From: Jason Gunthorpe <jgg@nvidia.com>
To: "Tian, Kevin" <kevin.tian@intel.com>
Cc: Joao Martins <joao.m.martins@oracle.com>,
"iommu@lists.linux.dev" <iommu@lists.linux.dev>,
Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>,
Lu Baolu <baolu.lu@linux.intel.com>,
Avihai Horon <avihaih@nvidia.com>,
Alex Williamson <alex.williamson@redhat.com>,
Shameerali Kolothum Thodi <shameerali.kolothum.thodi@huawei.com>
Subject: Re: [PATCH v1 0/9] iommufd/iova_bitmap: Bug fixes for IOMMU dirty tracking
Date: Thu, 8 Feb 2024 13:23:36 -0400 [thread overview]
Message-ID: <20240208172336.GM10476@nvidia.com> (raw)
In-Reply-To: <BN9PR11MB5276EE3DE0C5A923C9C077E68C442@BN9PR11MB5276.namprd11.prod.outlook.com>
On Thu, Feb 08, 2024 at 08:21:01AM +0000, Tian, Kevin wrote:
> could be a framework in iommu core which calls @do_dma callback
> provided by iommu drivers. Within the callback the driver specific
> code can walk the page table, set dirty bit, or trigger IOPF, etc. Kind
> of a sw page walker.
My next next? project is going to be looking at improving the page
table code to more completely consolidate it around common
algorithms. Joao and I had shared a few ideas last year and it turns
out there are quite a few needs out there.
A big point of that would be to create a selftest that could do the
kinds of manipulations you are talking about here.
Then the idea is mock could back the mock domains using the io page
table storage instead of the xarray and we'd get a big improvement to
the other big area of code iommu drivers have to implement.
We'll see how it looks, it may be too ambitious.
Jason
prev parent reply other threads:[~2024-02-08 17:23 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-02-02 13:34 [PATCH v1 0/9] iommufd/iova_bitmap: Bug fixes for IOMMU dirty tracking Joao Martins
2024-02-02 13:34 ` [PATCH v1 1/9] iommufd/iova_bitmap: Bounds check mapped::pages access Joao Martins
2024-02-07 16:49 ` Avihai Horon
2024-02-02 13:34 ` [PATCH v1 2/9] iommufd/iova_bitmap: Switch iova_bitmap::bitmap to an u8 array Joao Martins
2024-02-07 16:50 ` Avihai Horon
2024-02-02 13:34 ` [PATCH v1 3/9] iommufd/selftest: Test u64 unaligned bitmaps Joao Martins
2024-02-02 13:34 ` [PATCH v1 4/9] iommufd/iova_bitmap: Handle recording beyond the mapped pages Joao Martins
2024-02-07 16:51 ` Avihai Horon
2024-05-24 11:22 ` Joao Martins
2024-02-02 13:34 ` [PATCH v1 5/9] iommufd/selftest: Refactor dirty bitmap tests Joao Martins
2024-02-02 13:34 ` [PATCH v1 6/9] iommufd/selftest: Refactor mock_domain_read_and_clear_dirty() Joao Martins
2024-02-02 13:34 ` [PATCH v1 7/9] iommufd/selftest: Hugepage mock domain support Joao Martins
2024-02-02 13:34 ` [PATCH v1 8/9] iommufd/selftest: Add mock IO hugepages tests Joao Martins
2024-02-02 13:34 ` [PATCH v1 9/9] iommufd/iova_bitmap: Consider page offset for the pages to be pinned Joao Martins
2024-02-07 16:52 ` Avihai Horon
2024-02-06 18:13 ` [PATCH v1 0/9] iommufd/iova_bitmap: Bug fixes for IOMMU dirty tracking Jason Gunthorpe
2024-02-06 18:32 ` Joao Martins
2024-02-06 20:57 ` Joao Martins
2024-02-07 8:41 ` Tian, Kevin
2024-02-07 10:23 ` Joao Martins
2024-02-08 8:21 ` Tian, Kevin
2024-02-08 17:23 ` Jason Gunthorpe [this message]
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=20240208172336.GM10476@nvidia.com \
--to=jgg@nvidia.com \
--cc=alex.williamson@redhat.com \
--cc=avihaih@nvidia.com \
--cc=baolu.lu@linux.intel.com \
--cc=iommu@lists.linux.dev \
--cc=joao.m.martins@oracle.com \
--cc=kevin.tian@intel.com \
--cc=shameerali.kolothum.thodi@huawei.com \
--cc=suravee.suthikulpanit@amd.com \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.