Hi Eric, >-----Original Message----- >From: Eric Auger <eric.au...@redhat.com> >Cc: m...@redhat.com; c...@redhat.com >Subject: [RFC 0/7] VIRTIO-IOMMU/VFIO: Fix host iommu geometry handling >for hotplugged devices > >In [1] we attempted to fix a case where a VFIO-PCI device protected >with a virtio-iommu was assigned to an x86 guest. On x86 the physical >IOMMU may have an address width (gaw) of 39 or 48 bits whereas the >virtio-iommu used to expose a 64b address space by default. >Hence the guest was trying to use the full 64b space and we hit >DMA MAP failures. To work around this issue we managed to pass >usable IOVA regions (excluding the out of range space) from VFIO >to the virtio-iommu device. This was made feasible by introducing >a new IOMMU Memory Region callback dubbed iommu_set_iova_regions(). >This latter gets called when the IOMMU MR is enabled which >causes the vfio_listener_region_add() to be called. > >However with VFIO-PCI hotplug, this technique fails due to the >race between the call to the callback in the add memory listener >and the virtio-iommu probe request. Indeed the probe request gets >called before the attach to the domain. So in that case the usable >regions are communicated after the probe request and fail to be >conveyed to the guest. To be honest the problem was hinted by >Jean-Philippe in [1] and I should have been more careful at >listening to him and testing with hotplug :-(
It looks the global virtio_iommu_config.bypass is never cleared in guest. When guest virtio_iommu driver enable IOMMU, should it clear this bypass attribute? If it could be cleared in viommu_probe(), then qemu will call virtio_iommu_set_config() then virtio_iommu_switch_address_space_all() to enable IOMMU MR. Then both coldplugged and hotplugged devices will work. Intel iommu has a similar bit in register GCMD_REG.TE, when guest intel_iommu driver probe set it, on qemu side, vtd_address_space_refresh_all() is called to enable IOMMU MRs. > >For coldplugged device the technique works because we make sure all >the IOMMU MR are enabled once on the machine init done: 94df5b2180 >("virtio-iommu: Fix 64kB host page size VFIO device assignment") >for granule freeze. But I would be keen to get rid of this trick. > >Using an IOMMU MR Ops is unpractical because this relies on the IOMMU >MR to have been enabled and the corresponding vfio_listener_region_add() >to be executed. Instead this series proposes to replace the usage of this >API by the recently introduced PCIIOMMUOps: ba7d12eb8c ("hw/pci: >modify >pci_setup_iommu() to set PCIIOMMUOps"). That way, the callback can be >called earlier, once the usable IOVA regions have been collected by >VFIO, without the need for the IOMMU MR to be enabled. > >This looks cleaner. In the short term this may also be used for >passing the page size mask, which would allow to get rid of the >hacky transient IOMMU MR enablement mentionned above. > >[1] [PATCH v4 00/12] VIRTIO-IOMMU/VFIO: Don't assume 64b IOVA space > https://lore.kernel.org/all/20231019134651.842175-1- >eric.au...@redhat.com/ > >[2] https://lore.kernel.org/all/20230929161547.GB2957297@myrica/ > >Extra Notes: >With that series, the reserved memory regions are communicated on time >so that the virtio-iommu probe request grabs them. However this is not >sufficient. In some cases (my case), I still see some DMA MAP failures >and the guest keeps on using IOVA ranges outside the geometry of the >physical IOMMU. This is due to the fact the VFIO-PCI device is in the >same iommu group as the pcie root port. Normally the kernel >iova_reserve_iommu_regions (dma-iommu.c) is supposed to call >reserve_iova() >for each reserved IOVA, which carves them out of the allocator. When >iommu_dma_init_domain() gets called for the hotplugged vfio-pci device >the iova domain is already allocated and set and we don't call >iova_reserve_iommu_regions() again for the vfio-pci device. So its >corresponding reserved regions are not properly taken into account. I suspect there is same issue with coldplugged devices. If those devices are in same group, get iova_reserve_iommu_regions() is only called for first device. But other devices's reserved regions are missed. Curious how you make passthrough device and pcie root port under same group. When I start a x86 guest with passthrough device, I see passthrough device and pcie root port are in different group. -[0000:00]-+-00.0 +-01.0 +-02.0 +-03.0-[01]----00.0 /sys/kernel/iommu_groups/3/devices: 0000:00:03.0 /sys/kernel/iommu_groups/7/devices: 0000:01:00.0 My qemu cmdline: -device pcie-root-port,id=root0,slot=0 -device vfio-pci,host=6f:01.0,id=vfio0,bus=root0 Thanks Zhenzhong > >This is not trivial to fix because theoretically the 1st attached >devices could already have allocated IOVAs within the reserved regions >of the second device. Also we are somehow hijacking the reserved >memory regions to model the geometry of the physical IOMMU so not sure >any attempt to fix that upstream will be accepted. At the moment one >solution is to make sure assigned devices end up in singleton group. >Another solution is to work on a different approach where the gaw >can be passed as an option to the virtio-iommu device, similarly at >what is done with intel iommu. > >This series can be found at: >https://github.com/eauger/qemu/tree/hotplug-resv-rfc > > >Eric Auger (7): > hw/pci: Introduce PCIIOMMUOps::set_host_iova_regions > hw/pci: Introduce pci_device_iommu_bus > vfio/pci: Pass the usable IOVA ranges through PCIIOMMUOps > virtio-iommu: Implement PCIIOMMUOps set_host_resv_regions > virtio-iommu: Remove the implementation of iommu_set_iova_ranges > hw/vfio: Remove memory_region_iommu_set_iova_ranges() call > memory: Remove IOMMU MR iommu_set_iova_range API > > include/exec/memory.h | 32 ------- > include/hw/pci/pci.h | 16 ++++ > hw/pci/pci.c | 16 ++++ > hw/vfio/common.c | 10 -- > hw/vfio/pci.c | 27 ++++++ > hw/virtio/virtio-iommu.c | 201 ++++++++++++++++++++------------------- > system/memory.c | 13 --- > 7 files changed, 160 insertions(+), 155 deletions(-) > >-- >2.41.0