[QEMU,v23,16/18] vfio: Add ioctl to get dirty pages bitmap during dma unmap.

With vIOMMU, IO virtual address range can get unmapped while in pre-copy
phase of migration. In that case, unmap ioctl should return pages pinned
in that range and QEMU should find its correcponding guest physical
addresses and report those dirty.

Suggested-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Kirti Wankhede <kwankhede@nvidia.com>
Reviewed-by: Neo Jia <cjia@nvidia.com>
---
 hw/vfio/common.c | 84 +++++++++++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 80 insertions(+), 4 deletions(-)

* Kirti Wankhede (kwankhede@nvidia.com) wrote:
> With vIOMMU, IO virtual address range can get unmapped while in pre-copy
> phase of migration. In that case, unmap ioctl should return pages pinned
> in that range and QEMU should find its correcponding guest physical
> addresses and report those dirty.
> 
> Suggested-by: Alex Williamson <alex.williamson@redhat.com>
> Signed-off-by: Kirti Wankhede <kwankhede@nvidia.com>
> Reviewed-by: Neo Jia <cjia@nvidia.com>
> ---
>  hw/vfio/common.c | 84 +++++++++++++++++++++++++++++++++++++++++++++++++++++---
>  1 file changed, 80 insertions(+), 4 deletions(-)
> 
> diff --git a/hw/vfio/common.c b/hw/vfio/common.c
> index 3f7049fbd1b0..2dd9e8b24788 100644
> --- a/hw/vfio/common.c
> +++ b/hw/vfio/common.c
> @@ -311,11 +311,82 @@ static bool vfio_devices_are_stopped_and_saving(void)
>      return true;
>  }
>  
> +static bool vfio_devices_are_running_and_saving(void)
> +{
> +    VFIOGroup *group;
> +    VFIODevice *vbasedev;
> +
> +    QLIST_FOREACH(group, &vfio_group_list, next) {
> +        QLIST_FOREACH(vbasedev, &group->device_list, next) {
> +            if ((vbasedev->device_state & VFIO_DEVICE_STATE_SAVING) &&
> +                (vbasedev->device_state & VFIO_DEVICE_STATE_RUNNING)) {
> +                continue;
> +            } else {
> +                return false;
> +            }
> +        }
> +    }
> +    return true;
> +}
> +
> +static int vfio_dma_unmap_bitmap(VFIOContainer *container,
> +                                 hwaddr iova, ram_addr_t size,
> +                                 IOMMUTLBEntry *iotlb)
> +{
> +    struct vfio_iommu_type1_dma_unmap *unmap;
> +    struct vfio_bitmap *bitmap;
> +    uint64_t pages = TARGET_PAGE_ALIGN(size) >> TARGET_PAGE_BITS;
> +    int ret;
> +
> +    unmap = g_malloc0(sizeof(*unmap) + sizeof(*bitmap));
> +    if (!unmap) {
> +        return -ENOMEM;
> +    }

Again that's a fixed size thing so you don't really need to malloc it;
g_malloc0 won't return NULL; it'll just assert (which it shouldn't
do anyway because those structures are small).  Personally I'd just put
it on the stack.

> +    unmap->argsz = sizeof(*unmap) + sizeof(*bitmap);
> +    unmap->iova = iova;
> +    unmap->size = size;
> +    unmap->flags |= VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP;
> +    bitmap = (struct vfio_bitmap *)&unmap->data;
> +
> +    /*
> +     * cpu_physical_memory_set_dirty_lebitmap() expects pages in bitmap of
> +     * TARGET_PAGE_SIZE to mark those dirty. Hence set bitmap_pgsize to
> +     * TARGET_PAGE_SIZE.
> +     */
> +
> +    bitmap->pgsize = TARGET_PAGE_SIZE;
> +    bitmap->size = ROUND_UP(pages, sizeof(__u64) * BITS_PER_BYTE) /
> +                   BITS_PER_BYTE;
> +
> +    if (bitmap->size > container->max_dirty_bitmap_size) {
> +        error_report("UNMAP: Size of bitmap too big 0x%llx", bitmap->size);
> +        ret = -E2BIG;
> +        goto unmap_exit;
> +    }
> +
> +    bitmap->data = g_malloc0(bitmap->size);

That one should be a g_try_malloc0 and check it's non-null.

> +
> +    ret = ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, unmap);
> +    if (!ret) {
> +        cpu_physical_memory_set_dirty_lebitmap((uint64_t *)bitmap->data,
> +                iotlb->translated_addr, pages);
> +    } else {
> +        error_report("VFIO_UNMAP_DMA with DIRTY_BITMAP : %d", -errno);

You're allowed touse %m in hw/vfio for printing the error nicely.

> +    }
> +
> +    g_free(bitmap->data);
> +unmap_exit:
> +    g_free(unmap);
> +    return ret;
> +}
> +
>  /*
>   * DMA - Mapping and unmapping for the "type1" IOMMU interface used on x86
>   */
>  static int vfio_dma_unmap(VFIOContainer *container,
> -                          hwaddr iova, ram_addr_t size)
> +                          hwaddr iova, ram_addr_t size,
> +                          IOMMUTLBEntry *iotlb)
>  {
>      struct vfio_iommu_type1_dma_unmap unmap = {
>          .argsz = sizeof(unmap),
> @@ -324,6 +395,11 @@ static int vfio_dma_unmap(VFIOContainer *container,
>          .size = size,
>      };
>  
> +    if (iotlb && container->dirty_pages_supported &&
> +        vfio_devices_are_running_and_saving()) {
> +        return vfio_dma_unmap_bitmap(container, iova, size, iotlb);
> +    }
> +
>      while (ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, &unmap)) {
>          /*
>           * The type1 backend has an off-by-one bug in the kernel (71a7d3d78e3c
> @@ -371,7 +447,7 @@ static int vfio_dma_map(VFIOContainer *container, hwaddr iova,
>       * the VGA ROM space.
>       */
>      if (ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) == 0 ||
> -        (errno == EBUSY && vfio_dma_unmap(container, iova, size) == 0 &&
> +        (errno == EBUSY && vfio_dma_unmap(container, iova, size, NULL) == 0 &&
>           ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) == 0)) {
>          return 0;
>      }
> @@ -519,7 +595,7 @@ static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
>                           iotlb->addr_mask + 1, vaddr, ret);
>          }
>      } else {
> -        ret = vfio_dma_unmap(container, iova, iotlb->addr_mask + 1);
> +        ret = vfio_dma_unmap(container, iova, iotlb->addr_mask + 1, iotlb);
>          if (ret) {
>              error_report("vfio_dma_unmap(%p, 0x%"HWADDR_PRIx", "
>                           "0x%"HWADDR_PRIx") = %d (%m)",
> @@ -822,7 +898,7 @@ static void vfio_listener_region_del(MemoryListener *listener,
>      }
>  
>      if (try_unmap) {
> -        ret = vfio_dma_unmap(container, iova, int128_get64(llsize));
> +        ret = vfio_dma_unmap(container, iova, int128_get64(llsize), NULL);
>          if (ret) {
>              error_report("vfio_dma_unmap(%p, 0x%"HWADDR_PRIx", "
>                           "0x%"HWADDR_PRIx") = %d (%m)",
> -- 
> 2.7.0
> 
--
Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK