netdev - Re: [Intel-wired-lan] Increased memory usage on NUMA nodes with ICE driver after upgrade to 6.13.y (regression in commit 492a044508ad)

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>] [day] [month] [year] [list]

Message-ID: <1c43ebac-2334-473d-b3dc-de26bf5abca7@molgen.mpg.de>
Date: Wed, 25 Jun 2025 16:53:06 +0200
From: Paul Menzel <pmenzel@...gen.mpg.de>
To: Jaroslav Pulchart <jaroslav.pulchart@...ddata.com>
Cc: Jacob E Keller <jacob.e.keller@...el.com>,
 Jakub Kicinski <kuba@...nel.org>,
 Przemyslaw Kitszel <przemyslaw.kitszel@...el.com>,
 Joe Damato <jdamato@...tly.com>, intel-wired-lan@...ts.osuosl.org,
 netdev@...r.kernel.org, Anthony L Nguyen <anthony.l.nguyen@...el.com>,
 Michal Swiatkowski <michal.swiatkowski@...ux.intel.com>,
 Lukasz Czapnik <lukasz.czapnik@...el.com>, Eric Dumazet
 <edumazet@...gle.com>, Ahmed Zaki <ahmed.zaki@...el.com>,
 Martin Karsten <mkarsten@...terloo.ca>, Igor Raits <igor@...ddata.com>,
 Daniel Secik <daniel.secik@...ddata.com>,
 Zdenek Pesek <zdenek.pesek@...ddata.com>, regressions@...ts.linux.dev
Subject: Re: [Intel-wired-lan] Increased memory usage on NUMA nodes with ICE
 driver after upgrade to 6.13.y (regression in commit 492a044508ad)

Dear Jaroslav,


Am 25.06.25 um 14:17 schrieb Jaroslav Pulchart:

> We are still facing the memory issue with Intel 810 NICs (even on latest
> 6.15.y).

Commit 492a044508ad13 ("ice: Add support for persistent NAPI config") 
was added in Linux v6.13-rc1, and as until now, no fix could be 
presented, but reverting it fixes your issue, I strongly recommend to 
send a revert. No idea if it’s compiler depended or what else could be 
the issue. But due to Linux’ no regression policy this should be 
reverted as soon as possible.


Kind regards,

Paul