netdev - Re: [PATCH net-next 00/15] eth: fbnic: support queue API and zero-copy Rx

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Message-ID: <5bba5969-36f4-4a0a-8c03-aea16e2a40de@redhat.com>
Date: Thu, 21 Aug 2025 09:51:55 +0200
From: Paolo Abeni <pabeni@...hat.com>
To: Jakub Kicinski <kuba@...nel.org>
Cc: netdev@...r.kernel.org, edumazet@...gle.com, andrew+netdev@...n.ch,
 horms@...nel.org, almasrymina@...gle.com, michael.chan@...adcom.com,
 tariqt@...dia.com, dtatulea@...dia.com, hawk@...nel.org,
 ilias.apalodimas@...aro.org, alexanderduyck@...com, sdf@...ichev.me,
 davem@...emloft.net
Subject: Re: [PATCH net-next 00/15] eth: fbnic: support queue API and
 zero-copy Rx

On 8/20/25 4:56 AM, Jakub Kicinski wrote:
> Add support for queue API to fbnic, enable zero-copy Rx.
> 
> The first patch adds page_pool_get(), I alluded to this
> new helper when dicussing commit 64fdaa94bfe0 ("net: page_pool:
> allow enabling recycling late, fix false positive warning").
> For page pool-oriented reviewers another patch of interest
> is patch 11, which adds a helper to test whether rxq wants
> to create a unreadable page pool. mlx5 already has this
> sort of a check, we said we will add a helper when more
> drivers need it (IIRC), so I guess now is the time.
> 
> Patches 2-4 reshuffle the Rx init/allocation path to better
> align structures and functions which operate on them. Notably
> patch 2 moves the page pool pointer to the queue struct (from
> NAPI).
> 
> Patch 5 converts the driver to use netmem_ref. The driver has
> separate and explicit buffer queue for scatter / payloads,
> so only references to those are converted.
> 
> Next 5 patches are more boring code shifts.
> 
> Patch 12 adds unreadable memory support to page pool allocation.
> 
> Patch 15 finally adds the support for queue API.
> 
>   $ ./tools/testing/selftests/drivers/net/hw/iou-zcrx.py
>   TAP version 13
>   1..3
>   ok 1 iou-zcrx.test_zcrx
>   ok 2 iou-zcrx.test_zcrx_oneshot
>   ok 3 iou-zcrx.test_zcrx_rss
>   # Totals: pass:3 fail:0 xfail:0 xpass:0 skip:0 error:0

Blindly noting that this series is apparently causing a few H/W
selftests failures, even if i.e. this one:

# ok 2 ping.test_default_v6
# # Exception| Traceback (most recent call last):
# # Exception|   File
"/home/virtme/testing/wt-24/tools/testing/selftests/net/lib/py/ksft.py",
line 244, in ksft_run
# # Exception|     case(*args)
# # Exception|   File
"/home/virtme/testing/wt-24/tools/testing/selftests/drivers/net/./ping.py",
line 173, in test_xdp_generic_sb
# # Exception|     _set_xdp_generic_sb_on(cfg)
# # Exception|   File
"/home/virtme/testing/wt-24/tools/testing/selftests/drivers/net/./ping.py",
line 72, in _set_xdp_generic_sb_on
# # Exception|     cmd(f"ip link set dev {cfg.ifname} mtu 1500
xdpgeneric obj {prog} sec xdp", shell=True)
# # Exception|   File
"/home/virtme/testing/wt-24/tools/testing/selftests/net/lib/py/utils.py",
line 71, in __init__
# # Exception|     self.process(terminate=False, fail=fail, timeout=timeout)
# # Exception|   File
"/home/virtme/testing/wt-24/tools/testing/selftests/net/lib/py/utils.py",
line 91, in process
# # Exception|     raise CmdExitFailure("Command failed: %s\nSTDOUT:
%s\nSTDERR: %s" %
# # Exception| net.lib.py.utils.CmdExitFailure: Command failed: ip link
set dev enp1s0 mtu 1500 xdpgeneric obj
/home/virtme/testing/wt-24/tools/testing/selftests/net/lib/xdp_dummy.bpf.o
sec xdp
# # Exception| STDOUT: b''
# # Exception| STDERR: b'Error: unable to install XDP to device using
tcp-data-split.\n'
# not ok 3 ping.test_xdp_generic_sb

looks more related to commit 2b30fc01a6c788ed4a799ed8a6f42ed9ac82417f
(but ping did not failed back than)

/P