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.
Note: This patch is not yet tested. I'm trying to see how I can test this code path. Suggested-by: Alex Williamson <alex.william...@redhat.com> Signed-off-by: Kirti Wankhede <kwankh...@nvidia.com> Reviewed-by: Neo Jia <c...@nvidia.com> --- hw/vfio/common.c | 83 ++++++++++++++++++++++++++++++++++++++++--- include/hw/vfio/vfio-common.h | 1 + 2 files changed, 80 insertions(+), 4 deletions(-) diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 6d41e1ac5c2f..e0f91841bc82 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -311,11 +311,77 @@ 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; + } + + unmap->argsz = sizeof(*unmap) + sizeof(*bitmap); + 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, 64) / 8; + bitmap->data = g_malloc0(bitmap->size); + if (!bitmap->data) { + error_report("UNMAP: Error allocating bitmap of size 0x%llx", + bitmap->size); + g_free(unmap); + return -ENOMEM; + } + + 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); + } + + g_free(bitmap->data); + 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 +390,11 @@ 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 +442,7 @@ 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 +590,7 @@ 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 +893,7 @@ 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)", @@ -1479,6 +1550,7 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as, container->space = space; container->fd = fd; container->error = NULL; + container->dirty_pages_supported = false; QLIST_INIT(&container->giommu_list); QLIST_INIT(&container->hostwin_list); @@ -1509,6 +1581,9 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as, } vfio_host_win_add(container, 0, (hwaddr)-1, info.iova_pgsizes); container->pgsizes = info.iova_pgsizes; + if (info.flags & VFIO_IOMMU_INFO_DIRTY_PGS) { + container->dirty_pages_supported = true; + } break; } case VFIO_SPAPR_TCE_v2_IOMMU: diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h index c78033e4149d..8ab741463d50 100644 --- a/include/hw/vfio/vfio-common.h +++ b/include/hw/vfio/vfio-common.h @@ -79,6 +79,7 @@ typedef struct VFIOContainer { unsigned iommu_type; Error *error; bool initialized; + bool dirty_pages_supported; unsigned long pgsizes; QLIST_HEAD(, VFIOGuestIOMMU) giommu_list; QLIST_HEAD(, VFIOHostDMAWindow) hostwin_list; -- 2.7.0