[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20180213164418.x7pcjaveorx24rgz@8bytes.org>
Date: Tue, 13 Feb 2018 17:44:18 +0100
From: Joerg Roedel <joro@...tes.org>
To: Dmitry Safonov <dima@...sta.com>
Cc: linux-kernel@...r.kernel.org, 0x7f454c46@...il.com,
Alex Williamson <alex.williamson@...hat.com>,
David Woodhouse <dwmw2@...radead.org>,
Ingo Molnar <mingo@...nel.org>,
Lu Baolu <baolu.lu@...ux.intel.com>,
iommu@...ts.linux-foundation.org
Subject: Re: [PATCHv2 0/6] iommu/intel: Handle DMAR faults in a wq
Hi Dmitry,
On Mon, Feb 12, 2018 at 04:48:19PM +0000, Dmitry Safonov wrote:
> Dmitry Safonov (6):
> iommu/intel: Add __init for dmar_register_bus_notifier()
> iommu/intel: Clean/document fault status flags
> iommu/intel: Introduce clear_primary_faults() helper
> iommu/intel: Handle DMAR faults on workqueue
> iommu/intel: Rename dmar_fault() => dmar_serve_faults()
> iommu/intel: Ratelimit each dmar fault printing
I applied patches 1 and 2 because they are nice cleanups, thanks. For
the rest, I am not convinced that work-queues are a good solution for
the soft lockups you are seeing. Please consider the approach I outlined
in my reply to patch 4.
Also, please prefix your next patches with 'iommu/vt-d' instead of
'iommu/intel'.
Thanks,
Joerg
Powered by blists - more mailing lists