[PATCH v9 0/8] KVM PCIe/MSI passthrough on ARM/ARM64: kernel part 1/3: iommu changes

From: Eric Auger
Date: Wed May 04 2016 - 07:40:21 EST

This series introduces the msi-iommu api used to:

- allocate/free resources for MSI IOMMU mapping
- set the MSI iova window aperture
- map/unmap physical addresses onto MSI IOVAs.
- determine whether an msi needs to be iommu mapped
- overwrite an msi_msg PA address with its pre-allocated/mapped IOVA

Also a new iommu domain attribute, DOMAIN_ATTR_MSI_GEOMETRY is introduced
to report the MSI iova window geometry (aperture and iommu-msi API support).

- iommu driver is supposed to allocate/free MSI mapping resources
- VFIO subsystem is supposed to set the MSI IOVA aperture.
- The MSI layer is supposed to allocate/free iova mappings and overwrite
msi_msg with IOVA at composition time

More details & context can be found at:

Best Regards


Git: complete series available at


v8 -> v9:
- rename iommu_domain_msi_geometry programmable flag into iommu_msi_supported
- introduce msi_apperture_valid helper and use this instead of is_aperture_set

v7 -> v8:
- The API is retargetted for MSI: renamed msi-iommu
all "dma-reserved" namings removed
- now implemented upon dma-iommu (get, put, init), ie. reuse iova_cookie,
and iova API
- msi mapping resources now are guaranteed to exist during the whole iommu
domain's lifetime. No need to lock to garantee the cookie integrity
- removed alloc/free_reserved_reserved_iova_domain. We now have a single
function that sets the aperture, looking like iommu_dma_init_domain.
- we now use a list instead of an RB-tree
- prot is not propagated anymore at domain creation due to the retargetting
for MSI
- iommu_domain pointer removed from doorbell_mapping struct

v6 -> v7:
- fixed known lock bugs and multiple page sized slots matching
(I only have a single MSI frame made of a single page)
- reserved_iova_cookie now pointing to a struct that encapsulates the
iova domain handle + protection attribute passed from VFIO (Alex' req)
- 2 new functions exposed: iommu_msi_mapping_translate_msg,
iommu_msi_mapping_desc_to_domain: not sure this is the right location/proto
- iommu_put_reserved_iova now takes a phys_addr_t
- everything now is cleanup on iommu_domain destruction

RFC v5 -> patch v6:
- split to ease the review process
- in dma-reserved-api use a spin lock instead of a mutex (reported by
- revisit iommu_get_reserved_iova API to pass a size parameter upon
Marc's request
- Consistently use the page order passed when creating the iova domain.
- init reserved_binding_list (reported by Julien)

RFC v4 -> RFC v5:
- take into account Thomas' comments on MSI related patches
- split "msi: IOMMU map the doorbell address when needed"
- increase readability and add comments
- fix style issues
- split "iommu: Add DOMAIN_ATTR_MSI_MAPPING attribute"
- platform ITS now advertises IOMMU_CAP_INTR_REMAP
- fix compilation issue with CONFIG_IOMMU API unset
- arm-smmu-v3 now advertises DOMAIN_ATTR_MSI_MAPPING

RFC v3 -> v4:
- Move doorbell mapping/unmapping in msi.c
- fix ref count issue on set_affinity: in case of a change in the address
the previous address is decremented
- doorbell map/unmap now is done on msi composition. Should allow the use
case for platform MSI controllers
- create dma-reserved-iommu.h/c exposing/implementing a new API dedicated
to reserved IOVA management (looking like dma-iommu glue)
- series reordering to ease the review:
- first part is related to IOMMU
- second related to MSI sub-system
- third related to VFIO (except arm-smmu IOMMU_CAP_INTR_REMAP removal)
- expose the number of requested IOVA pages through VFIO_IOMMU_GET_INFO
[this partially addresses Marc's comments on iommu_get/put_single_reserved
size/alignment problematic - which I did not ignore - but I don't know
how much I can do at the moment]

RFC v2 -> RFC v3:
- should fix wrong handling of some CONFIG combinations:
- fix MSI_FLAG_IRQ_REMAPPING setting in GICv3 ITS (although not tested)

PATCH v1 -> RFC v2:
- reverted to RFC since it looks more reasonable ;-) the code is split
between VFIO, IOMMU, MSI controller and I am not sure I did the right
choices. Also API need to be further discussed.
- iova API usage in arm-smmu.c.
- MSI controller natively programs the MSI addr with either the PA or IOVA.
This is not done anymore in vfio-pci driver as suggested by Alex.
- check irq remapping capability of the group

RFC v1 [2] -> PATCH v1:
- use the existing dma map/unmap ioctl interface with a flag to register a
reserved IOVA range. Use the legacy Rb to store this special vfio_dma.
- a single reserved IOVA contiguous region now is allowed
- use of an RB tree indexed by PA to store allocated reserved slots
- use of a vfio_domain iova_domain to manage iova allocation within the
window provided by the userspace
- vfio alloc_map/unmap_free take a vfio_group handle
- vfio_group handle is cached in vfio_pci_device
- add ref counting to bindings
- user modality enabled at the end of the series

Eric Auger (8):
iommu: Add iommu_domain_msi_geometry and DOMAIN_ATTR_MSI_GEOMETRY
iommu/arm-smmu: initialize the msi geometry and advertise iommu-msi
iommu: introduce an msi cookie
iommu/msi-iommu: initialization
iommu/msi-iommu: iommu_msi_[get,put]_doorbell_iova
iommu/msi-iommu: iommu_msi_domain
iommu/msi-iommu: iommu_msi_msg_pa_to_va
iommu/arm-smmu: get/put the msi cookie

drivers/iommu/Kconfig | 7 +
drivers/iommu/Makefile | 1 +
drivers/iommu/arm-smmu-v3.c | 18 ++-
drivers/iommu/arm-smmu.c | 18 ++-
drivers/iommu/iommu.c | 5 +
drivers/iommu/msi-iommu.c | 319 ++++++++++++++++++++++++++++++++++++++++++++
include/linux/iommu.h | 15 +++
include/linux/msi-iommu.h | 144 ++++++++++++++++++++
8 files changed, 519 insertions(+), 8 deletions(-)
create mode 100644 drivers/iommu/msi-iommu.c
create mode 100644 include/linux/msi-iommu.h