[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <aWq8woXQ1E6XO9tA@google.com>
Date: Fri, 16 Jan 2026 22:33:38 +0000
From: David Matlack <dmatlack@...gle.com>
To: Alex Mastro <amastro@...com>
Cc: Alex Williamson <alex@...zbot.org>, Shuah Khan <shuah@...nel.org>,
Peter Xu <peterx@...hat.com>, linux-kernel@...r.kernel.org,
kvm@...r.kernel.org, linux-kselftest@...r.kernel.org,
Jason Gunthorpe <jgg@...pe.ca>
Subject: Re: [PATCH v3 0/3] vfio: selftests: Add MMIO DMA mapping test
On 2026-01-14 10:57 AM, Alex Mastro wrote:
> Test IOMMU mapping the BAR mmaps created during vfio_pci_device_setup().
>
> All IOMMU modes are tested: vfio_type1 variants are expected to succeed,
> while non-type1 modes are expected to fail. iommufd compat mode can be
> updated to expect success once kernel support lands. Native iommufd will
> not support mapping vaddrs backed by MMIO (it will support dma-buf based
> MMIO mapping instead).
>
> Changes in v3:
> - Rename mmap_aligned() to mmap_reserve()
> - Reorder variable declarations for reverse-fir-tree style
> - Update patch 2 commit message to mention MADV_HUGEPAGE and MAP_FILE
> - Move BAR size check into map_partial_bar test only
> - Link to v2: https://lore.kernel.org/r/20260113-map-mmio-test-v2-0-e6d34f09c0bb@fb.com
>
> Changes in v2:
> - Split into patch series
> - Factor out mmap_reserve() for vaddr alignment
> - Align BAR mmaps to improve hugepage IOMMU mapping efficiency
> - Centralize MODE_* string definitions
> - Add is_power_of_2() assertion for BAR size
> - Simplify align calculation to min(size, 1G)
> - Add map_bar_misaligned test case
> - Link to v1: https://lore.kernel.org/all/20260107-scratch-amastro-vfio-dma-mapping-mmio-test-v1-1-0cec5e9ec89b@fb.com
>
> Signed-off-by: Alex Mastro <amastro@...com>
Reviewed-by: David Matlack <dmatlack@...gle.com>
Tested-by: David Matlack <dmatlack@...gle.com>
Powered by blists - more mailing lists