[PATCH v5 00/17] iommu/riscv: Enable MSI remapping, IOMMU_DMA and VFIO
From: Andrew Jones
Date: Mon Aug 31 2026 - 14:15:59 EST
This series adds MSI remapping for IMSIC so a device's MSI target gets
translated the same way its DMA does, allowing RISC-V to enable IOMMU_DMA
and paging domains by default.
v1[1] used get_resv_regions() with IOMMU_RESV_DIRECT_RELAXABLE to identity
map IMSIC pages, but that was rejected as only a workaround. v2 through
v4[2] instead introduced a RISC-V IOMMU IRQ domain which pre-mapped every
possible IMSIC target and maintained a domain-local PA-to-IOVA table. The
v4 discussion with Jason identified a simpler way to handle the RISC-V
requirement that the MSI target address changes with interrupt affinity:
extend the existing iommu_dma_prepare_msi() model to prepare an ordered
list of MSI targets as one contiguous IOVA range. v5 is a complete redesign
around that approach.
The IMSIC driver now builds an array containing the supervisor IMSIC page
for every possible CPU, indexed by logical CPU number. When allocating an
IRQ, it passes the complete array to iommu_dma_prepare_msi_list(). The new
API maps the ordered physical address list into one contiguous IOVA range
through either DMA-IOMMU or iommufd, then caches the base IOVA and mapping
granule in the MSI descriptor. MSI composition can therefore select the
target for the current CPU with simple arithmetic, including during an
affinity change, without allocating memory or consulting IOMMU-owned state
in atomic context.
DMA-IOMMU extends its existing per-page MSI cache to recognize and reuse
complete ranges. iommufd grows its software-MSI bitmap on demand, bounds
allocations to the reserved MSI window, and prepares, installs, rolls back,
and replays a range as one unit. This keeps the descriptor's contiguous
IOVA valid across iommufd paging-domain replacement without exposing a
partially installed range.
Unlike v4, v5 has no RISC-V IOMMU IRQ domain, no domain-local IMSIC mapping
table, and no IOMMU lookup during MSI composition. The IMSIC IRQ domain
owns the target list and message composition, while the IOMMU layers only
provide the mappings. Devices which do not need IOMMU MSI translation keep
using physical MSI addresses through the same IMSIC path.
The series also carries the remaining plumbing needed for RISC-V PCIe
device assignment through VFIO/KVM: the RISC-V IOMMU reports DMA
cache-coherency capability for coherent devices, VFIO type1 and KVM_VFIO
are enabled for RISC-V, defconfig enables IOMMUFD/VFIO as modules with cdev
support, and the generic VFIO/iommufd selftests can be built for RISC-V.
The RISC-V IOMMU specification does not provide MSI data validation, so
VFIO device assignment requires the applicable allow_unsafe_interrupts=1
module parameter. Direct MSI routing to guest interrupt files (irqbypass)
is not yet supported by this series and will be posted separately on top.
LLM-based coding assistants were used during development for code
exploration, patch review, test execution, and drafting and editing
commit messages and this cover letter. I reviewed and finalized all
resulting code and text. Per-patch Assisted-by tags are omitted in
light of ongoing discussions about simplifying coding-assistant
attribution.
Thanks,
drew
[1] https://lore.kernel.org/all/20260508212339.381933-1-andrew.jones@xxxxxxxxxxxxxxxx/
[2] https://lore.kernel.org/all/20260820214150.545737-1-andrew.jones@xxxxxxxxxxxxxxxx/
v5:
- Completely redesigned MSI remapping based on the v4 discussion[2]
- Replaced per-target mapping with iommu_dma_prepare_msi_list(), which maps
an ordered physical address list into one contiguous IOVA range
- Reworked DMA-IOMMU and iommufd software MSI mappings to allocate, cache,
install, roll back, and replay complete ranges
- Moved host MSI remapping into the IMSIC IRQ domain and removed the RISC-V
IOMMU IRQ domain and domain-local PA-to-IOVA table
- Made the IMSIC driver publish a logical-CPU-indexed S-mode address list
and derive each composed target from the descriptor's cached IOVA base
- Fixed the VFIO selftest architecture check to accept both riscv and
riscv64
Andrew Jones (14):
iommu/dma: Prepare MSI physical address lists
iommufd: Convert struct iommufd_sw_msi_maps to a growable bitmap
iommufd: Split software MSI map lookup and allocation
iommufd: Bound software MSI mappings to the reserved range
iommufd: Prepare software MSI maps for address lists
iommufd: Install software MSI map ranges atomically
iommufd: Prepare software MSI installation for address lists
iommu/dma: Introduce iommu_dma_prepare_msi_list()
iommu/riscv: Report cache coherency capability
iommu/riscv: Reserve an MSI IOVA window for iommufd
irqchip/riscv-imsic: Add S-mode MSI address list
irqchip/riscv-imsic: Support IOMMU MSI address lists
riscv: defconfig: Enable IOMMUFD and VFIO
selftests/vfio: Allow building on RISC-V
Tomasz Jeznach (3):
iommu/dma: Enable IOMMU_DMA for 64-bit RISC-V
vfio: enable IOMMU_TYPE1 for RISC-V
RISC-V: KVM: Enable KVM_VFIO interfaces on RISC-V arch
arch/riscv/configs/defconfig | 4 +
arch/riscv/kvm/Kconfig | 1 +
drivers/iommu/Kconfig | 2 +-
drivers/iommu/dma-iommu.c | 117 ++++++--
drivers/iommu/dma-iommu.h | 13 +-
drivers/iommu/iommu-priv.h | 7 +-
drivers/iommu/iommu.c | 109 +++++--
drivers/iommu/iommufd/device.c | 20 +-
drivers/iommu/iommufd/driver.c | 315 +++++++++++++++++----
drivers/iommu/iommufd/hw_pagetable.c | 1 +
drivers/iommu/iommufd/io_pagetable.c | 9 +-
drivers/iommu/iommufd/iommufd_private.h | 51 +++-
drivers/iommu/riscv/iommu.c | 32 +++
drivers/iommu/riscv/iommu.h | 4 +
drivers/irqchip/Kconfig | 1 +
drivers/irqchip/irq-riscv-imsic-platform.c | 25 +-
drivers/irqchip/irq-riscv-imsic-state.c | 54 ++++
drivers/irqchip/irq-riscv-imsic-state.h | 1 +
drivers/vfio/Kconfig | 2 +-
include/linux/iommu.h | 8 +
include/linux/irqchip/riscv-imsic.h | 6 +
tools/testing/selftests/vfio/Makefile | 2 +-
22 files changed, 657 insertions(+), 127 deletions(-)
--
2.43.0