From: Jason Gunthorpe <jgg@nvidia.com>
To: Ethan Zhao <etzhao1900@gmail.com>
Cc: Nicolin Chen <nicolinc@nvidia.com>,
joro@8bytes.org, will@kernel.org, robin.murphy@arm.com,
rafael@kernel.org, lenb@kernel.org, bhelgaas@google.com,
iommu@lists.linux.dev, linux-kernel@vger.kernel.org,
linux-acpi@vger.kernel.org, linux-pci@vger.kernel.org,
patches@lists.linux.dev, pjaroszynski@nvidia.com,
vsethi@nvidia.com, helgaas@kernel.org, baolu.lu@linux.intel.com
Subject: Re: [PATCH RFC v2 0/4] Disable ATS via iommu during PCI resets
Date: Sun, 27 Jul 2025 13:20:41 -0300 [thread overview]
Message-ID: <20250727162041.GC7551@nvidia.com> (raw)
In-Reply-To: <606f65e1-ccfc-4492-a32f-90343be654e7@gmail.com>
On Sun, Jul 27, 2025 at 08:48:26PM +0800, Ethan Zhao wrote:
> At least, we can do some attempt in DPC and Hot-plug driver, and then
> push the hardware specification update to provide pre-reset notification for
> DPC & hotplug. does it make sense ?
I think DPC is a different case..
If we get a DPC we should also push the iommu into blocking, disable
ATS and abandon any outstanding ATC invalidations as part of
recovering from the DPC. Once everythings is cleaned up we can set the
iommu back up again and allow the driver to recover the device.
I think the current series is a good step along that path, but we'd
also need to improve the drivers to handle abandonding/aborting the
ATC invalidations.
IMHO DPC and SW initiated reset are separate projects.
Jason
next prev parent reply other threads:[~2025-07-27 16:20 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-06-28 7:42 [PATCH RFC v2 0/4] Disable ATS via iommu during PCI resets Nicolin Chen
2025-06-28 7:42 ` [PATCH RFC v2 1/4] iommu: Lock group->mutex in iommu_deferred_attach Nicolin Chen
2025-07-04 15:22 ` Jason Gunthorpe
2025-06-28 7:42 ` [PATCH RFC v2 2/4] iommu: Pass in gdev to __iommu_device_set_domain Nicolin Chen
2025-07-04 15:23 ` Jason Gunthorpe
2025-06-28 7:42 ` [PATCH RFC v2 3/4] iommu: Introduce iommu_dev_reset_prepare() and iommu_dev_reset_done() Nicolin Chen
2025-06-28 13:28 ` Baolu Lu
2025-06-30 12:38 ` Jason Gunthorpe
2025-06-30 17:29 ` Nicolin Chen
2025-06-30 22:49 ` Jason Gunthorpe
2025-07-04 15:43 ` Jason Gunthorpe
2025-07-22 21:58 ` Nicolin Chen
2025-07-23 2:21 ` Baolu Lu
2025-07-23 2:53 ` Nicolin Chen
2025-07-27 16:25 ` Jason Gunthorpe
2025-07-28 19:07 ` Nicolin Chen
2025-07-29 13:02 ` Jason Gunthorpe
2025-06-28 7:42 ` [PATCH RFC v2 4/4] pci: Suspend iommu function prior to resetting a device Nicolin Chen
2025-07-24 6:50 ` [PATCH RFC v2 0/4] Disable ATS via iommu during PCI resets Ethan Zhao
2025-07-25 16:41 ` Nicolin Chen
2025-07-27 12:48 ` Ethan Zhao
2025-07-27 16:20 ` Jason Gunthorpe [this message]
2025-07-29 6:16 ` Ethan Zhao
2025-07-29 12:59 ` Jason Gunthorpe
2025-07-31 1:10 ` Ethan Zhao
2025-07-31 13:47 ` Jason Gunthorpe
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=20250727162041.GC7551@nvidia.com \
--to=jgg@nvidia.com \
--cc=baolu.lu@linux.intel.com \
--cc=bhelgaas@google.com \
--cc=etzhao1900@gmail.com \
--cc=helgaas@kernel.org \
--cc=iommu@lists.linux.dev \
--cc=joro@8bytes.org \
--cc=lenb@kernel.org \
--cc=linux-acpi@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pci@vger.kernel.org \
--cc=nicolinc@nvidia.com \
--cc=patches@lists.linux.dev \
--cc=pjaroszynski@nvidia.com \
--cc=rafael@kernel.org \
--cc=robin.murphy@arm.com \
--cc=vsethi@nvidia.com \
--cc=will@kernel.org \
/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;
as well as URLs for NNTP newsgroup(s).