>-----Original Message----- >From: Eric Auger <eric.au...@redhat.com> >Subject: Re: [RFC 0/7] VIRTIO-IOMMU/VFIO: Fix host iommu geometry >handling for hotplugged devices > >Hi Zhenzhong, >On 1/18/24 08:10, Duan, Zhenzhong wrote: >> 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. > >this field is iommu wide while the probe applies on a one device.In >general I would prefer not to be dependent on the MR enablement. We know >that the device is likely to be protected and we can collect its >requirements beforehand.
Agree that your new patch is cleaner. >> >> 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. >interesting. > >Would be curious to get Jean Philippe's pov. >> >>> 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. > >Correct >> >> 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 > >I just replayed the scenario: >- if you have a coldplugged vfio-pci device, the pci root port and the >passthroughed device end up in different iommu groups. On my end I use >ioh3420 but you confirmed that's the same for the generic pcie-root-port >- however if you hotplug the vfio-pci device that's a different story: >they end up in the same group. Don't ask me why. I tried with >both virtio-iommu and intel iommu and I end up with the same topology. >That looks really weird to me. That's strange. I tested two vfio devices with ioh3420, one coldplug, the other hotplug. ioh3420 and vfio devices are in same group. -[0000:00]-+-00.0 +-01.0 +-02.0 +-03.0-[01]----00.0 +-04.0-[02]----00.0 /sys/kernel/iommu_groups/3/devices: 0000:00:03.0 0000:01:00.0 /sys/kernel/iommu_groups/4/devices: 0000:00:04.0 0000:02:00.0 Thanks Zhenzhong > >I initially thought this was an ACS issue but I am now puzzled. > >Thanks! > >Eric >> >> 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