[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <841680ea-1086-4380-910e-8a836b711a42@amd.com>
Date: Fri, 31 Oct 2025 09:44:28 +0100
From: Christian König <christian.koenig@....com>
To: Marco Crivellari <marco.crivellari@...e.com>
Cc: linux-kernel@...r.kernel.org, amd-gfx@...ts.freedesktop.org,
dri-devel@...ts.freedesktop.org, Tejun Heo <tj@...nel.org>,
Lai Jiangshan <jiangshanlai@...il.com>,
Frederic Weisbecker <frederic@...nel.org>,
Sebastian Andrzej Siewior <bigeasy@...utronix.de>,
Michal Hocko <mhocko@...e.com>, Alex Deucher <alexander.deucher@....com>,
David Airlie <airlied@...il.com>, Simona Vetter <simona@...ll.ch>
Subject: Re: [PATCH 1/4] drm/amdgpu: replace use of system_unbound_wq with
system_dfl_wq
On 10/31/25 09:42, Marco Crivellari wrote:
> On Thu, Oct 30, 2025 at 6:14 PM Christian König
> <christian.koenig@....com> wrote:
>> [...]
>> In all the cases below we actually want the work to run on a different CPU than the current one.
>>
>> So using system_unbound_wq seems to be more appropriate.
>
> Hello Christian,
>
> system_dfl_wq is the new workqueue that will replace
> system_unbound_wq, but the behavior is the same.
> So, if you need system_unbound_wq, it means system_dfl_wq is fine here.
Ah, ok thanks! In that case I'm fine with the change.
It sounded like system_dfl_wq is the new per CPU wq.
Regards,
Christian.
>
> Thanks!
Powered by blists - more mailing lists