -D 2001:db8::1 -t 60 -C 0 -l 1 -b 1 -n 1 -z 1 -d -s 256000
[3] commands:
$> taskset -c 11 ./zcrx 6 -i eth2 -q 9 -A 1 -B 4096 -S 33554432
$> ./send-zerocopy tcp -6 -D 2001:db8::1 -t 60 -C 0 -l 1 -b 1 -n 1 -z 1 -d -s 256000
[4] commands:
$> taskset -c 11 ./zcrx 6 -i eth2 -q 9 -A 1 -B 131072 -S 33554432
$> ./send-zerocopy tcp -6 -D 2001:db8::1 -t 60 -C 0 -l 1 -b 1 -n 1 -z 1 -d -s 256000
Dragos Tatulea (15):
net/mlx5e: Make mlx5e_rq_param naming consistent
net/mlx5e: Extract striding rq param calculation in function
net/mlx5e: Extract max_xsk_wqebbs into its own function
net/mlx5e: Expose and rename xsk channel parameter function
net/mlx5e: Alloc xsk channel param out of mlx5e_open_xsk()
net/mlx5e: Move xsk param into new option container struct
net/mlx5e: Drop unused channel parameters
net/mlx5e: SHAMPO, Always calculate page size
net/mlx5e: Set page_pool order based on calculated page_shift
net/mlx5e: Alloc rq drop page based on calculated page_shift
net/mlx5e: RX, Make page frag bias more robust
net/mlx5e: Add queue config ops for page size
net/mlx5e: Pass netdev queue config to param calculations
net/mlx5e: Add param helper to calculate max page size
net/mlx5e: SHAMPO, Allow high order pages in zerocopy mode
drivers/net/ethernet/mellanox/mlx5/core/en.h | 9 +-
.../ethernet/mellanox/mlx5/core/en/params.c | 415 +++++++++++-------
.../ethernet/mellanox/mlx5/core/en/params.h | 45 +-
.../net/ethernet/mellanox/mlx5/core/en/ptp.c | 4 +-
.../net/ethernet/mellanox/mlx5/core/en/xdp.c | 5 +-
.../net/ethernet/mellanox/mlx5/core/en/xdp.h | 3 +-
.../ethernet/mellanox/mlx5/core/en/xsk/pool.c | 23 +-
.../mellanox/mlx5/core/en/xsk/setup.c | 59 +--
.../mellanox/mlx5/core/en/xsk/setup.h | 6 +-
.../net/ethernet/mellanox/mlx5/core/en_main.c | 194 +++++---
.../net/ethernet/mellanox/mlx5/core/en_rx.c | 36 +-
11 files changed, 502 insertions(+), 297 deletions(-)
base-commit: 8bf22c33e7a172fbc72464f4cc484d23a6b412ba
--
2.44.0
next reply other threads:[~2026-02-23 20:43 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-02-23 20:41 Tariq Toukan [this message]
2026-02-23 20:41 ` [PATCH net-next 01/15] net/mlx5e: Make mlx5e_rq_param naming consistent Tariq Toukan
2026-02-23 20:41 ` [PATCH net-next 02/15] net/mlx5e: Extract striding rq param calculation in function Tariq Toukan
2026-02-23 20:41 ` [PATCH net-next 03/15] net/mlx5e: Extract max_xsk_wqebbs into its own function Tariq Toukan
2026-02-23 20:41 ` [PATCH net-next 04/15] net/mlx5e: Expose and rename xsk channel parameter function Tariq Toukan
2026-02-23 20:41 ` [PATCH net-next 05/15] net/mlx5e: Alloc xsk channel param out of mlx5e_open_xsk() Tariq Toukan
2026-02-23 20:41 ` [PATCH net-next 06/15] net/mlx5e: Move xsk param into new option container struct Tariq Toukan
2026-02-23 20:41 ` [PATCH net-next 07/15] net/mlx5e: Drop unused channel parameters Tariq Toukan
2026-02-23 20:41 ` [PATCH net-next 08/15] net/mlx5e: SHAMPO, Always calculate page size Tariq Toukan
2026-02-23 20:41 ` [PATCH net-next 09/15] net/mlx5e: Set page_pool order based on calculated page_shift Tariq Toukan
2026-02-23 20:41 ` [PATCH net-next 10/15] net/mlx5e: Alloc rq drop page " Tariq Toukan
2026-02-23 20:41 ` [PATCH net-next 11/15] net/mlx5e: RX, Make page frag bias more robust Tariq Toukan
2026-02-23 20:41 ` [PATCH net-next 12/15] net/mlx5e: Add queue config ops for page size Tariq Toukan
2026-02-23 20:41 ` [PATCH net-next 13/15] net/mlx5e: Pass netdev queue config to param calculations Tariq Toukan
2026-02-23 20:41 ` [PATCH net-next 14/15] net/mlx5e: Add param helper to calculate max page size Tariq Toukan
2026-02-23 20:41 ` [PATCH net-next 15/15] net/mlx5e: SHAMPO, Allow high order pages in zerocopy mode Tariq Toukan
2026-02-26 10:10 ` [PATCH net-next 00/15] " patchwork-bot+netdevbpf
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=20260223204155.1783580-1-tariqt@nvidia.com \
--to=tariqt@nvidia.com \
--cc=andrew+netdev@lunn.ch \
--cc=asml.silence@gmail.com \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=cratiu@nvidia.com \
--cc=daniel@iogearbox.net \
--cc=davem@davemloft.net \
--cc=dtatulea@nvidia.com \
--cc=dw@davidwei.uk \
--cc=edumazet@google.com \
--cc=gal@nvidia.com \
--cc=hawk@kernel.org \
--cc=john.fastabend@gmail.com \
--cc=kuba@kernel.org \
--cc=leon@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=mbloch@nvidia.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=richardcochran@gmail.com \
--cc=saeedm@nvidia.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox