Re: [Qemu-devel] [PATCH 11/11] vfio: Add guest side IOMMU support

[Paolo Bonzini]

Il 14/05/2013 11:13, David Gibson ha scritto:
> This patch uses the new IOMMU notifiers to allow VFIO pass through devices
> to work with guest side IOMMUs, as long as the host-side VFIO iommu has
> sufficient capability and granularity to match the guest side. This works
> by tracking all map and unmap operations on the guest IOMMU using the
> notifiers, and mirroring them into VFIO.
> 
> There are a number of FIXMEs, and the scheme involves rather more notifier
> structures than I'd like, but it shuold make for a reasonable proof of
> concept.
> 
> Signed-off-by: David Gibson <address@hidden>
> ---
>  hw/misc/vfio.c |  139 
> ++++++++++++++++++++++++++++++++++++++++++++++++++------
>  1 file changed, 126 insertions(+), 13 deletions(-)
> 
> diff --git a/hw/misc/vfio.c b/hw/misc/vfio.c
> index f4e3792..62a83ca 100644
> --- a/hw/misc/vfio.c
> +++ b/hw/misc/vfio.c
> @@ -133,10 +133,18 @@ typedef struct VFIOContainer {
>          };
>          void (*release)(struct VFIOContainer *);
>      } iommu_data;
> +    QLIST_HEAD(, VFIOGuestIOMMU) guest_iommus;
>      QLIST_HEAD(, VFIOGroup) group_list;
>      QLIST_ENTRY(VFIOContainer) next;
>  } VFIOContainer;
>  
> +typedef struct VFIOGuestIOMMU {
> +    VFIOContainer *container;
> +    MemoryRegion *iommu;
> +    Notifier n;
> +    QLIST_ENTRY(VFIOGuestIOMMU) list;
> +} VFIOGuestIOMMU;
> +
>  /* Cache of MSI-X setup plus extra mmap and memory region for split BAR map 
> */
>  typedef struct VFIOMSIXInfo {
>      uint8_t table_bar;
> @@ -1940,7 +1948,64 @@ static int vfio_dma_map(VFIOContainer *container, 
> hwaddr iova,
>  
>  static bool vfio_listener_skipped_section(MemoryRegionSection *section)
>  {
> -    return !memory_region_is_ram(section->mr);
> +    return !memory_region_is_ram(section->mr) &&
> +        !memory_region_is_iommu(section->mr);
> +}
> +
> +static void vfio_iommu_map_notify(Notifier *n, void *data)
> +{
> +    VFIOGuestIOMMU *giommu = container_of(n, VFIOGuestIOMMU, n);
> +    MemoryRegion *iommu = giommu->iommu;
> +    VFIOContainer *container = giommu->container;
> +    IOMMUTLBEntry *iotlb = data;
> +    MemoryRegionSection *mrs;
> +    hwaddr xlat;
> +    hwaddr len = iotlb->addr_mask + 1;
> +    void *vaddr;
> +    int ret;
> +
> +    DPRINTF("iommu map @ %"HWADDR_PRIx" - %"HWADDR_PRIx"\n",
> +            iotlb->iova, iotlb->iova + iotlb->address_mask);
> +
> +    /* The IOMMU TLB entry we have just covers translation through
> +     * this IOMMU to its immediate target.  We need to translate
> +     * it the rest of the way through to memory. */
> +    mrs = address_space_translate(iommu->iommu_target_as,
> +                                  iotlb->translated_addr,
> +                                  &xlat, &len, iotlb->perm[1]);
> +    if (!memory_region_is_ram(mrs->mr)) {
> +        DPRINTF("iommu map to non memory area %"HWADDR_PRIx"\n",
> +                xlat);
> +        return;
> +    }
> +    if (len & iotlb->addr_mask) {
> +        DPRINTF("iommu has granularity incompatible with target AS\n");
> +        return;
> +    }
> +
> +    vaddr = memory_region_get_ram_ptr(mrs->mr) +
> +        mrs->offset_within_region +
> +        (xlat - mrs->offset_within_address_space);

Are you sure you need this translation?  It's done already in
address_space_translate, so it should be just

vaddr = memory_region_get_ram_ptr(mrs->mr) + xlat;

Paolo

> +    if (iotlb->perm[0] || iotlb->perm[1]) {
> +        ret = vfio_dma_map(container, iotlb->iova,
> +                           iotlb->addr_mask + 1, vaddr,
> +                           !iotlb->perm[1] || mrs->readonly);
> +        if (ret) {
> +            error_report("vfio_dma_map(%p, 0x%"HWADDR_PRIx", "
> +                         "0x%"HWADDR_PRIx", %p) = %d (%m)",
> +                         container, iotlb->iova,
> +                         iotlb->addr_mask + 1, vaddr, ret);
> +        }
> +    } else {
> +        ret = vfio_dma_unmap(container, iotlb->iova, iotlb->addr_mask + 1);
> +        if (ret) {
> +            error_report("vfio_dma_unmap(%p, 0x%"HWADDR_PRIx", "
> +                         "0x%"HWADDR_PRIx") = %d (%m)",
> +                         container, iotlb->iova,
> +                         iotlb->addr_mask + 1, ret);
> +        }
> +    }
>  }
>  
>  static void vfio_listener_region_add(MemoryListener *listener,
> @@ -1949,11 +2014,8 @@ static void vfio_listener_region_add(MemoryListener 
> *listener,
>      VFIOContainer *container = container_of(listener, VFIOContainer,
>                                              iommu_data.listener);
>      hwaddr iova, end;
> -    void *vaddr;
>      int ret;
>  
> -    assert(!memory_region_is_iommu(section->mr));
> -
>      if (vfio_listener_skipped_section(section)) {
>          DPRINTF("SKIPPING region_add %"HWADDR_PRIx" - %"PRIx64"\n",
>                  section->offset_within_address_space,
> @@ -1975,20 +2037,55 @@ static void vfio_listener_region_add(MemoryListener 
> *listener,
>          return;
>      }
>  
> -    vaddr = memory_region_get_ram_ptr(section->mr) +
> +    memory_region_ref(section->mr);
> +
> +    if (memory_region_is_ram(section->mr)) {
> +        void *vaddr;
> +
> +        DPRINTF("region_add [ram] %"HWADDR_PRIx" - %"HWADDR_PRIx" [%p]\n",
> +                iova, end - 1, vaddr);
> +
> +        vaddr = memory_region_get_ram_ptr(section->mr) +
>              section->offset_within_region +
>              (iova - section->offset_within_address_space);
>  
> -    DPRINTF("region_add %"HWADDR_PRIx" - %"HWADDR_PRIx" [%p]\n",
> -            iova, end - 1, vaddr);
>  
> -    memory_region_ref(section->mr);
> -    ret = vfio_dma_map(container, iova, end - iova, vaddr, 
> section->readonly);
> -    if (ret) {
> -        error_report("vfio_dma_map(%p, 0x%"HWADDR_PRIx", "
> -                     "0x%"HWADDR_PRIx", %p) = %d (%m)",
> -                     container, iova, end - iova, vaddr, ret);
> +        ret = vfio_dma_map(container, iova, end - iova, vaddr,
> +                           section->readonly);
> +        if (ret) {
> +            error_report("vfio_dma_map(%p, 0x%"HWADDR_PRIx", "
> +                         "0x%"HWADDR_PRIx", %p) = %d (%m)",
> +                         container, iova, end - iova, vaddr, ret);
> +        }
> +    } else if (memory_region_is_iommu(section->mr)) {
> +        VFIOGuestIOMMU *giommu;
> +
> +        DPRINTF("region_add [iommu] %"HWADDR_PRIx" - %"HWADDR_PRIx"\n",
> +                iova, end - 1);
> +
> +        /*
> +         * FIXME: We should do some checking to see if the
> +         * capabilities of the host VFIO IOMMU are adequate to model
> +         * the guest IOMMU
> +         *
> +         * FIXME: This assumes that the guest IOMMU is empty of
> +         * mappings at this point - we should either enforce this, or
> +         * loop through existing mappings to map them into VFIO.
> +         *
> +         * FIXME: For VFIO iommu types which have KVM acceleration to
> +         * avoid bouncing all map/unmaps through qemu this way, this
> +         * would be the right place to wire that up (tell the KVM
> +         * device emulation the VFIO iommu handles to use).
> +         */
> +        giommu = g_malloc0(sizeof(*giommu));
> +        giommu->iommu = section->mr;
> +        giommu->container = container;
> +        giommu->n.notify = vfio_iommu_map_notify;
> +
> +        QLIST_INSERT_HEAD(&container->guest_iommus, giommu, list);
> +        memory_region_register_iommu_notifier(giommu->iommu, &giommu->n);
>      }
> +
>  }
>  
>  static void vfio_listener_region_del(MemoryListener *listener,
> @@ -2012,6 +2109,22 @@ static void vfio_listener_region_del(MemoryListener 
> *listener,
>          return;
>      }
>  
> +    if (memory_region_is_iommu(section->mr)) {
> +        VFIOGuestIOMMU *giommu;
> +
> +        QLIST_FOREACH(giommu, &container->guest_iommus, list) {
> +            if (giommu->iommu == section->mr) {
> +                memory_region_unregister_iommu_notifier(&giommu->n);
> +                break;
> +            }
> +        }
> +
> +        /* FIXME: We assume the one big unmap below is adequate to
> +         * remove any individual page mappings in the IOMMU which
> +         * might have been copied into VFIO.  That may not be true for
> +         * all IOMMU types */
> +    }
> +
>      iova = TARGET_PAGE_ALIGN(section->offset_within_address_space);
>      end = (section->offset_within_address_space + section->size) &
>            TARGET_PAGE_MASK;
>